mirror of
https://github.com/Bunsly/JobSpy.git
synced 2026-03-05 03:54:31 -08:00
Compare commits
2 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
78c1ec8e9f | ||
|
|
a2dd93aca1 |
@@ -1,7 +0,0 @@
|
||||
repos:
|
||||
- repo: https://github.com/psf/black
|
||||
rev: 24.2.0
|
||||
hooks:
|
||||
- id: black
|
||||
language_version: python
|
||||
args: [--line-length=88, --quiet]
|
||||
124
README.md
124
README.md
@@ -4,14 +4,17 @@
|
||||
|
||||
**Not technical?** Try out the web scraping tool on our site at [usejobspy.com](https://usejobspy.com).
|
||||
|
||||
*Looking to build a data-focused software product?* **[Book a call](https://bunsly.com/)** *to
|
||||
work with us.*
|
||||
*Looking to build a data-focused software product?* **[Book a call](https://calendly.com/bunsly/15min)** *to
|
||||
work with us.*
|
||||
\
|
||||
Check out another project we wrote: ***[HomeHarvest](https://github.com/Bunsly/HomeHarvest)** – a Python package
|
||||
for real estate scraping*
|
||||
|
||||
## Features
|
||||
|
||||
- Scrapes job postings from **LinkedIn**, **Indeed**, **Glassdoor**, & **ZipRecruiter** simultaneously
|
||||
- Scrapes job postings from **LinkedIn**, **Indeed** & **ZipRecruiter** simultaneously
|
||||
- Aggregates the job postings in a Pandas DataFrame
|
||||
- Proxy support
|
||||
- Proxy support (HTTP/S, SOCKS)
|
||||
|
||||
[Video Guide for JobSpy](https://www.youtube.com/watch?v=RuP1HrAZnxs&pp=ygUgam9icyBzY3JhcGVyIGJvdCBsaW5rZWRpbiBpbmRlZWQ%3D) -
|
||||
Updated for release v1.1.3
|
||||
@@ -21,7 +24,7 @@ Updated for release v1.1.3
|
||||
### Installation
|
||||
|
||||
```
|
||||
pip install -U python-jobspy
|
||||
pip install python-jobspy
|
||||
```
|
||||
|
||||
_Python version >= [3.10](https://www.python.org/downloads/release/python-3100/) required_
|
||||
@@ -29,27 +32,24 @@ _Python version >= [3.10](https://www.python.org/downloads/release/python-3100/)
|
||||
### Usage
|
||||
|
||||
```python
|
||||
import csv
|
||||
from jobspy import scrape_jobs
|
||||
|
||||
jobs = scrape_jobs(
|
||||
site_name=["indeed", "linkedin", "zip_recruiter", "glassdoor"],
|
||||
site_name=["indeed", "linkedin", "zip_recruiter"],
|
||||
search_term="software engineer",
|
||||
location="Dallas, TX",
|
||||
results_wanted=20,
|
||||
hours_old=72, # (only Linkedin/Indeed is hour specific, others round up to days old)
|
||||
country_indeed='USA', # only needed for indeed / glassdoor
|
||||
# linkedin_fetch_description=True # get full description and direct job url for linkedin (slower)
|
||||
results_wanted=10,
|
||||
country_indeed='USA' # only needed for indeed
|
||||
)
|
||||
print(f"Found {len(jobs)} jobs")
|
||||
print(jobs.head())
|
||||
jobs.to_csv("jobs.csv", quoting=csv.QUOTE_NONNUMERIC, escapechar="\\", index=False) # to_xlsx
|
||||
jobs.to_csv("jobs.csv", index=False) # / to_xlsx
|
||||
```
|
||||
|
||||
### Output
|
||||
|
||||
```
|
||||
SITE TITLE COMPANY CITY STATE JOB_TYPE INTERVAL MIN_AMOUNT MAX_AMOUNT JOB_URL DESCRIPTION
|
||||
SITE TITLE COMPANY_NAME CITY STATE JOB_TYPE INTERVAL MIN_AMOUNT MAX_AMOUNT JOB_URL DESCRIPTION
|
||||
indeed Software Engineer AMERICAN SYSTEMS Arlington VA None yearly 200000 150000 https://www.indeed.com/viewjob?jk=5e409e577046... THIS POSITION COMES WITH A 10K SIGNING BONUS!...
|
||||
indeed Senior Software Engineer TherapyNotes.com Philadelphia PA fulltime yearly 135000 110000 https://www.indeed.com/viewjob?jk=da39574a40cb... About Us TherapyNotes is the national leader i...
|
||||
linkedin Software Engineer - Early Career Lockheed Martin Sunnyvale CA fulltime yearly None None https://www.linkedin.com/jobs/view/3693012711 Description:By bringing together people that u...
|
||||
@@ -61,24 +61,19 @@ zip_recruiter Software Developer TEKsystems Phoenix
|
||||
### Parameters for `scrape_jobs()`
|
||||
|
||||
```plaintext
|
||||
Required
|
||||
├── site_type (List[enum]): linkedin, zip_recruiter, indeed
|
||||
└── search_term (str)
|
||||
Optional
|
||||
├── site_name (list|str): linkedin, zip_recruiter, indeed, glassdoor (default is all four)
|
||||
├── search_term (str)
|
||||
├── location (str)
|
||||
├── distance (int): in miles, default 50
|
||||
├── job_type (str): fulltime, parttime, internship, contract
|
||||
├── proxy (str): in format 'http://user:pass@host:port'
|
||||
├── location (int)
|
||||
├── distance (int): in miles
|
||||
├── job_type (enum): fulltime, parttime, internship, contract
|
||||
├── proxy (str): in format 'http://user:pass@host:port' or [https, socks]
|
||||
├── is_remote (bool)
|
||||
├── results_wanted (int): number of job results to retrieve for each site specified in 'site_name'
|
||||
├── easy_apply (bool): filters for jobs that are hosted on the job board site (LinkedIn & Indeed do not allow pairing this with hours_old)
|
||||
├── linkedin_fetch_description (bool): fetches full description and direct job url for LinkedIn (slower)
|
||||
├── linkedin_company_ids (list[int]): searches for linkedin jobs with specific company ids
|
||||
├── description_format (str): markdown, html (Format type of the job descriptions. Default is markdown.)
|
||||
├── country_indeed (str): filters the country on Indeed (see below for correct spelling)
|
||||
├── offset (int): starts the search from an offset (e.g. 25 will start the search from the 25th result)
|
||||
├── hours_old (int): filters jobs by the number of hours since the job was posted (ZipRecruiter and Glassdoor round up to next day. If you use this on Indeed, it will not filter by job_type/is_remote/easy_apply)
|
||||
├── verbose (int) {0, 1, 2}: Controls the verbosity of the runtime printouts (0 prints only errors, 1 is errors+warnings, 2 is all logs. Default is 2.)
|
||||
├── hyperlinks (bool): Whether to turn `job_url`s into hyperlinks. Default is false.
|
||||
├── results_wanted (int): number of job results to retrieve for each site specified in 'site_type'
|
||||
├── easy_apply (bool): filters for jobs that are hosted on LinkedIn
|
||||
├── country_indeed (enum): filters the country on Indeed (see below for correct spelling)
|
||||
├── offset (num): starts the search from an offset (e.g. 25 will start the search from the 25th result)
|
||||
```
|
||||
|
||||
### JobPost Schema
|
||||
@@ -87,7 +82,6 @@ Optional
|
||||
JobPost
|
||||
├── title (str)
|
||||
├── company (str)
|
||||
├── company_url (str)
|
||||
├── job_url (str)
|
||||
├── location (object)
|
||||
│ ├── country (str)
|
||||
@@ -102,62 +96,53 @@ JobPost
|
||||
│ └── currency (enum)
|
||||
└── date_posted (date)
|
||||
└── emails (str)
|
||||
└── num_urgent_words (int)
|
||||
└── is_remote (bool)
|
||||
|
||||
Indeed specific
|
||||
├── company_country (str)
|
||||
└── company_addresses (str)
|
||||
└── company_industry (str)
|
||||
└── company_employees_label (str)
|
||||
└── company_revenue_label (str)
|
||||
└── company_description (str)
|
||||
└── ceo_name (str)
|
||||
└── ceo_photo_url (str)
|
||||
└── logo_photo_url (str)
|
||||
└── banner_photo_url (str)
|
||||
```
|
||||
|
||||
### Exceptions
|
||||
|
||||
The following exceptions may be raised when using JobSpy:
|
||||
|
||||
* `LinkedInException`
|
||||
* `IndeedException`
|
||||
* `ZipRecruiterException`
|
||||
|
||||
## Supported Countries for Job Searching
|
||||
|
||||
### **LinkedIn**
|
||||
|
||||
LinkedIn searches globally & uses only the `location` parameter.
|
||||
LinkedIn searches globally & uses only the `location` parameter.
|
||||
|
||||
### **ZipRecruiter**
|
||||
|
||||
ZipRecruiter searches for jobs in **US/Canada** & uses only the `location` parameter.
|
||||
|
||||
### **Indeed / Glassdoor**
|
||||
### **Indeed**
|
||||
|
||||
Indeed & Glassdoor supports most countries, but the `country_indeed` parameter is required. Additionally, use the `location`
|
||||
parameter to narrow down the location, e.g. city & state if necessary.
|
||||
Indeed supports most countries, but the `country_indeed` parameter is required. Additionally, use the `location`
|
||||
parameter to narrow down the location, e.g. city & state if necessary.
|
||||
|
||||
You can specify the following countries when searching on Indeed (use the exact name, * indicates support for Glassdoor):
|
||||
You can specify the following countries when searching on Indeed (use the exact name):
|
||||
|
||||
| | | | |
|
||||
|----------------------|--------------|------------|----------------|
|
||||
| Argentina | Australia* | Austria* | Bahrain |
|
||||
| Belgium* | Brazil* | Canada* | Chile |
|
||||
| Argentina | Australia | Austria | Bahrain |
|
||||
| Belgium | Brazil | Canada | Chile |
|
||||
| China | Colombia | Costa Rica | Czech Republic |
|
||||
| Denmark | Ecuador | Egypt | Finland |
|
||||
| France* | Germany* | Greece | Hong Kong* |
|
||||
| Hungary | India* | Indonesia | Ireland* |
|
||||
| Israel | Italy* | Japan | Kuwait |
|
||||
| Luxembourg | Malaysia | Mexico* | Morocco |
|
||||
| Netherlands* | New Zealand* | Nigeria | Norway |
|
||||
| France | Germany | Greece | Hong Kong |
|
||||
| Hungary | India | Indonesia | Ireland |
|
||||
| Israel | Italy | Japan | Kuwait |
|
||||
| Luxembourg | Malaysia | Mexico | Morocco |
|
||||
| Netherlands | New Zealand | Nigeria | Norway |
|
||||
| Oman | Pakistan | Panama | Peru |
|
||||
| Philippines | Poland | Portugal | Qatar |
|
||||
| Romania | Saudi Arabia | Singapore* | South Africa |
|
||||
| South Korea | Spain* | Sweden | Switzerland* |
|
||||
| Romania | Saudi Arabia | Singapore | South Africa |
|
||||
| South Korea | Spain | Sweden | Switzerland |
|
||||
| Taiwan | Thailand | Turkey | Ukraine |
|
||||
| United Arab Emirates | UK* | USA* | Uruguay |
|
||||
| Venezuela | Vietnam* | | |
|
||||
|
||||
|
||||
## Notes
|
||||
* Indeed is the best scraper currently with no rate limiting.
|
||||
* All the job board endpoints are capped at around 1000 jobs on a given search.
|
||||
* LinkedIn is the most restrictive and usually rate limits around the 10th page.
|
||||
| United Arab Emirates | UK | USA | Uruguay |
|
||||
| Venezuela | Vietnam | | |
|
||||
|
||||
## Frequently Asked Questions
|
||||
|
||||
@@ -172,7 +157,16 @@ persist, [submit an issue](https://github.com/Bunsly/JobSpy/issues).
|
||||
**Q: Received a response code 429?**
|
||||
**A:** This indicates that you have been blocked by the job board site for sending too many requests. All of the job board sites are aggressive with blocking. We recommend:
|
||||
|
||||
- Waiting some time between scrapes (site-dependent).
|
||||
- Waiting a few seconds between requests.
|
||||
- Trying a VPN or proxy to change your IP address.
|
||||
|
||||
---
|
||||
|
||||
**Q: Experiencing a "Segmentation fault: 11" on macOS Catalina?**
|
||||
**A:** This is due to `tls_client` dependency not supporting your architecture. Solutions and workarounds include:
|
||||
|
||||
- Upgrade to a newer version of MacOS
|
||||
- Reach out to the maintainers of [tls_client](https://github.com/bogdanfinn/tls-client) for fixes
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -2,11 +2,12 @@ from jobspy import scrape_jobs
|
||||
import pandas as pd
|
||||
|
||||
jobs: pd.DataFrame = scrape_jobs(
|
||||
site_name=["indeed", "linkedin", "zip_recruiter", "glassdoor"],
|
||||
site_name=["indeed", "linkedin", "zip_recruiter"],
|
||||
search_term="software engineer",
|
||||
location="Dallas, TX",
|
||||
results_wanted=25, # be wary the higher it is, the more likey you'll get blocked (rotating proxy can help tho)
|
||||
results_wanted=50, # be wary the higher it is, the more likey you'll get blocked (rotating proxy should work tho)
|
||||
country_indeed="USA",
|
||||
offset=25 # start jobs from an offset (use if search failed and want to continue)
|
||||
# proxy="http://jobspy:5a4vpWtj8EeJ2hoYzk@ca.smartproxy.com:20001",
|
||||
)
|
||||
|
||||
@@ -1,78 +0,0 @@
|
||||
from jobspy import scrape_jobs
|
||||
import pandas as pd
|
||||
import os
|
||||
import time
|
||||
|
||||
# creates csv a new filename if the jobs.csv already exists.
|
||||
csv_filename = "jobs.csv"
|
||||
counter = 1
|
||||
while os.path.exists(csv_filename):
|
||||
csv_filename = f"jobs_{counter}.csv"
|
||||
counter += 1
|
||||
|
||||
# results wanted and offset
|
||||
results_wanted = 1000
|
||||
offset = 0
|
||||
|
||||
all_jobs = []
|
||||
|
||||
# max retries
|
||||
max_retries = 3
|
||||
|
||||
# nuumber of results at each iteration
|
||||
results_in_each_iteration = 30
|
||||
|
||||
while len(all_jobs) < results_wanted:
|
||||
retry_count = 0
|
||||
while retry_count < max_retries:
|
||||
print("Doing from", offset, "to", offset + results_in_each_iteration, "jobs")
|
||||
try:
|
||||
jobs = scrape_jobs(
|
||||
site_name=["indeed"],
|
||||
search_term="software engineer",
|
||||
# New York, NY
|
||||
# Dallas, TX
|
||||
# Los Angeles, CA
|
||||
location="Los Angeles, CA",
|
||||
results_wanted=min(
|
||||
results_in_each_iteration, results_wanted - len(all_jobs)
|
||||
),
|
||||
country_indeed="USA",
|
||||
offset=offset,
|
||||
# proxy="http://jobspy:5a4vpWtj8EeJ2hoYzk@ca.smartproxy.com:20001",
|
||||
)
|
||||
|
||||
# Add the scraped jobs to the list
|
||||
all_jobs.extend(jobs.to_dict("records"))
|
||||
|
||||
# Increment the offset for the next page of results
|
||||
offset += results_in_each_iteration
|
||||
|
||||
# Add a delay to avoid rate limiting (you can adjust the delay time as needed)
|
||||
print(f"Scraped {len(all_jobs)} jobs")
|
||||
print("Sleeping secs", 100 * (retry_count + 1))
|
||||
time.sleep(100 * (retry_count + 1)) # Sleep for 2 seconds between requests
|
||||
|
||||
break # Break out of the retry loop if successful
|
||||
except Exception as e:
|
||||
print(f"Error: {e}")
|
||||
retry_count += 1
|
||||
print("Sleeping secs before retry", 100 * (retry_count + 1))
|
||||
time.sleep(100 * (retry_count + 1))
|
||||
if retry_count >= max_retries:
|
||||
print("Max retries reached. Exiting.")
