mirror of https://github.com/Bunsly/JobSpy
Cullen Watson
GitHub
parent
91b137ef86
commit
aeb1a50d2c
|
|
@ -1,6 +1,6 @@
|
|||
[tool.poetry]
|
||||
name = "python-jobspy"
|
||||
version = "1.1.43"
|
||||
version = "1.1.44"
|
||||
description = "Job scraper for LinkedIn, Indeed, Glassdoor & ZipRecruiter"
|
||||
authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
|
||||
homepage = "https://github.com/Bunsly/JobSpy"
|
||||
|
|
|
|||
|
|
@ -192,4 +192,4 @@ def scrape_jobs(
|
|||
else:
|
||||
jobs_formatted_df = pd.DataFrame()
|
||||
|
||||
return jobs_formatted_df.sort_values(by='date_posted', ascending=False)
|
||||
return jobs_formatted_df.sort_values(by=['site', 'date_posted'], ascending=[True, False])
|
||||
|
|
|
|||
|
|
@ -6,7 +6,6 @@ This module contains routines to scrape Glassdoor.
|
|||
"""
|
||||
import json
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
from typing import Optional
|
||||
from datetime import datetime, timedelta
|
||||
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||||
|
|
@ -14,7 +13,7 @@ from ..utils import count_urgent_words, extract_emails_from_text
|
|||
|
||||
from .. import Scraper, ScraperInput, Site
|
||||
from ..exceptions import GlassdoorException
|
||||
from ..utils import create_session, modify_and_get_description
|
||||
from ..utils import create_session
|
||||
from ...jobs import (
|
||||
JobPost,
|
||||
Compensation,
|
||||
|
|
@ -35,6 +34,7 @@ class GlassdoorScraper(Scraper):
|
|||
|
||||
self.url = None
|
||||
self.country = None
|
||||
self.session = None
|
||||
self.jobs_per_page = 30
|
||||
self.seen_urls = set()
|
||||
|
||||
|
|
@ -53,8 +53,7 @@ class GlassdoorScraper(Scraper):
|
|||
payload = self.add_payload(
|
||||
scraper_input, location_id, location_type, page_num, cursor
|
||||
)
|
||||
session = create_session(self.proxy, is_tls=False, has_retry=True)
|
||||
response = session.post(
|
||||
response = self.session.post(
|
||||
f"{self.url}/graph", headers=self.headers(), timeout=10, data=payload
|
||||
)
|
||||
if response.status_code != 200:
|
||||
|
|
@ -73,7 +72,6 @@ class GlassdoorScraper(Scraper):
|
|||
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):
|
||||
job_data = future_to_job_data[future]
|
||||
try:
|
||||
job_post = future.result()
|
||||
if job_post:
|
||||
|
|
@ -111,7 +109,7 @@ class GlassdoorScraper(Scraper):
|
|||
|
||||
try:
|
||||
description = self.fetch_job_description(job_id)
|
||||
except Exception as e :
|
||||
except:
|
||||
description = None
|
||||
|
||||
job_post = JobPost(
|
||||
|
|
@ -145,6 +143,8 @@ class GlassdoorScraper(Scraper):
|
|||
all_jobs: list[JobPost] = []
|
||||
cursor = None
|
||||
max_pages = 30
|
||||
self.session = create_session(self.proxy, is_tls=False, has_retry=True)
|
||||
self.session.get(self.url)
|
||||
|
||||
try:
|
||||
for page in range(
|
||||
|
|
@ -201,8 +201,7 @@ class GlassdoorScraper(Scraper):
|
|||
return None
|
||||
data = response.json()[0]
|
||||
desc = data['data']['jobview']['job']['description']
|
||||