|
||||
break
|
||||
|
||||
# DataFrame from the collected job data
|
||||
jobs_df = pd.DataFrame(all_jobs)
|
||||
|
||||
# Formatting
|
||||
pd.set_option("display.max_columns", None)
|
||||
pd.set_option("display.max_rows", None)
|
||||
pd.set_option("display.width", None)
|
||||
pd.set_option("display.max_colwidth", 50)
|
||||
|
||||
print(jobs_df)
|
||||
|
||||
jobs_df.to_csv(csv_filename, index=False)
|
||||
print(f"Outputted to {csv_filename}")
|
||||
2217
poetry.lock
generated
2217
poetry.lock
generated
File diff suppressed because it is too large
Load Diff
@@ -1,7 +1,7 @@
|
||||
[tool.poetry]
|
||||
name = "python-jobspy"
|
||||
version = "1.1.53"
|
||||
description = "Job scraper for LinkedIn, Indeed, Glassdoor & ZipRecruiter"
|
||||
version = "1.1.16"
|
||||
description = "Job scraper for LinkedIn, Indeed & ZipRecruiter"
|
||||
authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
|
||||
homepage = "https://github.com/Bunsly/JobSpy"
|
||||
readme = "README.md"
|
||||
@@ -13,24 +13,17 @@ packages = [
|
||||
[tool.poetry.dependencies]
|
||||
python = "^3.10"
|
||||
requests = "^2.31.0"
|
||||
tls-client = "^0.2.1"
|
||||
beautifulsoup4 = "^4.12.2"
|
||||
pandas = "^2.1.0"
|
||||
NUMPY = "1.24.2"
|
||||
pydantic = "^2.3.0"
|
||||
tls-client = "^1.0.1"
|
||||
markdownify = "^0.11.6"
|
||||
regex = "^2024.4.28"
|
||||
|
||||
|
||||
[tool.poetry.group.dev.dependencies]
|
||||
pytest = "^7.4.1"
|
||||
jupyter = "^1.0.0"
|
||||
black = "*"
|
||||
pre-commit = "*"
|
||||
|
||||
[build-system]
|
||||
requires = ["poetry-core"]
|
||||
build-backend = "poetry.core.masonry.api"
|
||||
|
||||
[tool.black]
|
||||
line-length = 88
|
||||
|
||||
@@ -1,58 +1,48 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import pandas as pd
|
||||
from typing import Tuple
|
||||
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||||
import concurrent.futures
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
from typing import Tuple, Optional
|
||||
|
||||
from .jobs import JobType, Location
|
||||
from .scrapers.utils import logger, set_logger_level
|
||||
from .scrapers.indeed import IndeedScraper
|
||||
from .scrapers.ziprecruiter import ZipRecruiterScraper
|
||||
from .scrapers.glassdoor import GlassdoorScraper
|
||||
from .scrapers.linkedin import LinkedInScraper
|
||||
from .scrapers import ScraperInput, Site, JobResponse, Country
|
||||
from .scrapers.exceptions import (
|
||||
LinkedInException,
|
||||
IndeedException,
|
||||
ZipRecruiterException,
|
||||
GlassdoorException,
|
||||
)
|
||||
|
||||
SCRAPER_MAPPING = {
|
||||
Site.LINKEDIN: LinkedInScraper,
|
||||
Site.INDEED: IndeedScraper,
|
||||
Site.ZIP_RECRUITER: ZipRecruiterScraper,
|
||||
}
|
||||
|
||||
|
||||
def _map_str_to_site(site_name: str) -> Site:
|
||||
return Site[site_name.upper()]
|
||||
|
||||
|
||||
def scrape_jobs(
|
||||
site_name: str | list[str] | Site | list[Site] | None = None,
|
||||
search_term: str | None = None,
|
||||
location: str | None = None,
|
||||
distance: int | None = 50,
|
||||
site_name: str | list[str] | Site | list[Site],
|
||||
search_term: str,
|
||||
location: str = "",
|
||||
distance: int = None,
|
||||
is_remote: bool = False,
|
||||
job_type: str | None = None,
|
||||
easy_apply: bool | None = None,
|
||||
job_type: str = None,
|
||||
easy_apply: bool = False, # linkedin
|
||||
results_wanted: int = 15,
|
||||
country_indeed: str = "usa",
|
||||
hyperlinks: bool = False,
|
||||
proxy: str | None = None,
|
||||
description_format: str = "markdown",
|
||||
linkedin_fetch_description: bool | None = False,
|
||||
linkedin_company_ids: list[int] | None = None,
|
||||
offset: int | None = 0,
|
||||
hours_old: int = None,
|
||||
verbose: int = 2,
|
||||
**kwargs,
|
||||
proxy: Optional[str] = None,
|
||||
offset: Optional[int] = 0,
|
||||
) -> pd.DataFrame:
|
||||
"""
|
||||
Simultaneously scrapes job data from multiple job sites.
|
||||
:return: pandas dataframe containing job data
|
||||
:return: results_wanted: pandas dataframe containing job data
|
||||
"""
|
||||
SCRAPER_MAPPING = {
|
||||
Site.LINKEDIN: LinkedInScraper,
|
||||
Site.INDEED: IndeedScraper,
|
||||
Site.ZIP_RECRUITER: ZipRecruiterScraper,
|
||||
Site.GLASSDOOR: GlassdoorScraper,
|
||||
}
|
||||
set_logger_level(verbose)
|
||||
|
||||
def map_str_to_site(site_name: str) -> Site:
|
||||
return Site[site_name.upper()]
|
||||
|
||||
def get_enum_from_value(value_str):
|
||||
for job_type in JobType:
|
||||
@@ -62,23 +52,18 @@ def scrape_jobs(
|
||||
|
||||
job_type = get_enum_from_value(job_type) if job_type else None
|
||||
|
||||
def get_site_type():
|
||||
site_types = list(Site)
|
||||
if isinstance(site_name, str):
|
||||
site_types = [map_str_to_site(site_name)]
|
||||
elif isinstance(site_name, Site):
|
||||
site_types = [site_name]
|
||||
elif isinstance(site_name, list):
|
||||
site_types = [
|
||||
map_str_to_site(site) if isinstance(site, str) else site
|
||||
for site in site_name
|
||||
]
|
||||
return site_types
|
||||
if type(site_name) == str:
|
||||
site_type = [_map_str_to_site(site_name)]
|
||||
else: #: if type(site_name) == list
|
||||
site_type = [
|
||||
_map_str_to_site(site) if type(site) == str else site_name
|
||||
for site in site_name
|
||||
]
|
||||
|
||||
country_enum = Country.from_string(country_indeed)
|
||||
|
||||
scraper_input = ScraperInput(
|
||||
site_type=get_site_type(),
|
||||
site_type=site_type,
|
||||
country=country_enum,
|
||||
search_term=search_term,
|
||||
location=location,
|
||||
@@ -86,21 +71,27 @@ def scrape_jobs(
|
||||
is_remote=is_remote,
|
||||
job_type=job_type,
|
||||
easy_apply=easy_apply,
|
||||
description_format=description_format,
|
||||
linkedin_fetch_description=linkedin_fetch_description,
|
||||
results_wanted=results_wanted,
|
||||
linkedin_company_ids=linkedin_company_ids,
|
||||
offset=offset,
|
||||
hours_old=hours_old,
|
||||
)
|
||||
|
||||
def scrape_site(site: Site) -> Tuple[str, JobResponse]:
|
||||
scraper_class = SCRAPER_MAPPING[site]
|
||||
scraper = scraper_class(proxy=proxy)
|
||||
scraped_data: JobResponse = scraper.scrape(scraper_input)
|
||||
cap_name = site.value.capitalize()
|
||||
site_name = "ZipRecruiter" if cap_name == "Zip_recruiter" else cap_name
|
||||
logger.info(f"{site_name} finished scraping")
|
||||
|
||||
try:
|
||||
scraped_data: JobResponse = scraper.scrape(scraper_input)
|
||||
except (LinkedInException, IndeedException, ZipRecruiterException) as lie:
|
||||
raise lie
|
||||
except Exception as e:
|
||||
if site == Site.LINKEDIN:
|
||||
raise LinkedInException(str(e))
|
||||
if site == Site.INDEED:
|
||||
raise IndeedException(str(e))
|
||||
if site == Site.ZIP_RECRUITER:
|
||||
raise ZipRecruiterException(str(e))
|
||||
else:
|
||||
raise e
|
||||
return site.value, scraped_data
|
||||
|
||||
site_to_jobs_dict = {}
|
||||
@@ -114,7 +105,7 @@ def scrape_jobs(
|
||||
executor.submit(worker, site): site for site in scraper_input.site_type
|
||||
}
|
||||
|
||||
for future in as_completed(future_to_site):
|
||||
for future in concurrent.futures.as_completed(future_to_site):
|
||||
site_value, scraped_data = future.result()
|
||||
site_to_jobs_dict[site_value] = scraped_data
|
||||
|
||||
@@ -123,8 +114,9 @@ def scrape_jobs(
|
||||
for site, job_response in site_to_jobs_dict.items():
|
||||
for job in job_response.jobs:
|
||||
job_data = job.dict()
|
||||
job_url = job_data["job_url"]
|
||||
job_data["job_url_hyper"] = f'<a href="{job_url}">{job_url}</a>'
|
||||
job_data[
|
||||
"job_url_hyper"
|
||||
] = f'<a href="{job_data["job_url"]}">{job_data["job_url"]}</a>'
|
||||
job_data["site"] = site
|
||||
job_data["company"] = job_data["company_name"]
|
||||
job_data["job_type"] = (
|
||||
@@ -135,10 +127,7 @@ def scrape_jobs(
|
||||
job_data["emails"] = (
|
||||
", ".join(job_data["emails"]) if job_data["emails"] else None
|
||||
)
|
||||
if job_data["location"]:
|
||||
job_data["location"] = Location(
|
||||
**job_data["location"]
|
||||
).display_location()
|
||||
job_data["location"] = Location(**job_data["location"]).display_location()
|
||||
|
||||
compensation_obj = job_data.get("compensation")
|
||||
if compensation_obj and isinstance(compensation_obj, dict):
|
||||
@@ -160,18 +149,10 @@ def scrape_jobs(
|
||||
jobs_dfs.append(job_df)
|
||||
|
||||
if jobs_dfs:
|
||||
# Step 1: Filter out all-NA columns from each DataFrame before concatenation
|
||||
filtered_dfs = [df.dropna(axis=1, how="all") for df in jobs_dfs]
|
||||
|
||||
# Step 2: Concatenate the filtered DataFrames
|
||||
jobs_df = pd.concat(filtered_dfs, ignore_index=True)
|
||||
|
||||
# Desired column order
|
||||
desired_order = [
|
||||
"id",
|
||||
"site",
|
||||
jobs_df = pd.concat(jobs_dfs, ignore_index=True)
|
||||
desired_order: list[str] = [
|
||||
"job_url_hyper" if hyperlinks else "job_url",
|
||||
"job_url_direct",
|
||||
"site",
|
||||
"title",
|
||||
"company",
|
||||
"location",
|
||||
@@ -182,30 +163,13 @@ def scrape_jobs(
|
||||
"max_amount",
|
||||
"currency",
|
||||
"is_remote",
|
||||
"num_urgent_words",
|
||||
"benefits",
|
||||
"emails",
|
||||
"description",
|
||||
"company_url",
|
||||
"company_url_direct",
|
||||
"company_addresses",
|
||||
"company_industry",
|
||||
"company_num_employees",
|
||||
"company_revenue",
|
||||
"company_description",
|
||||
"logo_photo_url",
|
||||
"banner_photo_url",
|
||||
"ceo_name",
|
||||
"ceo_photo_url",
|
||||
]
|
||||
|
||||
# Step 3: Ensure all desired columns are present, adding missing ones as empty
|
||||
for column in desired_order:
|
||||
if column not in jobs_df.columns:
|
||||
jobs_df[column] = None # Add missing columns as empty
|
||||
|
||||
# Reorder the DataFrame according to the desired order
|
||||
jobs_df = jobs_df[desired_order]
|
||||
|
||||
# Step 4: Sort the DataFrame as required
|
||||
return jobs_df.sort_values(by=["site", "date_posted"], ascending=[True, False])
|
||||
jobs_formatted_df = jobs_df[desired_order]
|
||||
else:
|
||||
return pd.DataFrame()
|
||||
jobs_formatted_df = pd.DataFrame()
|
||||
|
||||
return jobs_formatted_df
|
||||
|
||||
@@ -1,9 +1,8 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Optional
|
||||
from typing import Union, Optional
|
||||
from datetime import date
|
||||
from enum import Enum
|
||||
from pydantic import BaseModel
|
||||
|
||||
from pydantic import BaseModel, validator
|
||||
|
||||
|
||||
class JobType(Enum):
|
||||
@@ -57,46 +56,40 @@ class JobType(Enum):
|
||||
|
||||
|
||||
class Country(Enum):
|
||||
"""
|
||||
Gets the subdomain for Indeed and Glassdoor.
|
||||
The second item in the tuple is the subdomain (and API country code if there's a ':' separator) for Indeed
|
||||
The third item in the tuple is the subdomain (and tld if there's a ':' separator) for Glassdoor
|
||||
"""
|
||||
|
||||
ARGENTINA = ("argentina", "ar", "com.ar")
|
||||
AUSTRALIA = ("australia", "au", "com.au")
|
||||
AUSTRIA = ("austria", "at", "at")
|
||||
ARGENTINA = ("argentina", "ar")
|
||||
AUSTRALIA = ("australia", "au")
|
||||
AUSTRIA = ("austria", "at")
|
||||
BAHRAIN = ("bahrain", "bh")
|
||||
BELGIUM = ("belgium", "be", "fr:be")
|
||||
BRAZIL = ("brazil", "br", "com.br")
|
||||
CANADA = ("canada", "ca", "ca")
|
||||
BELGIUM = ("belgium", "be")
|
||||
BRAZIL = ("brazil", "br")
|
||||
CANADA = ("canada", "ca")
|
||||
CHILE = ("chile", "cl")
|
||||
CHINA = ("china", "cn")
|
||||
COLOMBIA = ("colombia", "co")
|
||||
COSTARICA = ("costa rica", "cr")
|
||||
CZECHREPUBLIC = ("czech republic,czechia", "cz")
|
||||
CZECHREPUBLIC = ("czech republic", "cz")
|
||||
DENMARK = ("denmark", "dk")
|
||||
ECUADOR = ("ecuador", "ec")
|
||||
EGYPT = ("egypt", "eg")
|
||||
FINLAND = ("finland", "fi")
|
||||
FRANCE = ("france", "fr", "fr")
|
||||
GERMANY = ("germany", "de", "de")
|
||||
FRANCE = ("france", "fr")
|
||||
GERMANY = ("germany", "de")
|
||||
GREECE = ("greece", "gr")
|
||||
HONGKONG = ("hong kong", "hk", "com.hk")
|
||||
HONGKONG = ("hong kong", "hk")
|
||||
HUNGARY = ("hungary", "hu")
|
||||
INDIA = ("india", "in", "co.in")
|
||||
INDIA = ("india", "in")
|
||||
INDONESIA = ("indonesia", "id")
|
||||
IRELAND = ("ireland", "ie", "ie")
|
||||
IRELAND = ("ireland", "ie")
|
||||
ISRAEL = ("israel", "il")
|
||||
ITALY = ("italy", "it", "it")
|
||||
ITALY = ("italy", "it")
|
||||
JAPAN = ("japan", "jp")
|
||||
KUWAIT = ("kuwait", "kw")
|
||||
LUXEMBOURG = ("luxembourg", "lu")
|
||||
MALAYSIA = ("malaysia", "malaysia")
|
||||
MEXICO = ("mexico", "mx", "com.mx")
|
||||
MEXICO = ("mexico", "mx")
|
||||
MOROCCO = ("morocco", "ma")
|
||||
NETHERLANDS = ("netherlands", "nl", "nl")
|
||||
NEWZEALAND = ("new zealand", "nz", "co.nz")
|
||||
NETHERLANDS = ("netherlands", "nl")
|
||||
NEWZEALAND = ("new zealand", "nz")
|
||||
NIGERIA = ("nigeria", "ng")
|
||||
NORWAY = ("norway", "no")
|
||||
OMAN = ("oman", "om")
|
||||
@@ -109,66 +102,54 @@ class Country(Enum):
|
||||
QATAR = ("qatar", "qa")
|
||||
ROMANIA = ("romania", "ro")
|
||||
SAUDIARABIA = ("saudi arabia", "sa")
|
||||
SINGAPORE = ("singapore", "sg", "sg")
|
||||
SINGAPORE = ("singapore", "sg")
|
||||
SOUTHAFRICA = ("south africa", "za")
|
||||
SOUTHKOREA = ("south korea", "kr")
|
||||
SPAIN = ("spain", "es", "es")
|
||||
SPAIN = ("spain", "es")
|
||||
SWEDEN = ("sweden", "se")
|
||||
SWITZERLAND = ("switzerland", "ch", "de:ch")
|
||||
SWITZERLAND = ("switzerland", "ch")
|
||||
TAIWAN = ("taiwan", "tw")
|
||||
THAILAND = ("thailand", "th")
|
||||
TURKEY = ("turkey", "tr")
|
||||
UKRAINE = ("ukraine", "ua")
|
||||
UNITEDARABEMIRATES = ("united arab emirates", "ae")
|
||||
UK = ("uk,united kingdom", "uk:gb", "co.uk")
|
||||
USA = ("usa,us,united states", "www:us", "com")
|
||||
UK = ("uk", "uk")
|
||||
USA = ("usa", "www")
|
||||
URUGUAY = ("uruguay", "uy")
|
||||
VENEZUELA = ("venezuela", "ve")
|
||||
VIETNAM = ("vietnam", "vn", "com")
|
||||
VIETNAM = ("vietnam", "vn")
|
||||
|
||||
# internal for ziprecruiter
|
||||
US_CANADA = ("usa/ca", "www")
|
||||
|
||||
# internal for linkedin
|
||||
# internal for linkeind
|
||||
WORLDWIDE = ("worldwide", "www")
|
||||
|
||||
@property
|
||||
def indeed_domain_value(self):
|
||||
subdomain, _, api_country_code = self.value[1].partition(":")
|
||||
if subdomain and api_country_code:
|
||||
return subdomain, api_country_code.upper()
|
||||
return self.value[1], self.value[1].upper()
|
||||
def __new__(cls, country, domain):
|
||||
obj = object.__new__(cls)
|
||||
obj._value_ = country
|
||||
obj.domain = domain
|
||||
return obj
|
||||
|
||||
@property
|
||||
def glassdoor_domain_value(self):
|
||||
if len(self.value) == 3:
|
||||
subdomain, _, domain = self.value[2].partition(":")
|
||||
if subdomain and domain:
|
||||
return f"{subdomain}.glassdoor.{domain}"
|
||||
else:
|
||||
return f"www.glassdoor.{self.value[2]}"
|
||||
else:
|
||||
raise Exception(f"Glassdoor is not available for {self.name}")
|
||||
|
||||
def get_glassdoor_url(self):
|
||||
return f"https://{self.glassdoor_domain_value}/"
|
||||
def domain_value(self):
|
||||
return self.domain
|
||||
|
||||
@classmethod
|
||||
def from_string(cls, country_str: str):
|
||||
"""Convert a string to the corresponding Country enum."""
|
||||
country_str = country_str.strip().lower()
|
||||
for country in cls:
|
||||
country_names = country.value[0].split(",")
|
||||
if country_str in country_names:
|
||||
if country.value == country_str:
|
||||
return country
|
||||
valid_countries = [country.value for country in cls]
|
||||
raise ValueError(
|
||||
f"Invalid country string: '{country_str}'. Valid countries are: {', '.join([country[0] for country in valid_countries])}"
|
||||
f"Invalid country string: '{country_str}'. Valid countries (only include this param for Indeed) are: {', '.join(valid_countries)}"
|
||||
)
|
||||
|
||||
|
||||
class Location(BaseModel):
|
||||
country: Country | str | None = None
|
||||
country: Country = None
|
||||
city: Optional[str] = None
|
||||
state: Optional[str] = None
|
||||
|
||||
@@ -178,19 +159,11 @@ class Location(BaseModel):
|
||||
location_parts.append(self.city)
|
||||
if self.state:
|
||||
location_parts.append(self.state)
|
||||
if isinstance(self.country, str):
|
||||
location_parts.append(self.country)
|
||||
elif self.country and self.country not in (
|
||||
Country.US_CANADA,
|
||||
Country.WORLDWIDE,
|
||||
):
|
||||
country_name = self.country.value[0]
|
||||
if "," in country_name:
|
||||
country_name = country_name.split(",")[0]
|
||||
if country_name in ("usa", "uk"):
|
||||
location_parts.append(country_name.upper())
|
||||
if self.country and self.country not in (Country.US_CANADA, Country.WORLDWIDE):
|
||||
if self.country.value in ("usa", "uk"):
|
||||
location_parts.append(self.country.value.upper())
|
||||
else:
|
||||
location_parts.append(country_name.title())
|
||||
location_parts.append(self.country.value.title())
|
||||
return ", ".join(location_parts)
|
||||
|
||||
|
||||
@@ -201,58 +174,29 @@ class CompensationInterval(Enum):
|
||||
DAILY = "daily"
|
||||
HOURLY = "hourly"
|
||||
|
||||
@classmethod
|
||||
def get_interval(cls, pay_period):
|
||||
interval_mapping = {
|
||||
"YEAR": cls.YEARLY,
|
||||
"HOUR": cls.HOURLY,
|
||||
}
|
||||
if pay_period in interval_mapping:
|
||||
return interval_mapping[pay_period].value
|
||||
else:
|
||||
return cls[pay_period].value if pay_period in cls.__members__ else None
|
||||
|
||||
|
||||
class Compensation(BaseModel):
|
||||
interval: Optional[CompensationInterval] = None
|
||||
min_amount: float | None = None
|
||||
max_amount: float | None = None
|
||||
min_amount: int | None = None
|
||||
max_amount: int | None = None
|
||||
currency: Optional[str] = "USD"
|
||||
|
||||
|
||||
class DescriptionFormat(Enum):
|
||||
MARKDOWN = "markdown"
|
||||
HTML = "html"
|
||||
|
||||
|
||||
class JobPost(BaseModel):
|
||||
id: str | None = None
|
||||
title: str
|
||||
company_name: str | None
|
||||
company_name: str
|
||||
job_url: str
|
||||
job_url_direct: str | None = None
|
||||
location: Optional[Location]
|
||||
|
||||
description: str | None = None
|
||||
company_url: str | None = None
|
||||
company_url_direct: str | None = None
|
||||
|
||||
job_type: list[JobType] | None = None
|
||||
compensation: Compensation | None = None
|
||||
date_posted: date | None = None
|
||||
benefits: str | None = None
|
||||
emails: list[str] | None = None
|
||||
num_urgent_words: int | None = None
|
||||
is_remote: bool | None = None
|
||||
|
||||
# indeed specific
|
||||
company_addresses: str | None = None
|
||||
company_industry: str | None = None
|
||||
company_num_employees: str | None = None
|
||||
company_revenue: str | None = None
|
||||
company_description: str | None = None
|
||||
ceo_name: str | None = None
|
||||
ceo_photo_url: str | None = None
|
||||
logo_photo_url: str | None = None
|
||||
banner_photo_url: str | None = None
|
||||
# company_industry: str | None = None
|
||||
|
||||
|
||||
class JobResponse(BaseModel):
|
||||
|
||||
@@ -1,47 +1,32 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from abc import ABC, abstractmethod
|
||||
|
||||
from ..jobs import (
|
||||
Enum,
|
||||
BaseModel,
|
||||
JobType,
|
||||
JobResponse,
|
||||
Country,
|
||||
DescriptionFormat,
|
||||
)
|
||||
from ..jobs import Enum, BaseModel, JobType, JobResponse, Country
|
||||
from typing import List, Optional, Any
|
||||
|
||||
|
||||
class Site(Enum):
|
||||
LINKEDIN = "linkedin"
|
||||
INDEED = "indeed"
|
||||
ZIP_RECRUITER = "zip_recruiter"
|
||||
GLASSDOOR = "glassdoor"
|
||||
|
||||
|
||||
class ScraperInput(BaseModel):
|
||||
site_type: list[Site]
|
||||
search_term: str | None = None
|
||||
site_type: List[Site]
|
||||
search_term: str
|
||||
|
||||
location: str | None = None
|
||||
country: Country | None = Country.USA
|
||||
distance: int | None = None
|
||||
location: str = None
|
||||
country: Optional[Country] = Country.USA
|
||||
distance: Optional[int] = None
|
||||
is_remote: bool = False
|
||||
job_type: JobType | None = None
|
||||
easy_apply: bool | None = None
|
||||
job_type: Optional[JobType] = None
|
||||
easy_apply: bool = None # linkedin
|
||||
offset: int = 0
|
||||
linkedin_fetch_description: bool = False
|
||||
linkedin_company_ids: list[int] | None = None
|
||||
description_format: DescriptionFormat | None = DescriptionFormat.MARKDOWN
|
||||
|
||||
results_wanted: int = 15
|
||||
hours_old: int | None = None
|
||||
|
||||
|
||||
class Scraper(ABC):
|
||||
def __init__(self, site: Site, proxy: list[str] | None = None):
|
||||
class Scraper:
|
||||
def __init__(self, site: Site, proxy: Optional[List[str]] = None):
|
||||
self.site = site
|
||||
self.proxy = (lambda p: {"http": p, "https": p} if p else None)(proxy)
|
||||
|
||||
@abstractmethod
|
||||
def scrape(self, scraper_input: ScraperInput) -> JobResponse: ...
|
||||
def scrape(self, scraper_input: ScraperInput) -> JobResponse:
|
||||
...
|
||||
|
||||
@@ -19,8 +19,3 @@ class IndeedException(Exception):
|
||||
class ZipRecruiterException(Exception):
|
||||
def __init__(self, message=None):
|
||||
super().__init__(message or "An error occurred with ZipRecruiter")
|
||||
|
||||
|
||||
class GlassdoorException(Exception):
|
||||
def __init__(self, message=None):
|
||||
super().__init__(message or "An error occurred with Glassdoor")
|
||||
|
||||
@@ -1,535 +0,0 @@
|
||||
"""
|
||||
jobspy.scrapers.glassdoor
|
||||
~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
This module contains routines to scrape Glassdoor.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
import json
|
||||
import requests
|
||||
from typing import Optional, Tuple
|
||||
from datetime import datetime, timedelta
|
||||
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||||
|
||||
from .. import Scraper, ScraperInput, Site
|
||||
from ..utils import extract_emails_from_text
|
||||
from ..exceptions import GlassdoorException
|
||||
from ..utils import (
|
||||
create_session,
|
||||
markdown_converter,
|
||||
logger,
|
||||
)
|
||||
from ...jobs import (
|
||||
JobPost,
|
||||
Compensation,
|
||||
CompensationInterval,
|
||||
Location,
|
||||
JobResponse,
|
||||
JobType,
|
||||
DescriptionFormat,
|
||||
)
|
||||
|
||||
|
||||
class GlassdoorScraper(Scraper):
|
||||
def __init__(self, proxy: Optional[str] = None):
|
||||
"""
|
||||
Initializes GlassdoorScraper with the Glassdoor job search url
|
||||
"""
|
||||
site = Site(Site.GLASSDOOR)
|
||||
super().__init__(site, proxy=proxy)
|
||||
|
||||
self.base_url = None
|
||||
self.country = None
|
||||
self.session = None
|
||||
self.scraper_input = None
|
||||
self.jobs_per_page = 30
|
||||
self.max_pages = 30
|
||||
self.seen_urls = set()
|
||||
|
||||
def scrape(self, scraper_input: ScraperInput) -> JobResponse:
|
||||
"""
|
||||
Scrapes Glassdoor for jobs with scraper_input criteria.
|
||||
:param scraper_input: Information about job search criteria.
|
||||
:return: JobResponse containing a list of jobs.
|
||||
"""
|
||||
self.scraper_input = scraper_input
|
||||
self.scraper_input.results_wanted = min(900, scraper_input.results_wanted)
|
||||
self.base_url = self.scraper_input.country.get_glassdoor_url()
|
||||
|
||||
self.session = create_session(self.proxy, is_tls=True, has_retry=True)
|
||||
token = self._get_csrf_token()
|
||||
self.headers["gd-csrf-token"] = token if token else self.fallback_token
|
||||
|
||||
location_id, location_type = self._get_location(
|
||||
scraper_input.location, scraper_input.is_remote
|
||||
)
|
||||
if location_type is None:
|
||||
logger.error("Glassdoor: location not parsed")
|
||||
return JobResponse(jobs=[])
|
||||
all_jobs: list[JobPost] = []
|
||||
cursor = None
|
||||
|
||||
range_start = 1 + (scraper_input.offset // self.jobs_per_page)
|
||||
tot_pages = (scraper_input.results_wanted // self.jobs_per_page) + 2
|
||||
range_end = min(tot_pages, self.max_pages + 1)
|
||||
for page in range(range_start, range_end):
|
||||
logger.info(f"Glassdoor search page: {page}")
|
||||
try:
|
||||
jobs, cursor = self._fetch_jobs_page(
|
||||
scraper_input, location_id, location_type, page, cursor
|
||||
)
|
||||
all_jobs.extend(jobs)
|
||||
if not jobs or len(all_jobs) >= scraper_input.results_wanted:
|
||||
all_jobs = all_jobs[: scraper_input.results_wanted]
|
||||
break
|
||||
except Exception as e:
|
||||
logger.error(f"Glassdoor: {str(e)}")
|
||||
break
|
||||
return JobResponse(jobs=all_jobs)
|
||||
|
||||
def _fetch_jobs_page(
|
||||
self,
|
||||
scraper_input: ScraperInput,
|
||||
location_id: int,
|
||||
location_type: str,
|
||||
page_num: int,
|
||||
cursor: str | None,
|
||||
) -> Tuple[list[JobPost], str | None]:
|
||||
"""
|
||||
Scrapes a page of Glassdoor for jobs with scraper_input criteria
|
||||
"""
|
||||
jobs = []
|
||||
self.scraper_input = scraper_input
|
||||
try:
|
||||
payload = self._add_payload(location_id, location_type, page_num, cursor)
|
||||
response = self.session.post(
|
||||
f"{self.base_url}/graph",
|
||||
headers=self.headers,
|
||||
timeout_seconds=15,
|
||||
data=payload,
|
||||
)
|
||||
if response.status_code != 200:
|
||||
exc_msg = f"bad response status code: {response.status_code}"
|
||||
raise GlassdoorException(exc_msg)
|
||||
res_json = response.json()[0]
|
||||
if "errors" in res_json:
|
||||
raise ValueError("Error encountered in API response")
|
||||
except (
|
||||
requests.exceptions.ReadTimeout,
|
||||
GlassdoorException,
|
||||
ValueError,
|
||||
Exception,
|
||||
) as e:
|
||||
logger.error(f"Glassdoor: {str(e)}")
|
||||
return jobs, None
|
||||
|
||||
jobs_data = res_json["data"]["jobListings"]["jobListings"]
|
||||
|
||||
with ThreadPoolExecutor(max_workers=self.jobs_per_page) as executor:
|
||||
future_to_job_data = {
|
||||
executor.submit(self._process_job, job): job for job in jobs_data
|
||||
}
|
||||
for future in as_completed(future_to_job_data):
|
||||
try:
|
||||
job_post = future.result()
|
||||
if job_post:
|
||||
jobs.append(job_post)
|
||||
except Exception as exc:
|
||||
raise GlassdoorException(f"Glassdoor generated an exception: {exc}")
|
||||
|
||||
return jobs, self.get_cursor_for_page(
|
||||
res_json["data"]["jobListings"]["paginationCursors"], page_num + 1
|
||||
)
|
||||
|
||||
def _get_csrf_token(self):
|
||||
"""
|
||||
Fetches csrf token needed for API by visiting a generic page
|
||||
"""
|
||||
res = self.session.get(
|
||||
f"{self.base_url}/Job/computer-science-jobs.htm", headers=self.headers
|
||||
)
|
||||
pattern = r'"token":\s*"([^"]+)"'
|
||||
matches = re.findall(pattern, res.text)
|
||||
token = None
|
||||
if matches:
|
||||
token = matches[0]
|
||||
return token
|
||||
|
||||
def _process_job(self, job_data):
|
||||
"""
|
||||
Processes a single job and fetches its description.
|
||||
"""
|
||||
job_id = job_data["jobview"]["job"]["listingId"]
|
||||
job_url = f"{self.base_url}job-listing/j?jl={job_id}"
|
||||
if job_url in self.seen_urls:
|
||||
return None
|
||||
self.seen_urls.add(job_url)
|
||||
job = job_data["jobview"]
|
||||
title = job["job"]["jobTitleText"]
|
||||
company_name = job["header"]["employerNameFromSearch"]
|
||||
company_id = job_data["jobview"]["header"]["employer"]["id"]
|
||||
location_name = job["header"].get("locationName", "")
|
||||
location_type = job["header"].get("locationType", "")
|
||||
age_in_days = job["header"].get("ageInDays")
|
||||
is_remote, location = False, None
|
||||
date_diff = (datetime.now() - timedelta(days=age_in_days)).date()
|
||||
date_posted = date_diff if age_in_days is not None else None
|
||||
|
||||
if location_type == "S":
|
||||
is_remote = True
|
||||
else:
|
||||
location = self.parse_location(location_name)
|
||||
|
||||
compensation = self.parse_compensation(job["header"])
|
||||
try:
|
||||
description = self._fetch_job_description(job_id)
|
||||
except:
|
||||
description = None
|
||||
company_url = f"{self.base_url}Overview/W-EI_IE{company_id}.htm"
|
||||
return JobPost(
|
||||
id=str(job_id),
|
||||
title=title,
|
||||
company_url=company_url if company_id else None,
|
||||
company_name=company_name,
|
||||
date_posted=date_posted,
|
||||
job_url=job_url,
|
||||
location=location,
|
||||
compensation=compensation,
|
||||
is_remote=is_remote,
|
||||
description=description,
|
||||
emails=extract_emails_from_text(description) if description else None,
|
||||
)
|
||||
|
||||
def _fetch_job_description(self, job_id):
|
||||
"""
|
||||
Fetches the job description for a single job ID.