soup = BeautifulSoup(desc, 'html.parser')
|
||||
return modify_and_get_description(soup)
|
||||
return desc
|
||||
|
||||
@staticmethod
|
||||
def parse_compensation(data: dict) -> Optional[Compensation]:
|
||||
|
|
@ -267,7 +266,6 @@ class GlassdoorScraper(Scraper):
|
|||
filter_params.append({"filterKey": "fromAge", "values": str(fromage)})
|
||||
payload = {
|
||||
"operationName": "JobSearchResultsQuery",
|
||||
|
||||
"variables": {
|
||||
"excludeJobListingIds": [],
|
||||
"filterParams": filter_params,
|
||||
|
|
@ -281,21 +279,177 @@ class GlassdoorScraper(Scraper):
|
|||
"fromage": fromage,
|
||||
"sort": "date"
|
||||
},
|
||||
"query": "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) {\n jobListings(\n 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}}\n ) {\n companyFilterOptions {\n id\n shortName\n __typename\n }\n filterOptions\n indeedCtk\n jobListings {\n ...JobView\n __typename\n }\n jobListingSeoLinks {\n linkItems {\n position\n url\n __typename\n }\n __typename\n }\n jobSearchTrackingKey\n jobsPageSeoData {\n pageMetaDescription\n pageTitle\n __typename\n }\n paginationCursors {\n cursor\n pageNumber\n __typename\n }\n indexablePageForSeo\n searchResultsMetadata {\n searchCriteria {\n implicitLocation {\n id\n localizedDisplayName\n type\n __typename\n }\n keyword\n location {\n id\n shortName\n localizedShortName\n localizedDisplayName\n type\n __typename\n }\n __typename\n }\n footerVO {\n countryMenu {\n childNavigationLinks {\n id\n link\n textKey\n __typename\n }\n __typename\n }\n __typename\n }\n helpCenterDomain\n helpCenterLocale\n jobAlert {\n jobAlertExists\n __typename\n }\n jobSerpFaq {\n questions {\n answer\n question\n __typename\n }\n __typename\n }\n jobSerpJobOutlook {\n occupation\n paragraph\n __typename\n }\n showMachineReadableJobs\n __typename\n }\n serpSeoLinksVO {\n relatedJobTitlesResults\n searchedJobTitle\n searchedKeyword\n searchedLocationIdAsString\n searchedLocationSeoName\n searchedLocationType\n topCityIdsToNameResults {\n key\n value\n __typename\n }\n topEmployerIdsToNameResults {\n key\n value\n __typename\n }\n topEmployerNameResults\n topOccupationResults\n __typename\n }\n totalJobsCount\n __typename\n }\n}\n\nfragment JobView on JobListingSearchResult {\n jobview {\n header {\n adOrderId\n advertiserType\n adOrderSponsorshipLevel\n ageInDays\n divisionEmployerName\n easyApply\n employer {\n id\n name\n shortName\n __typename\n }\n employerNameFromSearch\n goc\n gocConfidence\n gocId\n jobCountryId\n jobLink\n jobResultTrackingKey\n jobTitleText\n locationName\n locationType\n locId\n needsCommission\n payCurrency\n payPeriod\n payPeriodAdjustedPay {\n p10\n p50\n p90\n __typename\n }\n rating\n salarySource\n savedJobId\n sponsored\n __typename\n }\n job {\n descriptionFragments\n importConfigId\n jobTitleId\n jobTitleText\n listingId\n __typename\n }\n jobListingAdminDetails {\n cpcVal\n importConfigId\n jobListingId\n jobSourceId\n userEligibleForAdminJobDetails\n __typename\n }\n overview {\n shortName\n squareLogoUrl\n __typename\n }\n __typename\n }\n __typename\n}\n",