|
||||
"""
|
||||
url = f"{self.base_url}/graph"
|
||||
body = [
|
||||
{
|
||||
"operationName": "JobDetailQuery",
|
||||
"variables": {
|
||||
"jl": job_id,
|
||||
"queryString": "q",
|
||||
"pageTypeEnum": "SERP",
|
||||
},
|
||||
"query": """
|
||||
query JobDetailQuery($jl: Long!, $queryString: String, $pageTypeEnum: PageTypeEnum) {
|
||||
jobview: jobView(
|
||||
listingId: $jl
|
||||
contextHolder: {queryString: $queryString, pageTypeEnum: $pageTypeEnum}
|
||||
) {
|
||||
job {
|
||||
description
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
}
|
||||
""",
|
||||
}
|
||||
]
|
||||
res = requests.post(url, json=body, headers=self.headers)
|
||||
if res.status_code != 200:
|
||||
return None
|
||||
data = res.json()[0]
|
||||
desc = data["data"]["jobview"]["job"]["description"]
|
||||
if self.scraper_input.description_format == DescriptionFormat.MARKDOWN:
|
||||
desc = markdown_converter(desc)
|
||||
return desc
|
||||
|
||||
def _get_location(self, location: str, is_remote: bool) -> (int, str):
|
||||
if not location or is_remote:
|
||||
return "11047", "STATE" # remote options
|
||||
url = f"{self.base_url}/findPopularLocationAjax.htm?maxLocationsToReturn=10&term={location}"
|
||||
session = create_session(self.proxy, has_retry=True)
|
||||
res = self.session.get(url, headers=self.headers)
|
||||
if res.status_code != 200:
|
||||
if res.status_code == 429:
|
||||
err = f"429 Response - Blocked by Glassdoor for too many requests"
|
||||
logger.error(err)
|
||||
return None, None
|
||||
else:
|
||||
err = f"Glassdoor response status code {res.status_code}"
|
||||
err += f" - {res.text}"
|
||||
logger.error(f"Glassdoor response status code {res.status_code}")
|
||||
return None, None
|
||||
items = res.json()
|
||||
|
||||
if not items:
|
||||
raise ValueError(f"Location '{location}' not found on Glassdoor")
|
||||
location_type = items[0]["locationType"]
|
||||
if location_type == "C":
|
||||
location_type = "CITY"
|
||||
elif location_type == "S":
|
||||
location_type = "STATE"
|
||||
elif location_type == "N":
|
||||
location_type = "COUNTRY"
|
||||
return int(items[0]["locationId"]), location_type
|
||||
|
||||
def _add_payload(
|
||||
self,
|
||||
location_id: int,
|
||||
location_type: str,
|
||||
page_num: int,
|
||||
cursor: str | None = None,
|
||||
) -> str:
|
||||
fromage = None
|
||||
if self.scraper_input.hours_old:
|
||||
fromage = max(self.scraper_input.hours_old // 24, 1)
|
||||
filter_params = []
|
||||
if self.scraper_input.easy_apply:
|
||||
filter_params.append({"filterKey": "applicationType", "values": "1"})
|
||||
if fromage:
|
||||
filter_params.append({"filterKey": "fromAge", "values": str(fromage)})
|
||||
payload = {
|
||||
"operationName": "JobSearchResultsQuery",
|
||||
"variables": {
|
||||
"excludeJobListingIds": [],
|
||||
"filterParams": filter_params,
|
||||
"keyword": self.scraper_input.search_term,
|
||||
"numJobsToShow": 30,
|
||||
"locationType": location_type,
|
||||
"locationId": int(location_id),
|
||||
"parameterUrlInput": f"IL.0,12_I{location_type}{location_id}",
|
||||
"pageNumber": page_num,
|
||||
"pageCursor": cursor,
|
||||
"fromage": fromage,
|
||||
"sort": "date",
|
||||
},
|
||||
"query": self.query_template,
|
||||
}
|
||||
if self.scraper_input.job_type:
|
||||
payload["variables"]["filterParams"].append(
|
||||
{"filterKey": "jobType", "values": self.scraper_input.job_type.value[0]}
|
||||
)
|
||||
return json.dumps([payload])
|
||||
|
||||
@staticmethod
|
||||
def parse_compensation(data: dict) -> Optional[Compensation]:
|
||||
pay_period = data.get("payPeriod")
|
||||
adjusted_pay = data.get("payPeriodAdjustedPay")
|
||||
currency = data.get("payCurrency", "USD")
|
||||
if not pay_period or not adjusted_pay:
|
||||
return None
|
||||
|
||||
interval = None
|
||||
if pay_period == "ANNUAL":
|
||||
interval = CompensationInterval.YEARLY
|
||||
elif pay_period:
|
||||
interval = CompensationInterval.get_interval(pay_period)
|
||||
min_amount = int(adjusted_pay.get("p10") // 1)
|
||||
max_amount = int(adjusted_pay.get("p90") // 1)
|
||||
return Compensation(
|
||||
interval=interval,
|
||||
min_amount=min_amount,
|
||||
max_amount=max_amount,
|
||||
currency=currency,
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def get_job_type_enum(job_type_str: str) -> list[JobType] | None:
|
||||
for job_type in JobType:
|
||||
if job_type_str in job_type.value:
|
||||
return [job_type]
|
||||
|
||||
@staticmethod
|
||||
def parse_location(location_name: str) -> Location | None:
|
||||
if not location_name or location_name == "Remote":
|
||||
return
|
||||
city, _, state = location_name.partition(", ")
|
||||
return Location(city=city, state=state)
|
||||
|
||||
@staticmethod
|
||||
def get_cursor_for_page(pagination_cursors, page_num):
|
||||
for cursor_data in pagination_cursors:
|
||||
if cursor_data["pageNumber"] == page_num:
|
||||
return cursor_data["cursor"]
|
||||
|
||||
fallback_token = "Ft6oHEWlRZrxDww95Cpazw:0pGUrkb2y3TyOpAIqF2vbPmUXoXVkD3oEGDVkvfeCerceQ5-n8mBg3BovySUIjmCPHCaW0H2nQVdqzbtsYqf4Q:wcqRqeegRUa9MVLJGyujVXB7vWFPjdaS1CtrrzJq-ok"
|
||||
headers = {
|
||||
"authority": "www.glassdoor.com",
|
||||
"accept": "*/*",
|
||||
"accept-language": "en-US,en;q=0.9",
|
||||
"apollographql-client-name": "job-search-next",
|
||||
"apollographql-client-version": "4.65.5",
|
||||
"content-type": "application/json",
|
||||
"origin": "https://www.glassdoor.com",
|
||||
"referer": "https://www.glassdoor.com/",
|
||||
"sec-ch-ua": '"Chromium";v="118", "Google Chrome";v="118", "Not=A?Brand";v="99"',
|
||||
"sec-ch-ua-mobile": "?0",
|
||||
"sec-ch-ua-platform": '"macOS"',
|
||||
"sec-fetch-dest": "empty",
|
||||
"sec-fetch-mode": "cors",
|
||||
"sec-fetch-site": "same-origin",
|
||||
"user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36",
|
||||
}
|
||||
query_template = """
|
||||
query JobSearchResultsQuery(
|
||||
$excludeJobListingIds: [Long!],
|
||||
$keyword: String,
|
||||
$locationId: Int,
|
||||
$locationType: LocationTypeEnum,
|
||||
$numJobsToShow: Int!,
|
||||
$pageCursor: String,
|
||||
$pageNumber: Int,
|
||||
$filterParams: [FilterParams],
|
||||
$originalPageUrl: String,
|
||||
$seoFriendlyUrlInput: String,
|
||||
$parameterUrlInput: String,
|
||||
$seoUrl: Boolean
|
||||
) {
|
||||
jobListings(
|
||||
contextHolder: {
|
||||
searchParams: {
|
||||
excludeJobListingIds: $excludeJobListingIds,
|
||||
keyword: $keyword,
|
||||
locationId: $locationId,
|
||||
locationType: $locationType,
|
||||
numPerPage: $numJobsToShow,
|
||||
pageCursor: $pageCursor,
|
||||
pageNumber: $pageNumber,
|
||||
filterParams: $filterParams,
|
||||
originalPageUrl: $originalPageUrl,
|
||||
seoFriendlyUrlInput: $seoFriendlyUrlInput,
|
||||
parameterUrlInput: $parameterUrlInput,
|
||||
seoUrl: $seoUrl,
|
||||
searchType: SR
|
||||
}
|
||||
}
|
||||
) {
|
||||
companyFilterOptions {
|
||||
id
|
||||
shortName
|
||||
__typename
|
||||
}
|
||||
filterOptions
|
||||
indeedCtk
|
||||
jobListings {
|
||||
...JobView
|
||||
__typename
|
||||
}
|
||||
jobListingSeoLinks {
|
||||
linkItems {
|
||||
position
|
||||
url
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
jobSearchTrackingKey
|
||||
jobsPageSeoData {
|
||||
pageMetaDescription
|
||||
pageTitle
|
||||
__typename
|
||||
}
|
||||
paginationCursors {
|
||||
cursor
|
||||
pageNumber
|
||||
__typename
|
||||
}
|
||||
indexablePageForSeo
|
||||
searchResultsMetadata {
|
||||
searchCriteria {
|
||||
implicitLocation {
|
||||
id
|
||||
localizedDisplayName
|
||||
type
|
||||
__typename
|
||||
}
|
||||
keyword
|
||||
location {
|
||||
id
|
||||
shortName
|
||||
localizedShortName
|
||||
localizedDisplayName
|
||||
type
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
helpCenterDomain
|
||||
helpCenterLocale
|
||||
jobSerpJobOutlook {
|
||||
occupation
|
||||
paragraph
|
||||
__typename
|
||||
}
|
||||
showMachineReadableJobs
|
||||
__typename
|
||||
}
|
||||
totalJobsCount
|
||||
__typename
|
||||
}
|
||||
}
|
||||
|
||||
fragment JobView on JobListingSearchResult {
|
||||
jobview {
|
||||
header {
|
||||
adOrderId
|
||||
advertiserType
|
||||
adOrderSponsorshipLevel
|
||||
ageInDays
|
||||
divisionEmployerName
|
||||
easyApply
|
||||
employer {
|
||||
id
|
||||
name
|
||||
shortName
|
||||
__typename
|
||||
}
|
||||
employerNameFromSearch
|
||||
goc
|
||||
gocConfidence
|
||||
gocId
|
||||
jobCountryId
|
||||
jobLink
|
||||
jobResultTrackingKey
|
||||
jobTitleText
|
||||
locationName
|
||||
locationType
|
||||
locId
|
||||
needsCommission
|
||||
payCurrency
|
||||
payPeriod
|
||||
payPeriodAdjustedPay {
|
||||
p10
|
||||
p50
|
||||
p90
|
||||
__typename
|
||||
}
|
||||
rating
|
||||
salarySource
|
||||
savedJobId
|
||||
sponsored
|
||||
__typename
|
||||
}
|
||||
job {
|
||||
description
|
||||
importConfigId
|
||||
jobTitleId
|
||||
jobTitleText
|
||||
listingId
|
||||
__typename
|
||||
}
|
||||
jobListingAdminDetails {
|
||||
cpcVal
|
||||
importConfigId
|
||||
jobListingId
|
||||
jobSourceId
|
||||
userEligibleForAdminJobDetails
|
||||
__typename
|
||||
}
|
||||
overview {
|
||||
shortName
|
||||
squareLogoUrl
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
"""
|
||||
@@ -4,22 +4,23 @@ jobspy.scrapers.indeed
|
||||
|
||||
This module contains routines to scrape Indeed.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
import math
|
||||
from typing import Tuple
|
||||
import io
|
||||
import json
|
||||
from datetime import datetime
|
||||
|
||||
import urllib.parse
|
||||
from bs4 import BeautifulSoup
|
||||
from bs4.element import Tag
|
||||
from concurrent.futures import ThreadPoolExecutor, Future
|
||||
|
||||
import requests
|
||||
|
||||
from .. import Scraper, ScraperInput, Site
|
||||
from ..exceptions import IndeedException
|
||||
from ..utils import (
|
||||
count_urgent_words,
|
||||
extract_emails_from_text,
|
||||
create_session,
|
||||
get_enum_from_job_type,
|
||||
markdown_converter,
|
||||
logger,
|
||||
)
|
||||
from ...jobs import (
|
||||
JobPost,
|
||||
@@ -28,408 +29,345 @@ from ...jobs import (
|
||||
Location,
|
||||
JobResponse,
|
||||
JobType,
|
||||
DescriptionFormat,
|
||||
)
|
||||
from .. import Scraper, ScraperInput, Site
|
||||
|
||||
|
||||
class IndeedScraper(Scraper):
|
||||
def __init__(self, proxy: str | None = None):
|
||||
"""
|
||||
Initializes IndeedScraper with the Indeed API url
|
||||
Initializes IndeedScraper with the Indeed job search url
|
||||
"""
|
||||
self.scraper_input = None
|
||||
self.jobs_per_page = 100
|
||||
self.num_workers = 10
|
||||
self.seen_urls = set()
|
||||
self.headers = None
|
||||
self.api_country_code = None
|
||||
self.base_url = None
|
||||
self.api_url = "https://apis.indeed.com/graphql"
|
||||
self.url = None
|
||||
self.country = None
|
||||
site = Site(Site.INDEED)
|
||||
super().__init__(site, proxy=proxy)
|
||||
|
||||
self.jobs_per_page = 15
|
||||
self.seen_urls = set()
|
||||
|
||||
def scrape_page(
|
||||
self, scraper_input: ScraperInput, page: int
|
||||
) -> tuple[list[JobPost], int]:
|
||||
"""
|
||||
Scrapes a page of Indeed for jobs with scraper_input criteria
|
||||
:param scraper_input:
|
||||
:param page:
|
||||
:return: jobs found on page, total number of jobs found for search
|
||||
"""
|
||||
self.country = scraper_input.country
|
||||
domain = self.country.domain_value
|
||||
self.url = f"https://{domain}.indeed.com"
|
||||
session = create_session(self.proxy)
|
||||
|
||||
params = {
|
||||
"q": scraper_input.search_term,
|
||||
"l": scraper_input.location,
|
||||
"filter": 0,
|
||||
"start": scraper_input.offset + page * 10,
|
||||
}
|
||||
if scraper_input.distance:
|
||||
params["radius"] = scraper_input.distance
|
||||
|
||||
sc_values = []
|
||||
if scraper_input.is_remote:
|
||||
sc_values.append("attr(DSQF7)")
|
||||
if scraper_input.job_type:
|
||||
sc_values.append("jt({})".format(scraper_input.job_type.value))
|
||||
|
||||
if sc_values:
|
||||
params["sc"] = "0kf:" + "".join(sc_values) + ";"
|
||||
try:
|
||||
response = session.get(
|
||||
f"{self.url}/jobs",
|
||||
headers=self.get_headers(),
|
||||
params=params,
|
||||
allow_redirects=True,
|
||||
timeout_seconds=10,
|
||||
)
|
||||
if response.status_code not in range(200, 400):
|
||||
raise IndeedException(
|
||||
f"bad response with status code: {response.status_code}"
|
||||
)
|
||||
except Exception as e:
|
||||
if "Proxy responded with" in str(e):
|
||||
raise IndeedException("bad proxy")
|
||||
raise IndeedException(str(e))
|
||||
|
||||
soup = BeautifulSoup(response.content, "html.parser")
|
||||
if "did not match any jobs" in response.text:
|
||||
raise IndeedException("Parsing exception: Search did not match any jobs")
|
||||
|
||||
jobs = IndeedScraper.parse_jobs(
|
||||
soup
|
||||
) #: can raise exception, handled by main scrape function
|
||||
total_num_jobs = IndeedScraper.total_jobs(soup)
|
||||
|
||||
if (
|
||||
not jobs.get("metaData", {})
|
||||
.get("mosaicProviderJobCardsModel", {})
|
||||
.get("results")
|
||||
):
|
||||
raise IndeedException("No jobs found.")
|
||||
|
||||
def process_job(job) -> JobPost | None:
|
||||
job_url = f'{self.url}/jobs/viewjob?jk={job["jobkey"]}'
|
||||
job_url_client = f'{self.url}/viewjob?jk={job["jobkey"]}'
|
||||
if job_url in self.seen_urls:
|
||||
return None
|
||||
|
||||
extracted_salary = job.get("extractedSalary")
|
||||
compensation = None
|
||||
if extracted_salary:
|
||||
salary_snippet = job.get("salarySnippet")
|
||||
currency = salary_snippet.get("currency") if salary_snippet else None
|
||||
interval = (extracted_salary.get("type"),)
|
||||
if isinstance(interval, tuple):
|
||||
interval = interval[0]
|
||||
|
||||
interval = interval.upper()
|
||||
if interval in CompensationInterval.__members__:
|
||||
compensation = Compensation(
|
||||
interval=CompensationInterval[interval],
|
||||
min_amount=int(extracted_salary.get("min")),
|
||||
max_amount=int(extracted_salary.get("max")),
|
||||
currency=currency,
|
||||
)
|
||||
|
||||
job_type = IndeedScraper.get_job_type(job)
|
||||
timestamp_seconds = job["pubDate"] / 1000
|
||||
date_posted = datetime.fromtimestamp(timestamp_seconds)
|
||||
date_posted = date_posted.strftime("%Y-%m-%d")
|
||||
|
||||
description = self.get_description(job_url)
|
||||
with io.StringIO(job["snippet"]) as f:
|
||||
soup_io = BeautifulSoup(f, "html.parser")
|
||||
li_elements = soup_io.find_all("li")
|
||||
if description is None and li_elements:
|
||||
description = " ".join(li.text for li in li_elements)
|
||||
|
||||
job_post = JobPost(
|
||||
title=job["normTitle"],
|
||||
description=description,
|
||||
company_name=job["company"],
|
||||
location=Location(
|
||||
city=job.get("jobLocationCity"),
|
||||
state=job.get("jobLocationState"),
|
||||
country=self.country,
|
||||
),
|
||||
job_type=job_type,
|
||||
compensation=compensation,
|
||||
date_posted=date_posted,
|
||||
job_url=job_url_client,
|
||||
emails=extract_emails_from_text(description) if description else None,
|
||||
num_urgent_words=count_urgent_words(description)
|
||||
if description
|
||||
else None,
|
||||
is_remote=self.is_remote_job(job),
|
||||
)
|
||||
return job_post
|
||||
|
||||
jobs = jobs["metaData"]["mosaicProviderJobCardsModel"]["results"]
|
||||
with ThreadPoolExecutor(max_workers=1) as executor:
|
||||
job_results: list[Future] = [
|
||||
executor.submit(process_job, job) for job in jobs
|
||||
]
|
||||
|
||||
job_list = [result.result() for result in job_results if result.result()]
|
||||
|
||||
return job_list, total_num_jobs
|
||||
|
||||
def scrape(self, scraper_input: ScraperInput) -> JobResponse:
|
||||
"""
|
||||
Scrapes Indeed for jobs with scraper_input criteria
|
||||
:param scraper_input:
|
||||
:return: job_response
|
||||
"""
|
||||
self.scraper_input = scraper_input
|
||||
domain, self.api_country_code = self.scraper_input.country.indeed_domain_value
|
||||
self.base_url = f"https://{domain}.indeed.com"
|
||||
self.headers = self.api_headers.copy()
|
||||
self.headers["indeed-co"] = self.scraper_input.country.indeed_domain_value
|
||||
job_list = []
|
||||
page = 1
|
||||
|
||||
cursor = None
|
||||
offset_pages = math.ceil(self.scraper_input.offset / 100)
|
||||
for _ in range(offset_pages):
|
||||
logger.info(f"Indeed skipping search page: {page}")
|
||||
__, cursor = self._scrape_page(cursor)
|
||||
if not __:
|
||||
logger.info(f"Indeed found no jobs on page: {page}")
|
||||
break
|
||||
|
||||
while len(self.seen_urls) < scraper_input.results_wanted:
|
||||
logger.info(f"Indeed search page: {page}")
|
||||
jobs, cursor = self._scrape_page(cursor)
|
||||
if not jobs:
|
||||
logger.info(f"Indeed found no jobs on page: {page}")
|
||||
break
|
||||
job_list += jobs
|
||||
page += 1
|
||||
return JobResponse(jobs=job_list[: scraper_input.results_wanted])
|
||||
|
||||
def _scrape_page(self, cursor: str | None) -> Tuple[list[JobPost], str | None]:
|
||||
"""
|
||||
Scrapes a page of Indeed for jobs with scraper_input criteria
|
||||
:param cursor:
|
||||
:return: jobs found on page, next page cursor
|
||||
"""
|
||||
jobs = []
|
||||
new_cursor = None
|
||||
filters = self._build_filters()
|
||||
search_term = self.scraper_input.search_term.replace('"', '\\"') if self.scraper_input.search_term else ""
|
||||
query = self.job_search_query.format(
|
||||
what=(
|
||||
f'what: "{search_term}"'
|
||||
if search_term
|
||||
else ""
|
||||
),
|
||||
location=(
|
||||
f'location: {{where: "{self.scraper_input.location}", radius: {self.scraper_input.distance}, radiusUnit: MILES}}'
|
||||
if self.scraper_input.location
|
||||
else ""
|
||||
),
|
||||
dateOnIndeed=self.scraper_input.hours_old,
|
||||
cursor=f'cursor: "{cursor}"' if cursor else "",
|
||||
filters=filters,
|
||||
pages_to_process = (
|
||||
math.ceil(scraper_input.results_wanted / self.jobs_per_page) - 1
|
||||
)
|
||||
payload = {
|
||||
"query": query,
|
||||
}
|
||||
api_headers = self.api_headers.copy()
|
||||
api_headers["indeed-co"] = self.api_country_code
|
||||
response = requests.post(
|
||||
self.api_url,
|
||||
headers=api_headers,
|
||||
json=payload,
|
||||
proxies=self.proxy,
|
||||
timeout=10,
|
||||
)
|
||||
if response.status_code != 200:
|
||||
logger.info(
|
||||
f"Indeed responded with status code: {response.status_code} (submit GitHub issue if this appears to be a bug)"
|
||||
)
|
||||
return jobs, new_cursor
|
||||
data = response.json()
|
||||
jobs = data["data"]["jobSearch"]["results"]
|
||||
new_cursor = data["data"]["jobSearch"]["pageInfo"]["nextCursor"]
|
||||
|
||||
with ThreadPoolExecutor(max_workers=self.num_workers) as executor:
|
||||
job_results: list[Future] = [
|
||||
executor.submit(self._process_job, job["job"]) for job in jobs
|
||||
#: get first page to initialize session
|
||||
job_list, total_results = self.scrape_page(scraper_input, 0)
|
||||
|
||||
with ThreadPoolExecutor(max_workers=1) as executor:
|
||||
futures: list[Future] = [
|
||||
executor.submit(self.scrape_page, scraper_input, page)
|
||||
for page in range(1, pages_to_process + 1)
|
||||
]
|
||||
job_list = [result.result() for result in job_results if result.result()]
|
||||
return job_list, new_cursor
|
||||
|
||||
def _build_filters(self):
|
||||
"""
|
||||
Builds the filters dict for job type/is_remote. If hours_old is provided, composite filter for job_type/is_remote is not possible.
|
||||
IndeedApply: filters: { keyword: { field: "indeedApplyScope", keys: ["DESKTOP"] } }
|
||||
"""
|
||||
filters_str = ""
|
||||
if self.scraper_input.hours_old:
|
||||
filters_str = """
|
||||
filters: {{
|
||||
date: {{
|
||||
field: "dateOnIndeed",
|
||||
start: "{start}h"
|
||||
}}
|
||||
}}
|
||||
""".format(
|
||||
start=self.scraper_input.hours_old
|
||||
)
|
||||
elif self.scraper_input.easy_apply:
|
||||
filters_str = """
|
||||
filters: {
|
||||
keyword: {
|
||||
field: "indeedApplyScope",
|
||||
keys: ["DESKTOP"]
|
||||
}
|
||||
}
|
||||
"""
|
||||
elif self.scraper_input.job_type or self.scraper_input.is_remote:
|
||||
job_type_key_mapping = {
|
||||
JobType.FULL_TIME: "CF3CP",
|
||||
JobType.PART_TIME: "75GKK",
|
||||
JobType.CONTRACT: "NJXCK",
|
||||
JobType.INTERNSHIP: "VDTG7",
|
||||
}
|
||||
for future in futures:
|
||||
jobs, _ = future.result()
|
||||
|
||||
keys = []
|
||||
if self.scraper_input.job_type:
|
||||
key = job_type_key_mapping[self.scraper_input.job_type]
|
||||
keys.append(key)
|
||||
job_list += jobs
|
||||
|
||||
if self.scraper_input.is_remote:
|
||||
keys.append("DSQF7")
|
||||
if len(job_list) > scraper_input.results_wanted:
|
||||
job_list = job_list[: scraper_input.results_wanted]
|
||||
|
||||
if keys:
|
||||
keys_str = '", "'.join(keys) # Prepare your keys string
|
||||
filters_str = f"""
|
||||
filters: {{
|
||||
composite: {{
|
||||
filters: [{{
|
||||
keyword: {{
|
||||
field: "attributes",
|
||||
keys: ["{keys_str}"]
|
||||
}}
|
||||
}}]
|
||||
}}
|
||||
}}
|
||||
"""
|
||||
return filters_str
|
||||
|
||||
def _process_job(self, job: dict) -> JobPost | None:
|
||||
"""
|
||||
Parses the job dict into JobPost model
|
||||
:param job: dict to parse
|
||||
:return: JobPost if it's a new job
|
||||
"""
|
||||
job_url = f'{self.base_url}/viewjob?jk={job["key"]}'
|
||||
if job_url in self.seen_urls:
|
||||
return
|
||||
self.seen_urls.add(job_url)
|
||||
description = job["description"]["html"]
|
||||
if self.scraper_input.description_format == DescriptionFormat.MARKDOWN:
|
||||
description = markdown_converter(description)
|
||||
|
||||
job_type = self._get_job_type(job["attributes"])
|
||||
timestamp_seconds = job["datePublished"] / 1000
|
||||
date_posted = datetime.fromtimestamp(timestamp_seconds).strftime("%Y-%m-%d")
|
||||
employer = job["employer"].get("dossier") if job["employer"] else None
|
||||
employer_details = employer.get("employerDetails", {}) if employer else {}
|
||||
rel_url = job["employer"]["relativeCompanyPageUrl"] if job["employer"] else None
|
||||
return JobPost(
|
||||
id=str(job["key"]),
|
||||
title=job["title"],
|
||||
description=description,
|
||||
company_name=job["employer"].get("name") if job.get("employer") else None,
|
||||
company_url=(f"{self.base_url}{rel_url}" if job["employer"] else None),
|
||||
company_url_direct=(
|
||||
employer["links"]["corporateWebsite"] if employer else None
|
||||
),
|
||||
location=Location(
|
||||
city=job.get("location", {}).get("city"),
|
||||
state=job.get("location", {}).get("admin1Code"),
|
||||
country=job.get("location", {}).get("countryCode"),
|
||||
),
|
||||
job_type=job_type,
|
||||
compensation=self._get_compensation(job),
|
||||
date_posted=date_posted,
|
||||
job_url=job_url,
|
||||
job_url_direct=(
|
||||
job["recruit"].get("viewJobUrl") if job.get("recruit") else None
|
||||
),
|
||||
emails=extract_emails_from_text(description) if description else None,
|
||||
is_remote=self._is_job_remote(job, description),
|
||||
company_addresses=(
|
||||
employer_details["addresses"][0]
|
||||
if employer_details.get("addresses")
|
||||
else None
|
||||
),
|
||||
company_industry=(
|
||||
employer_details["industry"]
|
||||
.replace("Iv1", "")
|
||||
.replace("_", " ")
|
||||
.title()
|
||||
if employer_details.get("industry")
|
||||
else None
|
||||
),
|
||||
company_num_employees=employer_details.get("employeesLocalizedLabel"),
|
||||
company_revenue=employer_details.get("revenueLocalizedLabel"),
|
||||
company_description=employer_details.get("briefDescription"),
|
||||
ceo_name=employer_details.get("ceoName"),
|
||||
ceo_photo_url=employer_details.get("ceoPhotoUrl"),
|
||||
logo_photo_url=(
|
||||
employer["images"].get("squareLogoUrl")
|
||||
if employer and employer.get("images")
|
||||
else None
|
||||
),
|
||||
banner_photo_url=(
|
||||
employer["images"].get("headerImageUrl")
|
||||
if employer and employer.get("images")
|
||||
else None
|
||||
),
|
||||
job_response = JobResponse(
|
||||
jobs=job_list,
|
||||
total_results=total_results,
|
||||
)
|
||||
return job_response
|
||||
|
||||
def get_description(self, job_page_url: str) -> str | None:
|
||||
"""
|
||||
Retrieves job description by going to the job page url
|
||||
:param job_page_url:
|
||||
:return: description
|
||||
"""
|
||||
parsed_url = urllib.parse.urlparse(job_page_url)
|
||||
params = urllib.parse.parse_qs(parsed_url.query)
|
||||
jk_value = params.get("jk", [None])[0]
|
||||
formatted_url = f"{self.url}/viewjob?jk={jk_value}&spa=1"
|
||||
session = create_session(self.proxy)
|
||||
|
||||
try:
|
||||
response = session.get(
|
||||
formatted_url,
|
||||
headers=self.get_headers(),
|
||||
allow_redirects=True,
|
||||
timeout_seconds=5,
|
||||
)
|
||||
except Exception as e:
|
||||
return None
|
||||
|
||||
if response.status_code not in range(200, 400):
|
||||
return None
|
||||
|
||||
soup = BeautifulSoup(response.text, "html.parser")
|
||||
script_tag = soup.find(
|
||||
"script", text=lambda x: x and "window._initialData" in x
|
||||
)
|
||||
|
||||
if not script_tag:
|
||||
return None
|
||||
|
||||
script_code = script_tag.string
|
||||
match = re.search(r"window\._initialData\s*=\s*({.*?})\s*;", script_code, re.S)
|
||||
|
||||
if not match:
|
||||
return None
|
||||
|
||||
json_string = match.group(1)
|
||||
data = json.loads(json_string)
|
||||
try:
|
||||
job_description = data["jobInfoWrapperModel"]["jobInfoModel"][
|
||||
"sanitizedJobDescription"
|
||||
]
|
||||
except (KeyError, TypeError, IndexError):
|
||||
return None
|
||||
|
||||
soup = BeautifulSoup(
|
||||
job_description, "html.parser"
|
||||
)
|
||||
text_content = " ".join(
|
||||
soup.get_text(separator=" ").split()
|
||||
).strip()
|
||||
|
||||
return text_content
|
||||
|
||||
@staticmethod
|
||||
def _get_job_type(attributes: list) -> list[JobType]:
|
||||
def get_job_type(job: dict) -> list[JobType] | None:
|
||||
"""
|
||||
Parses the attributes to get list of job types
|
||||
:param attributes:
|
||||
:return: list of JobType
|
||||
Parses the job to get list of job types
|
||||
:param job:
|
||||
:return:
|
||||
"""
|
||||
job_types: list[JobType] = []
|
||||
for attribute in attributes:
|
||||
job_type_str = attribute["label"].replace("-", "").replace(" ", "").lower()
|
||||
job_type = get_enum_from_job_type(job_type_str)
|
||||
if job_type:
|
||||
job_types.append(job_type)
|
||||
for taxonomy in job["taxonomyAttributes"]:
|
||||
if taxonomy["label"] == "job-types":
|
||||
for i in range(len(taxonomy["attributes"])):
|
||||
label = taxonomy["attributes"][i].get("label")
|
||||
if label:
|
||||
job_type_str = label.replace("-", "").replace(" ", "").lower()
|
||||
job_type = get_enum_from_job_type(job_type_str)
|
||||
if job_type:
|
||||
job_types.append(job_type)
|
||||
return job_types
|
||||
|
||||
@staticmethod
|
||||
def _get_compensation(job: dict) -> Compensation | None:
|
||||
def parse_jobs(soup: BeautifulSoup) -> dict:
|
||||
"""
|
||||
Parses the job to get compensation
|
||||
:param job:
|
||||
:param job:
|
||||
:return: compensation object
|
||||
Parses the jobs from the soup object
|
||||
:param soup:
|
||||
:return: jobs
|
||||
"""
|
||||
comp = job["compensation"]["baseSalary"]
|
||||
if not comp:
|
||||
return None
|
||||
interval = IndeedScraper._get_compensation_interval(comp["unitOfWork"])
|
||||
if not interval:
|
||||
return None
|
||||
min_range = comp["range"].get("min")
|
||||
max_range = comp["range"].get("max")
|
||||
return Compensation(
|
||||
interval=interval,
|
||||
min_amount=round(min_range, 2) if min_range is not None else None,
|
||||
max_amount=round(max_range, 2) if max_range is not None else None,
|
||||
currency=job["compensation"]["currencyCode"],
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _is_job_remote(job: dict, description: str) -> bool:
|
||||
"""
|
||||
Searches the description, location, and attributes to check if job is remote
|
||||
"""
|
||||
remote_keywords = ["remote", "work from home", "wfh"]
|
||||
is_remote_in_attributes = any(
|
||||
any(keyword in attr["label"].lower() for keyword in remote_keywords)
|
||||
for attr in job["attributes"]
|
||||
)
|
||||
is_remote_in_description = any(
|
||||
keyword in description.lower() for keyword in remote_keywords
|
||||
)
|
||||
is_remote_in_location = any(
|
||||
keyword in job["location"]["formatted"]["long"].lower()
|
||||
for keyword in remote_keywords
|
||||
)
|
||||
return (
|
||||
is_remote_in_attributes or is_remote_in_description or is_remote_in_location
|
||||
)
|
||||
def find_mosaic_script() -> Tag | None:
|
||||
"""
|
||||
Finds jobcards script tag
|
||||
:return: script_tag
|
||||
"""
|
||||
script_tags = soup.find_all("script")
|
||||
|
||||
@staticmethod
|
||||
def _get_compensation_interval(interval: str) -> CompensationInterval:
|
||||
interval_mapping = {
|
||||
"DAY": "DAILY",
|
||||
"YEAR": "YEARLY",
|
||||
"HOUR": "HOURLY",
|
||||
"WEEK": "WEEKLY",
|
||||
"MONTH": "MONTHLY",
|
||||
}
|
||||
mapped_interval = interval_mapping.get(interval.upper(), None)
|
||||
if mapped_interval and mapped_interval in CompensationInterval.__members__:
|
||||
return CompensationInterval[mapped_interval]
|
||||
for tag in script_tags:
|
||||
if (
|
||||
tag.string
|
||||
and "mosaic.providerData" in tag.string
|
||||
and "mosaic-provider-jobcards" in tag.string
|
||||
):
|
||||
return tag
|
||||
return None
|
||||
|
||||
script_tag = find_mosaic_script()
|
||||
|
||||
if script_tag:
|
||||
script_str = script_tag.string
|
||||
pattern = r'window.mosaic.providerData\["mosaic-provider-jobcards"\]\s*=\s*({.*?});'
|
||||
p = re.compile(pattern, re.DOTALL)
|
||||
m = p.search(script_str)
|
||||
if m:
|
||||
jobs = json.loads(m.group(1).strip())
|
||||
return jobs
|
||||
else:
|
||||
raise IndeedException("Could not find mosaic provider job cards data")
|
||||
else:
|
||||
raise ValueError(f"Unsupported interval: {interval}")
|
||||
raise IndeedException(
|
||||
"Could not find a script tag containing mosaic provider data"
|
||||
)
|
||||
|
||||
api_headers = {
|
||||
"Host": "apis.indeed.com",
|
||||
"content-type": "application/json",
|
||||
"indeed-api-key": "161092c2017b5bbab13edb12461a62d5a833871e7cad6d9d475304573de67ac8",
|
||||
"accept": "application/json",
|
||||
"indeed-locale": "en-US",
|
||||
"accept-language": "en-US,en;q=0.9",
|
||||
"user-agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 16_6_1 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Mobile/15E148 Indeed App 193.1",
|
||||
"indeed-app-info": "appv=193.1; appid=com.indeed.jobsearch; osv=16.6.1; os=ios; dtype=phone",
|
||||
}
|
||||
job_search_query = """
|
||||
query GetJobData {{
|
||||
jobSearch(
|
||||
{what}
|
||||
{location}
|
||||
includeSponsoredResults: NONE
|
||||
limit: 100
|
||||
sort: DATE
|
||||
{cursor}
|
||||
{filters}
|
||||
) {{
|
||||
pageInfo {{
|
||||
nextCursor
|
||||
}}
|
||||
results {{
|
||||
trackingKey
|
||||
job {{
|
||||
key
|
||||
title
|
||||
datePublished
|
||||
dateOnIndeed
|
||||
description {{
|
||||
html
|
||||
}}
|
||||
location {{
|
||||
countryName
|
||||
countryCode
|
||||
admin1Code
|
||||
city
|
||||
postalCode
|
||||
streetAddress
|
||||
formatted {{
|
||||
short
|
||||
long
|
||||
}}
|
||||
}}
|
||||
compensation {{
|
||||
baseSalary {{
|
||||
unitOfWork
|
||||
range {{
|
||||
... on Range {{
|
||||
min
|
||||
max
|
||||
}}
|
||||
}}
|
||||
}}
|
||||
currencyCode
|
||||
}}
|
||||
attributes {{
|
||||
key
|
||||
label
|
||||
}}
|
||||
employer {{
|
||||
relativeCompanyPageUrl
|
||||
name
|
||||
dossier {{
|
||||
employerDetails {{
|
||||
addresses
|
||||
industry
|
||||
employeesLocalizedLabel
|
||||
revenueLocalizedLabel
|
||||
briefDescription
|
||||
ceoName
|
||||
ceoPhotoUrl
|
||||
}}
|
||||
images {{
|
||||
headerImageUrl
|
||||
squareLogoUrl
|
||||
}}
|
||||
links {{
|
||||
corporateWebsite
|
||||
}}
|
||||
}}
|
||||
}}
|
||||
recruit {{
|
||||
viewJobUrl
|
||||
detailedSalary
|
||||
workSchedule
|
||||
}}
|
||||
}}
|
||||
}}
|
||||
}}
|
||||
}}
|
||||
@staticmethod
|
||||
def total_jobs(soup: BeautifulSoup) -> int:
|
||||
"""
|
||||
Parses the total jobs for that search from soup object
|
||||
:param soup:
|
||||
:return: total_num_jobs
|
||||
"""
|
||||
script = soup.find("script", string=lambda t: t and "window._initialData" in t)
|
||||
|
||||
pattern = re.compile(r"window._initialData\s*=\s*({.*})\s*;", re.DOTALL)
|
||||
match = pattern.search(script.string)
|
||||
total_num_jobs = 0
|
||||
if match:
|
||||
json_str = match.group(1)
|
||||
data = json.loads(json_str)
|
||||
total_num_jobs = int(data["searchTitleBarModel"]["totalNumResults"])
|
||||
return total_num_jobs
|
||||
|
||||
@staticmethod
|
||||
def get_headers():
|
||||
return {
|
||||
"authority": "www.indeed.com",
|
||||
"accept": "*/*",
|
||||
"accept-language": "en-US,en;q=0.9",
|
||||
"referer": "https://www.indeed.com/viewjob?jk=fe6182337d72c7b1&tk=1hcbfcmd0k62t802&from=serp&vjs=3&advn=8132938064490989&adid=408692607&ad=-6NYlbfkN0A3Osc99MJFDKjquSk4WOGT28ALb_ad4QMtrHreCb9ICg6MiSVy9oDAp3evvOrI7Q-O9qOtQTg1EPbthP9xWtBN2cOuVeHQijxHjHpJC65TjDtftH3AXeINjBvAyDrE8DrRaAXl8LD3Fs1e_xuDHQIssdZ2Mlzcav8m5jHrA0fA64ZaqJV77myldaNlM7-qyQpy4AsJQfvg9iR2MY7qeC5_FnjIgjKIy_lNi9OPMOjGRWXA94CuvC7zC6WeiJmBQCHISl8IOBxf7EdJZlYdtzgae3593TFxbkd6LUwbijAfjax39aAuuCXy3s9C4YgcEP3TwEFGQoTpYu9Pmle-Ae1tHGPgsjxwXkgMm7Cz5mBBdJioglRCj9pssn-1u1blHZM4uL1nK9p1Y6HoFgPUU9xvKQTHjKGdH8d4y4ETyCMoNF4hAIyUaysCKdJKitC8PXoYaWhDqFtSMR4Jys8UPqUV&xkcb=SoDD-_M3JLQfWnQTDh0LbzkdCdPP&xpse=SoBa6_I3JLW9FlWZlB0PbzkdCdPP&sjdu=i6xVERweJM_pVUvgf-MzuaunBTY7G71J5eEX6t4DrDs5EMPQdODrX7Nn-WIPMezoqr5wA_l7Of-3CtoiUawcHw",
|
||||
"sec-ch-ua": '"Google Chrome";v="119", "Chromium";v="119", "Not?A_Brand";v="24"',
|
||||
"sec-ch-ua-mobile": "?0",
|
||||
"sec-ch-ua-platform": '"Windows"',
|
||||
"sec-fetch-dest": "empty",
|
||||
"sec-fetch-mode": "cors",
|
||||
"sec-fetch-site": "same-origin",
|
||||
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36",
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def is_remote_job(job: dict) -> bool:
|
||||
"""
|
||||
:param job:
|
||||
:return: bool
|
||||
"""
|
||||
for taxonomy in job.get("taxonomyAttributes", []):
|
||||
if taxonomy["label"] == "remote" and len(taxonomy["attributes"]) > 0:
|
||||
return True
|
||||
return False
|
||||
|
||||
@@ -4,56 +4,40 @@ jobspy.scrapers.linkedin
|
||||
|
||||
This module contains routines to scrape LinkedIn.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import time
|
||||
import random
|
||||
import regex as re
|
||||
import urllib.parse
|
||||
from typing import Optional
|
||||
from datetime import datetime
|
||||
|
||||
from threading import Lock
|
||||
from bs4.element import Tag
|
||||
import requests
|
||||
import time
|
||||
from requests.exceptions import ProxyError
|
||||
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||||
from bs4 import BeautifulSoup
|
||||
from urllib.parse import urlparse, urlunparse
|
||||
from bs4.element import Tag
|
||||
from threading import Lock
|
||||
|
||||
from .. import Scraper, ScraperInput, Site
|
||||
from ..utils import count_urgent_words, extract_emails_from_text, get_enum_from_job_type
|
||||
from ..exceptions import LinkedInException
|
||||
from ..utils import create_session
|
||||
from ...jobs import (
|
||||
JobPost,
|
||||
Location,
|
||||
JobResponse,
|
||||
JobType,
|
||||
Country,
|
||||
Compensation,
|
||||
DescriptionFormat,
|
||||
)
|
||||
from ..utils import (
|
||||
logger,
|
||||
extract_emails_from_text,
|
||||
get_enum_from_job_type,
|
||||
currency_parser,
|
||||
markdown_converter,
|
||||
)
|
||||
|
||||
|
||||
class LinkedInScraper(Scraper):
|
||||
base_url = "https://www.linkedin.com"
|
||||
delay = 3
|
||||
band_delay = 4
|
||||
jobs_per_page = 25
|
||||
MAX_RETRIES = 3
|
||||
DELAY = 10
|
||||
|
||||
def __init__(self, proxy: Optional[str] = None):
|
||||
"""
|
||||
Initializes LinkedInScraper with the LinkedIn job search url
|
||||
"""
|
||||
super().__init__(Site(Site.LINKEDIN), proxy=proxy)
|
||||
self.scraper_input = None
|
||||
site = Site(Site.LINKEDIN)
|
||||
self.country = "worldwide"
|
||||
self.job_url_direct_regex = re.compile(r'(?<=\?url=)[^"]+')
|
||||
self.url = "https://www.linkedin.com"
|
||||
super().__init__(site, proxy=proxy)
|
||||
|
||||
def scrape(self, scraper_input: ScraperInput) -> JobResponse:
|
||||
"""
|
||||
@@ -61,136 +45,117 @@ class LinkedInScraper(Scraper):
|
||||
:param scraper_input:
|
||||
:return: job_response
|
||||
"""
|
||||
self.scraper_input = scraper_input
|
||||
job_list: list[JobPost] = []
|
||||
seen_urls = set()
|
||||
url_lock = Lock()
|
||||
page = scraper_input.offset // 25 + 25 if scraper_input.offset else 0
|
||||
seconds_old = (
|
||||
scraper_input.hours_old * 3600 if scraper_input.hours_old else None
|
||||
)
|
||||
continue_search = (
|
||||
lambda: len(job_list) < scraper_input.results_wanted and page < 1000
|
||||
)
|
||||
while continue_search():
|
||||
logger.info(f"LinkedIn search page: {page // 25 + 1}")
|
||||
session = create_session(is_tls=False, has_retry=True, delay=5)
|
||||
|
||||
def job_type_code(job_type_enum):
|
||||
mapping = {
|
||||
JobType.FULL_TIME: "F",
|
||||
JobType.PART_TIME: "P",
|
||||
JobType.INTERNSHIP: "I",
|
||||
JobType.CONTRACT: "C",
|
||||
JobType.TEMPORARY: "T",
|
||||
}
|
||||
|
||||
return mapping.get(job_type_enum, "")
|
||||
|
||||
while len(job_list) < scraper_input.results_wanted and page < 1000:
|
||||
params = {
|
||||
"keywords": scraper_input.search_term,
|
||||
"location": scraper_input.location,
|
||||
"distance": scraper_input.distance,
|
||||
"f_WT": 2 if scraper_input.is_remote else None,
|
||||
"f_JT": (
|
||||
self.job_type_code(scraper_input.job_type)
|
||||
if scraper_input.job_type
|
||||
else None
|
||||
),
|
||||
"f_JT": job_type_code(scraper_input.job_type)
|
||||
if scraper_input.job_type
|
||||
else None,
|
||||
"pageNum": 0,
|
||||
"start": page + scraper_input.offset,
|
||||
page: page + scraper_input.offset,
|
||||
"f_AL": "true" if scraper_input.easy_apply else None,
|
||||
"f_C": (
|
||||
",".join(map(str, scraper_input.linkedin_company_ids))
|
||||
if scraper_input.linkedin_company_ids
|
||||
else None
|
||||
),
|
||||
}
|
||||
if seconds_old is not None:
|
||||
params["f_TPR"] = f"r{seconds_old}"
|
||||
|
||||
params = {k: v for k, v in params.items() if v is not None}
|
||||
try:
|
||||
response = session.get(
|
||||
f"{self.base_url}/jobs-guest/jobs/api/seeMoreJobPostings/search?",
|
||||
params=params,
|
||||
allow_redirects=True,
|
||||
proxies=self.proxy,
|
||||
headers=self.headers,
|
||||
timeout=10,
|
||||
)
|
||||
if response.status_code not in range(200, 400):
|
||||
if response.status_code == 429:
|
||||
err = (
|
||||
f"429 Response - Blocked by LinkedIn for too many requests"
|
||||
)
|
||||
else:
|
||||
err = f"LinkedIn response status code {response.status_code}"
|
||||
err += f" - {response.text}"
|
||||
logger.error(err)
|
||||
return JobResponse(jobs=job_list)
|
||||
except Exception as e:
|
||||
if "Proxy responded with" in str(e):
|
||||
logger.error(f"LinkedIn: Bad proxy")
|
||||
else:
|
||||
logger.error(f"LinkedIn: {str(e)}")
|
||||
return JobResponse(jobs=job_list)
|
||||
|
||||
soup = BeautifulSoup(response.text, "html.parser")
|
||||
job_cards = soup.find_all("div", class_="base-search-card")
|
||||
if len(job_cards) == 0:
|
||||
return JobResponse(jobs=job_list)
|
||||
|
||||
for job_card in job_cards:
|
||||
job_url = None
|
||||
href_tag = job_card.find("a", class_="base-card__full-link")
|
||||
if href_tag and "href" in href_tag.attrs:
|
||||
href = href_tag.attrs["href"].split("?")[0]
|
||||
job_id = href.split("-")[-1]
|
||||
job_url = f"{self.base_url}/jobs/view/{job_id}"
|
||||
|
||||
with url_lock:
|
||||
if job_url in seen_urls:
|
||||
continue
|
||||
seen_urls.add(job_url)
|
||||
params = {k: v for k, v in params.items() if v is not None}
|
||||
retries = 0
|
||||
while retries < self.MAX_RETRIES:
|
||||
try:
|
||||
fetch_desc = scraper_input.linkedin_fetch_description
|
||||
job_post = self._process_job(job_card, job_url, fetch_desc)
|
||||
if job_post:
|
||||
job_list.append(job_post)
|
||||
if not continue_search():
|
||||
break
|
||||
response = requests.get(
|
||||
f"{self.url}/jobs-guest/jobs/api/seeMoreJobPostings/search?",
|
||||
params=params,
|
||||
allow_redirects=True,
|
||||
proxies=self.proxy,
|
||||
timeout=10,
|
||||
)
|
||||
response.raise_for_status()
|
||||
|
||||
break
|
||||
except requests.HTTPError as e:
|
||||
if hasattr(e, "response") and e.response is not None:
|
||||
if e.response.status_code == 429:
|
||||
time.sleep(self.DELAY)
|
||||
retries += 1
|
||||
continue
|
||||
else:
|
||||
raise LinkedInException(
|
||||
f"bad response status code: {e.response.status_code}"
|
||||
)
|
||||
else:
|
||||
raise
|
||||
except ProxyError as e:
|
||||
raise LinkedInException("bad proxy")
|
||||
except Exception as e:
|
||||
raise LinkedInException(str(e))
|
||||
else:
|
||||
# Raise an exception if the maximum number of retries is reached
|
||||
raise LinkedInException(
|
||||
"Max retries reached, failed to get a valid response"
|
||||
)
|
||||
|
||||
if continue_search():
|
||||
time.sleep(random.uniform(self.delay, self.delay + self.band_delay))
|
||||
page += self.jobs_per_page
|
||||
soup = BeautifulSoup(response.text, "html.parser")
|
||||
|
||||
with ThreadPoolExecutor(max_workers=5) as executor:
|
||||
futures = []
|
||||
for job_card in soup.find_all("div", class_="base-search-card"):
|
||||
job_url = None
|
||||
href_tag = job_card.find("a", class_="base-card__full-link")
|
||||
if href_tag and "href" in href_tag.attrs:
|
||||
href = href_tag.attrs["href"].split("?")[0]
|
||||
job_id = href.split("-")[-1]
|
||||
job_url = f"{self.url}/jobs/view/{job_id}"
|
||||
|
||||
with url_lock:
|
||||
if job_url in seen_urls:
|
||||
continue
|
||||
seen_urls.add(job_url)
|
||||
|
||||
futures.append(executor.submit(self.process_job, job_card, job_url))
|
||||
|
||||
for future in as_completed(futures):
|
||||
try:
|
||||
job_post = future.result()
|
||||
if job_post:
|
||||
job_list.append(job_post)
|
||||
except Exception as e:
|
||||
raise LinkedInException(
|
||||
"Exception occurred while processing jobs"
|
||||
)
|
||||
page += 25
|
||||
|
||||
job_list = job_list[: scraper_input.results_wanted]
|
||||
return JobResponse(jobs=job_list)
|
||||
|
||||
def _process_job(
|
||||
self, job_card: Tag, job_url: str, full_descr: bool
|
||||
) -> Optional[JobPost]:
|
||||
salary_tag = job_card.find("span", class_="job-search-card__salary-info")
|
||||
|
||||
compensation = None
|
||||
if salary_tag:
|
||||
salary_text = salary_tag.get_text(separator=" ").strip()
|
||||
salary_values = [currency_parser(value) for value in salary_text.split("-")]
|
||||
salary_min = salary_values[0]
|
||||
salary_max = salary_values[1]
|
||||
currency = salary_text[0] if salary_text[0] != "$" else "USD"
|
||||
|
||||
compensation = Compensation(
|
||||
min_amount=int(salary_min),
|
||||
max_amount=int(salary_max),
|
||||
currency=currency,
|
||||
)
|
||||
|
||||
def process_job(self, job_card: Tag, job_url: str) -> Optional[JobPost]:
|
||||
title_tag = job_card.find("span", class_="sr-only")
|
||||
title = title_tag.get_text(strip=True) if title_tag else "N/A"
|
||||
|
||||
company_tag = job_card.find("h4", class_="base-search-card__subtitle")
|
||||
company_a_tag = company_tag.find("a") if company_tag else None
|
||||
company_url = (
|
||||
urlunparse(urlparse(company_a_tag.get("href"))._replace(query=""))
|
||||
if company_a_tag and company_a_tag.has_attr("href")
|
||||
else ""
|
||||
)
|
||||
company = company_a_tag.get_text(strip=True) if company_a_tag else "N/A"
|
||||
|
||||
metadata_card = job_card.find("div", class_="base-search-card__metadata")
|
||||
location = self._get_location(metadata_card)
|
||||
location = self.get_location(metadata_card)
|
||||
|
||||
datetime_tag = (
|
||||
metadata_card.find("time", class_="job-search-card__listdate")
|
||||
@@ -202,87 +167,86 @@ class LinkedInScraper(Scraper):
|
||||
datetime_str = datetime_tag["datetime"]
|
||||
try:
|
||||
date_posted = datetime.strptime(datetime_str, "%Y-%m-%d")
|
||||
except:
|
||||
except Exception as e:
|
||||
date_posted = None
|
||||
job_details = {}
|
||||
if full_descr:
|
||||
job_details = self._get_job_details(job_url)
|
||||
benefits_tag = job_card.find("span", class_="result-benefits__text")
|
||||
benefits = " ".join(benefits_tag.get_text().split()) if benefits_tag else None
|
||||
|
||||
description, job_type = self.get_job_description(job_url)
|
||||
|
||||
return JobPost(
|
||||
id=self._get_id(job_url),
|
||||
title=title,
|
||||
description=description,
|
||||
company_name=company,
|
||||
company_url=company_url,
|
||||
location=location,
|
||||
date_posted=date_posted,
|
||||
job_url=job_url,
|
||||
compensation=compensation,
|
||||
job_type=job_details.get("job_type"),
|
||||
description=job_details.get("description"),
|
||||
job_url_direct=job_details.get("job_url_direct"),
|
||||
emails=extract_emails_from_text(job_details.get("description")),
|
||||
logo_photo_url=job_details.get("logo_photo_url"),
|
||||
# job_type=[JobType.FULL_TIME],
|
||||
job_type=job_type,
|
||||
benefits=benefits,
|
||||
emails=extract_emails_from_text(description) if description else None,
|
||||
num_urgent_words=count_urgent_words(description) if description else None,
|
||||
)
|
||||
|
||||
def _get_id(self, url: str):
|
||||
def get_job_description(
|
||||
self, job_page_url: str
|
||||
) -> tuple[None, None] | tuple[str | None, tuple[str | None, JobType | None]]:
|
||||
"""
|
||||
Extracts the job id from the job url
|
||||
:param url:
|
||||
:return: str
|
||||
"""
|
||||
if not url:
|
||||
return None
|
||||
return url.split("/")[-1]
|
||||
|
||||
def _get_job_details(self, job_page_url: str) -> dict:
|
||||
"""
|
||||
Retrieves job description and other job details by going to the job page url
|
||||
Retrieves job description by going to the job page url
|
||||
:param job_page_url:
|
||||
:return: dict
|
||||
:return: description or None
|
||||
"""
|
||||
try:
|
||||
session = create_session(is_tls=False, has_retry=True)
|
||||
response = session.get(
|
||||
job_page_url, headers=self.headers, timeout=5, proxies=self.proxy
|
||||
)
|
||||
response = requests.get(job_page_url, timeout=5, proxies=self.proxy)
|
||||
response.raise_for_status()
|
||||
except:
|
||||
return {}
|
||||
if response.url == "https://www.linkedin.com/signup":
|
||||
return {}
|
||||
except Exception as e:
|
||||
return None, None
|
||||
|
||||
soup = BeautifulSoup(response.text, "html.parser")
|
||||
div_content = soup.find(
|
||||
"div", class_=lambda x: x and "show-more-less-html__markup" in x
|
||||
)
|
||||
|
||||
description = None
|
||||
if div_content is not None:
|
||||
if div_content:
|
||||
description = " ".join(div_content.get_text().split()).strip()
|
||||
|
||||
def remove_attributes(tag):
|
||||
for attr in list(tag.attrs):
|
||||
del tag[attr]
|
||||
return tag
|
||||
def get_job_type(
|
||||
soup_job_type: BeautifulSoup,
|
||||
) -> list[JobType] | None:
|
||||
"""
|
||||
Gets the job type from job page
|
||||
:param soup_job_type:
|
||||
:return: JobType
|
||||
"""
|
||||
h3_tag = soup_job_type.find(
|
||||
"h3",
|
||||
class_="description__job-criteria-subheader",
|
||||
string=lambda text: "Employment type" in text,
|
||||
)
|
||||
|
||||
div_content = remove_attributes(div_content)
|
||||
description = div_content.prettify(formatter="html")
|
||||
if self.scraper_input.description_format == DescriptionFormat.MARKDOWN:
|
||||
description = markdown_converter(description)
|
||||
return {
|
||||
"description": description,
|
||||
"job_type": self._parse_job_type(soup),
|
||||
"job_url_direct": self._parse_job_url_direct(soup),
|
||||
"logo_photo_url": soup.find("img", {"class": "artdeco-entity-image"}).get(
|
||||
"data-delayed-url"
|
||||
),
|
||||
}
|
||||
employment_type = None
|
||||
if h3_tag:
|
||||
employment_type_span = h3_tag.find_next_sibling(
|
||||
"span",
|
||||
class_="description__job-criteria-text description__job-criteria-text--criteria",
|
||||
)
|
||||
if employment_type_span:
|
||||
employment_type = employment_type_span.get_text(strip=True)
|
||||
employment_type = employment_type.lower()
|
||||
employment_type = employment_type.replace("-", "")
|
||||
|
||||
def _get_location(self, metadata_card: Optional[Tag]) -> Location:
|
||||
return [get_enum_from_job_type(employment_type)]
|
||||
|
||||
return description, get_job_type(soup)
|
||||
|
||||
def get_location(self, metadata_card: Optional[Tag]) -> Location:
|
||||
"""
|
||||
Extracts the location data from the job metadata card.
|
||||
:param metadata_card
|
||||
:return: location
|
||||
"""
|
||||
location = Location(country=Country.from_string(self.country))
|
||||
location = Location(country=self.country)
|
||||
if metadata_card is not None:
|
||||
location_tag = metadata_card.find(
|
||||
"span", class_="job-search-card__location"
|
||||
@@ -294,71 +258,7 @@ class LinkedInScraper(Scraper):
|
||||
location = Location(
|
||||
city=city,
|
||||
state=state,
|
||||
country=Country.from_string(self.country),
|
||||
country=self.country,
|
||||
)
|
||||
elif len(parts) == 3:
|
||||
city, state, country = parts
|
||||
country = Country.from_string(country)
|
||||
location = Location(city=city, state=state, country=country)
|
||||
|
||||
return location
|
||||
|
||||
@staticmethod
|
||||
def _parse_job_type(soup_job_type: BeautifulSoup) -> list[JobType] | None:
|
||||
"""
|
||||
Gets the job type from job page
|
||||
:param soup_job_type:
|
||||
:return: JobType
|
||||
"""
|
||||
h3_tag = soup_job_type.find(
|
||||
"h3",
|
||||
class_="description__job-criteria-subheader",
|
||||
string=lambda text: "Employment type" in text,
|
||||
)
|
||||
employment_type = None
|
||||
if h3_tag:
|
||||
employment_type_span = h3_tag.find_next_sibling(
|
||||
"span",
|
||||
class_="description__job-criteria-text description__job-criteria-text--criteria",
|
||||
)
|
||||
if employment_type_span:
|
||||
employment_type = employment_type_span.get_text(strip=True)
|
||||
employment_type = employment_type.lower()
|
||||
employment_type = employment_type.replace("-", "")
|
||||
|
||||
return [get_enum_from_job_type(employment_type)] if employment_type else []
|
||||
|
||||
def _parse_job_url_direct(self, soup: BeautifulSoup) -> str | None:
|
||||
"""
|
||||
Gets the job url direct from job page
|
||||
:param soup:
|
||||
:return: str
|
||||
"""
|
||||
job_url_direct = None
|
||||
job_url_direct_content = soup.find("code", id="applyUrl")
|
||||
if job_url_direct_content:
|
||||
job_url_direct_match = self.job_url_direct_regex.search(
|
||||
job_url_direct_content.decode_contents().strip()
|
||||
)
|
||||
if job_url_direct_match:
|
||||
job_url_direct = urllib.parse.unquote(job_url_direct_match.group())
|
||||
|
||||
return job_url_direct
|
||||
|
||||
@staticmethod
|
||||
def job_type_code(job_type_enum: JobType) -> str:
|
||||
return {
|
||||
JobType.FULL_TIME: "F",
|
||||
JobType.PART_TIME: "P",
|
||||
JobType.INTERNSHIP: "I",
|
||||
JobType.CONTRACT: "C",
|
||||
JobType.TEMPORARY: "T",
|
||||
}.get(job_type_enum, "")
|
||||
|
||||
headers = {
|
||||
"authority": "www.linkedin.com",
|
||||
"accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
|
||||
"accept-language": "en-US,en;q=0.9",
|
||||
"cache-control": "max-age=0",
|
||||
"upgrade-insecure-requests": "1",
|
||||
"user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
|
||||
}
|
||||
|
||||
@@ -1,48 +1,20 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
import logging
|
||||
import requests
|
||||
import tls_client
|
||||
import numpy as np
|
||||
from markdownify import markdownify as md
|
||||
from requests.adapters import HTTPAdapter, Retry
|
||||
|
||||
from ..jobs import JobType
|
||||
|
||||
logger = logging.getLogger("JobSpy")
|
||||
logger.propagate = False
|
||||
if not logger.handlers:
|
||||
logger.setLevel(logging.INFO)
|
||||
console_handler = logging.StreamHandler()
|
||||
format = "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
|
||||
formatter = logging.Formatter(format)
|
||||
console_handler.setFormatter(formatter)
|
||||
logger.addHandler(console_handler)
|
||||
|
||||
|
||||
def set_logger_level(verbose: int = 2):
|
||||
def count_urgent_words(description: str) -> int:
|
||||
"""
|
||||
Adjusts the logger's level. This function allows the logging level to be changed at runtime.
|
||||
|
||||
Parameters:
|
||||
- verbose: int {0, 1, 2} (default=2, all logs)
|
||||
Count the number of urgent words or phrases in a job description.
|
||||
"""
|
||||
if verbose is None:
|
||||
return
|
||||
level_name = {2: "INFO", 1: "WARNING", 0: "ERROR"}.get(verbose, "INFO")
|
||||
level = getattr(logging, level_name.upper(), None)
|
||||
if level is not None:
|
||||
logger.setLevel(level)
|
||||
else:
|
||||
raise ValueError(f"Invalid log level: {level_name}")
|
||||
urgent_patterns = re.compile(
|
||||
r"\burgen(t|cy)|\bimmediate(ly)?\b|start asap|\bhiring (now|immediate(ly)?)\b",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
matches = re.findall(urgent_patterns, description)
|
||||
count = len(matches)
|
||||
|
||||
|
||||
def markdown_converter(description_html: str):
|
||||
if description_html is None:
|
||||
return None
|
||||
markdown = md(description_html)
|
||||
return markdown.strip()
|
||||
return count
|
||||
|
||||
|
||||
def extract_emails_from_text(text: str) -> list[str] | None:
|
||||
@@ -52,36 +24,24 @@ def extract_emails_from_text(text: str) -> list[str] | None:
|
||||
return email_regex.findall(text)
|
||||
|
||||
|
||||
def create_session(
|
||||
proxy: dict | None = None,
|
||||
is_tls: bool = True,
|
||||
has_retry: bool = False,
|
||||
delay: int = 1,
|
||||
) -> requests.Session:
|
||||
def create_session(proxy: str | None = None):
|
||||
"""
|
||||
Creates a requests session with optional tls, proxy, and retry settings.
|
||||
:return: A session object
|
||||
"""
|
||||
if is_tls:
|
||||
session = tls_client.Session(random_tls_extension_order=True)
|
||||
session.proxies = proxy
|
||||
else:
|
||||
session = requests.Session()
|
||||
session.allow_redirects = True
|
||||
if proxy:
|
||||
session.proxies.update(proxy)
|
||||
if has_retry:
|
||||
retries = Retry(
|
||||
total=3,
|
||||
connect=3,
|
||||
status=3,
|
||||
status_forcelist=[500, 502, 503, 504, 429],
|
||||
backoff_factor=delay,
|
||||
)
|
||||
adapter = HTTPAdapter(max_retries=retries)
|
||||
Creates a tls client session
|
||||
|
||||
:return: A session object with or without proxies.
|
||||
"""
|
||||
session = tls_client.Session(
|
||||
client_identifier="chrome112",
|
||||
random_tls_extension_order=True,
|
||||
)
|
||||
session.proxies = proxy
|
||||
# TODO multiple proxies
|
||||
# if self.proxies:
|
||||
# session.proxies = {
|
||||
# "http": random.choice(self.proxies),
|
||||
# "https": random.choice(self.proxies),
|
||||
# }
|
||||
|
||||
session.mount("http://", adapter)
|
||||
session.mount("https://", adapter)
|
||||
return session
|
||||
|
||||
|
||||
@@ -94,20 +54,3 @@ def get_enum_from_job_type(job_type_str: str) -> JobType | None:
|
||||
if job_type_str in job_type.value:
|
||||
res = job_type
|
||||
return res
|
||||
|
||||
|
||||
def currency_parser(cur_str):
|
||||
# Remove any non-numerical characters
|
||||
# except for ',' '.' or '-' (e.g. EUR)
|
||||
cur_str = re.sub("[^-0-9.,]", "", cur_str)
|
||||
# Remove any 000s separators (either , or .)
|
||||
cur_str = re.sub("[.,]", "", cur_str[:-3]) + cur_str[-3:]
|
||||
|
||||
if "." in list(cur_str[-3:]):
|
||||
num = float(cur_str)
|
||||
elif "," in list(cur_str[-3:]):
|
||||
num = float(cur_str.replace(",", "."))
|
||||
else:
|
||||
num = float(cur_str)
|
||||
|
||||
return np.round(num, 2)
|
||||
|
||||
@@ -4,209 +4,308 @@ jobspy.scrapers.ziprecruiter
|
||||
|
||||
This module contains routines to scrape ZipRecruiter.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import math
|
||||
import time
|
||||
from datetime import datetime
|
||||
import json
|
||||
import re
|
||||
from datetime import datetime, date
|
||||
from typing import Optional, Tuple, Any
|
||||
from urllib.parse import urlparse, parse_qs, urlunparse
|
||||
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
from bs4.element import Tag
|
||||
from concurrent.futures import ThreadPoolExecutor, Future
|
||||
|
||||
from .. import Scraper, ScraperInput, Site
|
||||
from ..utils import (
|
||||
logger,
|
||||
extract_emails_from_text,
|
||||
create_session,
|
||||
markdown_converter,
|
||||
)
|
||||
from ..exceptions import ZipRecruiterException
|
||||
from ..utils import count_urgent_words, extract_emails_from_text, create_session
|
||||
from ...jobs import (
|
||||
JobPost,
|
||||
Compensation,
|
||||
CompensationInterval,
|
||||
Location,
|
||||
JobResponse,
|
||||
JobType,
|
||||
Country,
|
||||
DescriptionFormat,
|
||||
)
|
||||
|
||||
|
||||
class ZipRecruiterScraper(Scraper):
|
||||
base_url = "https://www.ziprecruiter.com"
|
||||
api_url = "https://api.ziprecruiter.com"
|
||||
|
||||
def __init__(self, proxy: Optional[str] = None):
|
||||
"""
|
||||
Initializes ZipRecruiterScraper with the ZipRecruiter job search url
|
||||
Initializes LinkedInScraper with the ZipRecruiter job search url
|
||||
"""
|
||||
self.scraper_input = None
|
||||
self.session = create_session(proxy)
|
||||
self._get_cookies()
|
||||
super().__init__(Site.ZIP_RECRUITER, proxy=proxy)
|
||||
site = Site(Site.ZIP_RECRUITER)
|
||||
self.url = "https://www.ziprecruiter.com"
|
||||
super().__init__(site, proxy=proxy)
|
||||
|
||||
self.delay = 5
|
||||
self.jobs_per_page = 20
|
||||
self.seen_urls = set()
|
||||
|
||||
def find_jobs_in_page(self, scraper_input: ScraperInput, continue_token: Optional[str] = None) -> Tuple[list[JobPost], Optional[str]]:
|
||||
"""
|
||||
Scrapes a page of ZipRecruiter for jobs with scraper_input criteria
|
||||
:param scraper_input:
|
||||
:return: jobs found on page
|
||||
"""
|
||||
params = self.add_params(scraper_input)
|
||||
if continue_token:
|
||||
params['continue'] = continue_token
|
||||
try:
|
||||
response = requests.get(
|
||||
f"https://api.ziprecruiter.com/jobs-app/jobs",
|
||||
headers=self.headers(),
|
||||
params=self.add_params(scraper_input),
|
||||
allow_redirects=True,
|
||||
timeout=10,
|
||||
)
|
||||
if response.status_code != 200:
|
||||
raise ZipRecruiterException(
|
||||
f"bad response status code: {response.status_code}"
|
||||
)
|
||||
except Exception as e:
|
||||
if "Proxy responded with non 200 code" in str(e):
|
||||
raise ZipRecruiterException("bad proxy")
|
||||
raise ZipRecruiterException(str(e))
|
||||
|
||||
response_data = response.json()
|
||||
jobs_list = response_data.get("jobs", [])
|
||||
next_continue_token = response_data.get('continue', None)
|
||||
|
||||
with ThreadPoolExecutor(max_workers=10) as executor:
|
||||
job_results = [
|
||||
executor.submit(self.process_job, job)
|
||||
for job in jobs_list
|
||||
]
|
||||
|
||||
job_list = [result.result() for result in job_results if result.result()]
|
||||
return job_list, next_continue_token
|
||||
|
||||
def scrape(self, scraper_input: ScraperInput) -> JobResponse:
|
||||
"""
|
||||
Scrapes ZipRecruiter for jobs with scraper_input criteria.
|
||||
:param scraper_input: Information about job search criteria.
|
||||
:return: JobResponse containing a list of jobs.
|
||||
"""
|
||||
self.scraper_input = scraper_input
|
||||
job_list: list[JobPost] = []
|
||||
continue_token = None
|
||||
|
||||
max_pages = math.ceil(scraper_input.results_wanted / self.jobs_per_page)
|
||||
|
||||
for page in range(1, max_pages + 1):
|
||||
if len(job_list) >= scraper_input.results_wanted:
|
||||
break
|
||||
if page > 1:
|
||||
time.sleep(self.delay)
|
||||
logger.info(f"ZipRecruiter search page: {page}")
|
||||
jobs_on_page, continue_token = self._find_jobs_in_page(
|
||||
scraper_input, continue_token
|
||||
)
|
||||
|
||||
jobs_on_page, continue_token = self.find_jobs_in_page(scraper_input, continue_token)
|
||||
if jobs_on_page:
|
||||
job_list.extend(jobs_on_page)
|
||||
else:
|
||||
break
|
||||
|
||||
if not continue_token:
|
||||
break
|
||||
return JobResponse(jobs=job_list[: scraper_input.results_wanted])
|
||||
|
||||
def _find_jobs_in_page(
|
||||
self, scraper_input: ScraperInput, continue_token: str | None = None
|
||||
) -> Tuple[list[JobPost], Optional[str]]:
|
||||
"""
|
||||
Scrapes a page of ZipRecruiter for jobs with scraper_input criteria
|
||||
:param scraper_input:
|
||||
:param continue_token:
|
||||
:return: jobs found on page
|
||||
"""
|
||||
jobs_list = []
|
||||
params = self._add_params(scraper_input)
|
||||
if continue_token:
|
||||
params["continue_from"] = continue_token
|
||||
try:
|
||||
res = self.session.get(
|
||||
f"{self.api_url}/jobs-app/jobs", headers=self.headers, params=params
|
||||
)
|
||||
if res.status_code not in range(200, 400):
|
||||
if res.status_code == 429:
|
||||
err = "429 Response - Blocked by ZipRecruiter for too many requests"
|
||||
else:
|
||||
err = f"ZipRecruiter response status code {res.status_code}"
|
||||
err += f" with response: {res.text}" # ZipRecruiter likely not available in EU
|
||||
logger.error(err)
|
||||
return jobs_list, ""
|
||||
except Exception as e:
|
||||
if "Proxy responded with" in str(e):
|
||||
logger.error(f"Indeed: Bad proxy")
|
||||
else:
|
||||
logger.error(f"Indeed: {str(e)}")
|
||||
return jobs_list, ""
|
||||
if len(job_list) > scraper_input.results_wanted:
|
||||
job_list = job_list[:scraper_input.results_wanted]
|
||||
|
||||
res_data = res.json()
|
||||
jobs_list = res_data.get("jobs", [])
|
||||
next_continue_token = res_data.get("continue", None)
|
||||
with ThreadPoolExecutor(max_workers=self.jobs_per_page) as executor:
|
||||
job_results = [executor.submit(self._process_job, job) for job in jobs_list]
|
||||
return JobResponse(jobs=job_list)
|
||||
|
||||
job_list = list(filter(None, (result.result() for result in job_results)))
|
||||
return job_list, next_continue_token
|
||||
|
||||
def _process_job(self, job: dict) -> JobPost | None:
|
||||
"""
|
||||
Processes an individual job dict from the response
|
||||
"""
|
||||
def process_job(self, job: dict) -> JobPost:
|
||||
"""the most common type of jobs page on ZR"""
|
||||
title = job.get("name")
|
||||
job_url = f"{self.base_url}/jobs//j?lvk={job['listing_key']}"
|
||||
if job_url in self.seen_urls:
|
||||
return
|
||||
self.seen_urls.add(job_url)
|
||||
job_url = job.get("job_url")
|
||||
|
||||
description = job.get("job_description", "").strip()
|
||||
description = (
|
||||
markdown_converter(description)
|
||||
if self.scraper_input.description_format == DescriptionFormat.MARKDOWN
|
||||
else description
|
||||
)
|
||||
company = job.get("hiring_company", {}).get("name")
|
||||
country_value = "usa" if job.get("job_country") == "US" else "canada"
|
||||
country_enum = Country.from_string(country_value)
|
||||
description = BeautifulSoup(
|
||||
job.get("job_description", "").strip(), "html.parser"
|
||||
).get_text()
|
||||
|
||||
company = job['hiring_company'].get("name") if "hiring_company" in job else None
|
||||
location = Location(
|
||||
city=job.get("job_city"), state=job.get("job_state"), country=country_enum
|
||||
city=job.get("job_city"), state=job.get("job_state"), country='usa' if job.get("job_country") == 'US' else 'canada'
|
||||
)
|
||||
job_type = self._get_job_type_enum(
|
||||
job_type = ZipRecruiterScraper.get_job_type_enum(
|
||||
job.get("employment_type", "").replace("_", "").lower()
|
||||
)
|
||||
date_posted = datetime.fromisoformat(job["posted_time"].rstrip("Z")).date()
|
||||
comp_interval = job.get("compensation_interval")
|
||||
comp_interval = "yearly" if comp_interval == "annual" else comp_interval
|
||||
comp_min = int(job["compensation_min"]) if "compensation_min" in job else None
|
||||
comp_max = int(job["compensation_max"]) if "compensation_max" in job else None
|
||||
comp_currency = job.get("compensation_currency")
|
||||
|
||||
save_job_url = job.get("SaveJobURL", "")
|
||||
posted_time_match = re.search(
|
||||
r"posted_time=(\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}Z)", save_job_url
|
||||
)
|
||||
if posted_time_match:
|
||||
date_time_str = posted_time_match.group(1)
|
||||
date_posted_obj = datetime.strptime(date_time_str, "%Y-%m-%dT%H:%M:%SZ")
|
||||
date_posted = date_posted_obj.date()
|
||||
else:
|
||||
date_posted = date.today()
|
||||
|
||||
|
||||
return JobPost(
|
||||
id=str(job['listing_key']),
|
||||
title=title,
|
||||
company_name=company,
|
||||
location=location,
|
||||
job_type=job_type,
|
||||
compensation=Compensation(
|
||||
interval=comp_interval,
|
||||
min_amount=comp_min,
|
||||
max_amount=comp_max,
|
||||
currency=comp_currency,
|
||||
interval="yearly" if job.get("compensation_interval") == "annual" else job.get("compensation_interval") ,
|
||||
min_amount=int(job["compensation_min"]) if "compensation_min" in job else None,
|
||||
max_amount=int(job["compensation_max"]) if "compensation_max" in job else None,
|
||||
currency=job.get("compensation_currency"),
|
||||
),
|
||||
date_posted=date_posted,
|
||||
job_url=job_url,
|
||||
description=description,
|
||||
emails=extract_emails_from_text(description) if description else None,
|
||||
num_urgent_words=count_urgent_words(description) if description else None,
|
||||
)
|
||||
|
||||
def _get_cookies(self):
|
||||
data = "event_type=session&logged_in=false&number_of_retry=1&property=model%3AiPhone&property=os%3AiOS&property=locale%3Aen_us&property=app_build_number%3A4734&property=app_version%3A91.0&property=manufacturer%3AApple&property=timestamp%3A2024-01-12T12%3A04%3A42-06%3A00&property=screen_height%3A852&property=os_version%3A16.6.1&property=source%3Ainstall&property=screen_width%3A393&property=device_model%3AiPhone%2014%20Pro&property=brand%3AApple"
|
||||
url = f"{self.api_url}/jobs-app/event"
|
||||
self.session.post(url, data=data, headers=self.headers)
|
||||
|
||||
@staticmethod
|
||||
def _get_job_type_enum(job_type_str: str) -> list[JobType] | None:
|
||||
def get_job_type_enum(job_type_str: str) -> list[JobType] | None:
|
||||
for job_type in JobType:
|
||||
if job_type_str in job_type.value:
|
||||
return [job_type]
|
||||
return None
|
||||
|
||||
@staticmethod
|
||||
def _add_params(scraper_input) -> dict[str, str | Any]:
|
||||
def add_params(scraper_input) -> dict[str, str | Any]:
|
||||
params = {
|
||||
"search": scraper_input.search_term,
|
||||
"location": scraper_input.location,
|
||||
"form": "jobs-landing",
|
||||
}
|
||||
if scraper_input.hours_old:
|
||||
params["days"] = max(scraper_input.hours_old // 24, 1)
|
||||
job_type_map = {JobType.FULL_TIME: "full_time", JobType.PART_TIME: "part_time"}
|
||||
job_type_value = None
|
||||
if scraper_input.job_type:
|
||||
job_type = scraper_input.job_type
|
||||
params["employment_type"] = job_type_map.get(job_type, job_type.value[0])
|
||||
if scraper_input.easy_apply:
|
||||
params["zipapply"] = 1
|
||||
if scraper_input.job_type.value == "fulltime":
|
||||
job_type_value = "full_time"
|
||||
elif scraper_input.job_type.value == "parttime":
|
||||
job_type_value = "part_time"
|
||||
else:
|
||||
job_type_value = scraper_input.job_type.value
|
||||
|
||||
if job_type_value:
|
||||
params[
|
||||
"refine_by_employment"
|
||||
] = f"employment_type:employment_type:{job_type_value}"
|
||||
|
||||
if scraper_input.is_remote:
|
||||
params["remote"] = 1
|
||||
params["refine_by_location_type"] = "only_remote"
|
||||
|
||||
if scraper_input.distance:
|
||||
params["radius"] = scraper_input.distance
|
||||
return {k: v for k, v in params.items() if v is not None}
|
||||
|
||||
headers = {
|
||||
"Host": "api.ziprecruiter.com",
|
||||
"accept": "*/*",
|
||||
"x-zr-zva-override": "100000000;vid:ZT1huzm_EQlDTVEc",
|
||||
"x-pushnotificationid": "0ff4983d38d7fc5b3370297f2bcffcf4b3321c418f5c22dd152a0264707602a0",
|
||||
"x-deviceid": "D77B3A92-E589-46A4-8A39-6EF6F1D86006",
|
||||
"user-agent": "Job Search/87.0 (iPhone; CPU iOS 16_6_1 like Mac OS X)",
|
||||
"authorization": "Basic YTBlZjMyZDYtN2I0Yy00MWVkLWEyODMtYTI1NDAzMzI0YTcyOg==",
|
||||
"accept-language": "en-US,en;q=0.9",
|
||||
}
|
||||
return params
|
||||
|
||||
@staticmethod
|
||||
def get_interval(interval_str: str):
|
||||
"""
|
||||
Maps the interval alias to its appropriate CompensationInterval.
|
||||
:param interval_str
|
||||
:return: CompensationInterval
|
||||
"""
|
||||
interval_alias = {"annually": CompensationInterval.YEARLY}
|
||||
interval_str = interval_str.lower()
|
||||
|
||||
if interval_str in interval_alias:
|
||||
return interval_alias[interval_str]
|
||||
|
||||
return CompensationInterval(interval_str)
|
||||
|
||||
@staticmethod
|
||||
def get_date_posted(job: Tag) -> Optional[datetime.date]:
|
||||
"""
|
||||
Extracts the date a job was posted
|
||||
:param job
|
||||
:return: date the job was posted or None
|
||||
"""
|
||||
button = job.find(
|
||||
"button", {"class": "action_input save_job zrs_btn_secondary_200"}
|
||||
)
|
||||
if not button:
|
||||
return None
|
||||
|
||||
url_time = button.get("data-href", "")
|
||||
url_components = urlparse(url_time)
|
||||
params = parse_qs(url_components.query)
|
||||
posted_time_str = params.get("posted_time", [None])[0]
|
||||
|
||||
if posted_time_str:
|
||||
posted_date = datetime.strptime(
|
||||
posted_time_str, "%Y-%m-%dT%H:%M:%SZ"
|
||||
).date()
|
||||
return posted_date
|
||||
|
||||
return None
|
||||
|
||||
@staticmethod
|
||||
def get_compensation(job: Tag) -> Optional[Compensation]:
|
||||
"""
|
||||
Parses the compensation tag from the job BeautifulSoup object
|
||||
:param job
|
||||
:return: Compensation object or None
|
||||
"""
|
||||
pay_element = job.find("li", {"class": "perk_item perk_pay"})
|
||||
if pay_element is None:
|
||||
return None
|
||||
pay = pay_element.find("div", {"class": "value"}).find("span").text.strip()
|
||||
|
||||
def create_compensation_object(pay_string: str) -> Compensation:
|
||||
"""
|
||||
Creates a Compensation object from a pay_string
|
||||
:param pay_string
|
||||
:return: compensation
|
||||
"""
|
||||
interval = ZipRecruiterScraper.get_interval(pay_string.split()[-1])
|
||||
|
||||
amounts = []
|
||||
for amount in pay_string.split("to"):
|
||||
amount = amount.replace(",", "").strip("$ ").split(" ")[0]
|
||||
if "K" in amount:
|
||||
amount = amount.replace("K", "")
|
||||
amount = int(float(amount)) * 1000
|
||||
else:
|
||||
amount = int(float(amount))
|
||||
amounts.append(amount)
|
||||
|
||||
compensation = Compensation(
|
||||
interval=interval,
|
||||
min_amount=min(amounts),
|
||||
max_amount=max(amounts),
|
||||
currency="USD/CAD",
|
||||
)
|
||||
|
||||
return compensation
|
||||
|
||||
return create_compensation_object(pay)
|
||||
|
||||
@staticmethod
|
||||
def get_location(job: Tag) -> Location:
|
||||
"""
|
||||
Extracts the job location from BeatifulSoup object
|
||||
:param job:
|
||||
:return: location
|
||||
"""
|
||||
location_link = job.find("a", {"class": "company_location"})
|
||||
if location_link is not None:
|
||||
location_string = location_link.text.strip()
|
||||
parts = location_string.split(", ")
|
||||
if len(parts) == 2:
|
||||
city, state = parts
|
||||
else:
|
||||
city, state = None, None
|
||||
else:
|
||||
city, state = None, None
|
||||
return Location(city=city, state=state, country=Country.US_CANADA)
|
||||
|
||||
@staticmethod
|
||||
def headers() -> dict:
|
||||
"""
|
||||
Returns headers needed for requests
|
||||
:return: dict - Dictionary containing headers
|
||||
"""
|
||||
return {
|
||||
'Host': 'api.ziprecruiter.com',
|
||||
'Cookie': 'ziprecruiter_browser=018188e0-045b-4ad7-aa50-627a6c3d43aa; ziprecruiter_session=5259b2219bf95b6d2299a1417424bc2edc9f4b38; SplitSV=2016-10-19%3AU2FsdGVkX19f9%2Bx70knxc%2FeR3xXR8lWoTcYfq5QjmLU%3D%0A; __cf_bm=qXim3DtLPbOL83GIp.ddQEOFVFTc1OBGPckiHYxcz3o-1698521532-0-AfUOCkgCZyVbiW1ziUwyefCfzNrJJTTKPYnif1FZGQkT60dMowmSU/Y/lP+WiygkFPW/KbYJmyc+MQSkkad5YygYaARflaRj51abnD+SyF9V; zglobalid=68d49bd5-0326-428e-aba8-8a04b64bc67c.af2d99ff7c03.653d61bb; ziprecruiter_browser=018188e0-045b-4ad7-aa50-627a6c3d43aa; ziprecruiter_session=5259b2219bf95b6d2299a1417424bc2edc9f4b38',
|
||||
'accept': '*/*',
|
||||
'x-zr-zva-override': '100000000;vid:ZT1huzm_EQlDTVEc',
|
||||
'x-pushnotificationid': '0ff4983d38d7fc5b3370297f2bcffcf4b3321c418f5c22dd152a0264707602a0',
|
||||
'x-deviceid': 'D77B3A92-E589-46A4-8A39-6EF6F1D86006',
|
||||
'user-agent': 'Job Search/87.0 (iPhone; CPU iOS 16_6_1 like Mac OS X)',
|
||||
'authorization': 'Basic YTBlZjMyZDYtN2I0Yy00MWVkLWEyODMtYTI1NDAzMzI0YTcyOg==',
|
||||
'accept-language': 'en-US,en;q=0.9'
|
||||
}
|
||||
|
||||
@@ -4,7 +4,7 @@ import pandas as pd
|
||||
|
||||
def test_all():
|
||||
result = scrape_jobs(
|
||||
site_name=["linkedin", "indeed", "zip_recruiter", "glassdoor"],
|
||||
site_name=["linkedin", "indeed", "zip_recruiter"],
|
||||
search_term="software engineer",
|
||||
results_wanted=5,
|
||||
)
|
||||
|
||||
@@ -1,11 +0,0 @@
|
||||
from ..jobspy import scrape_jobs
|
||||
import pandas as pd
|
||||
|
||||
|
||||
def test_indeed():
|
||||
result = scrape_jobs(
|
||||
site_name="glassdoor", search_term="software engineer", country_indeed="USA"
|
||||
)
|
||||
assert (
|
||||
isinstance(result, pd.DataFrame) and not result.empty
|
||||
), "Result should be a non-empty DataFrame"
|
||||
@@ -4,7 +4,8 @@ import pandas as pd
|
||||
|
||||
def test_indeed():
|
||||
result = scrape_jobs(
|
||||
site_name="indeed", search_term="software engineer", country_indeed="usa"
|
||||
site_name="indeed",
|
||||
search_term="software engineer",
|
||||
)
|
||||
assert (
|
||||
isinstance(result, pd.DataFrame) and not result.empty
|
||||
|
||||
Reference in New Issue
Block a user