|
||||
"query": """
|
||||
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
|
||||
}
|
||||
}
|
||||
|
||||
job_type_filters = {
|
||||
JobType.FULL_TIME: "fulltime",
|
||||
JobType.PART_TIME: "parttime",
|
||||
JobType.CONTRACT: "contract",
|
||||
JobType.INTERNSHIP: "internship",
|
||||
JobType.TEMPORARY: "temporary",
|
||||
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
|
||||
}
|
||||
"""
|
||||
}
|
||||
|
||||
if scraper_input.job_type in job_type_filters:
|
||||
filter_value = job_type_filters[scraper_input.job_type]
|
||||
if scraper_input.job_type:
|
||||
payload["variables"]["filterParams"].append(
|
||||
{"filterKey": "jobType", "values": filter_value}
|
||||
{"filterKey": "jobType", "values": scraper_input.job_type.value[0]}
|
||||
)
|
||||
return json.dumps([payload])
|
||||
|
||||
|
|
@ -331,7 +485,6 @@ class GlassdoorScraper(Scraper):
|
|||
"apollographql-client-name": "job-search-next",
|
||||
"apollographql-client-version": "4.65.5",
|
||||
"content-type": "application/json",
|
||||
"cookie": 'gdId=91e2dfc4-c8b5-4fa7-83d0-11512b80262c; G_ENABLED_IDPS=google; trs=https%3A%2F%2Fwww.redhat.com%2F:referral:referral:2023-07-05+09%3A50%3A14.862:undefined:undefined; g_state={"i_p":1688587331651,"i_l":1}; _cfuvid=.7llazxhYFZWi6EISSPdVjtqF0NMVwzxr_E.cB1jgLs-1697828392979-0-604800000; GSESSIONID=undefined; JSESSIONID=F03DD1B5EE02DB6D842FE42B142F88F3; cass=1; jobsClicked=true; indeedCtk=1hd77b301k79i801; asst=1697829114.2; G_AUTHUSER_H=0; uc=8013A8318C98C517FE6DD0024636DFDEF978FC33266D93A2FAFEF364EACA608949D8B8FA2DC243D62DE271D733EB189D809ABE5B08D7B1AE865D217BD4EEBB97C282F5DA5FEFE79C937E3F6110B2A3A0ADBBA3B4B6DF5A996FEE00516100A65FCB11DA26817BE8D1C1BF6CFE36B5B68A3FDC2CFEC83AB797F7841FBB157C202332FC7E077B56BD39B167BDF3D9866E3B; AWSALB=zxc/Yk1nbWXXT6HjNyn3H4h4950ckVsFV/zOrq5LSoChYLE1qV+hDI8Axi3fUa9rlskndcO0M+Fw+ZnJ+AQ2afBFpyOd1acouLMYgkbEpqpQaWhY6/Gv4QH1zBcJ; AWSALBCORS=zxc/Yk1nbWXXT6HjNyn3H4h4950ckVsFV/zOrq5LSoChYLE1qV+hDI8Axi3fUa9rlskndcO0M+Fw+ZnJ+AQ2afBFpyOd1acouLMYgkbEpqpQaWhY6/Gv4QH1zBcJ; gdsid=1697828393025:1697830776351:668396EDB9E6A832022D34414128093D; at=HkH8Hnqi9uaMC7eu0okqyIwqp07ht9hBvE1_St7E_hRqPvkO9pUeJ1Jcpds4F3g6LL5ADaCNlxrPn0o6DumGMfog8qI1-zxaV_jpiFs3pugntw6WpVyYWdfioIZ1IDKupyteeLQEM1AO4zhGjY_rPZynpsiZBPO_B1au94sKv64rv23yvP56OiWKKfI-8_9hhLACEwWvM-Az7X-4aE2QdFt93VJbXbbGVf07bdDZfimsIkTtgJCLSRhU1V0kEM1Efyu66vo3m77gFFaMW7lxyYnb36I5PdDtEXBm3aL-zR7-qa5ywd94ISEivgqQOA4FPItNhqIlX4XrfD1lxVz6rfPaoTIDi4DI6UMCUjwyPsuv8mn0rYqDfRnmJpZ97fJ5AnhrknAd_6ZWN5v1OrxJczHzcXd8LO820QPoqxzzG13bmSTXLwGSxMUCtSrVsq05hicimQ3jpRt0c1dA4OkTNqF7_770B9JfcHcM8cr8-C4IL56dnOjr9KBGfN1Q2IvZM2cOBRbV7okiNOzKVZ3qJ24AE34WA2F3U6Whiu6H8nIuGG5hSNkVygY6CtglNZfFF9p8pJAZm79PngrrBv-CXFBZmhYLFo46lmFetDkiJ6mirtez4tKpzTIYjIp4_JAkiZFwbLJ2QGH4mK8kyyW0lZiX1DTuQec50N_5wvRo0Gt7nlKxzLsApMnaNhuQeH5ygh_pa381ORo9mQGi0EYF9zk00pa2--z4PtjfQ8KFq36GgpxKy5-o4qgqygZj8F01L8r-FiX2G4C7PREMIpAyHX2A4-_JxA1IS2j12EyqKTLqE9VcP06qm2Z-YuIW3ctmpMxy5G9_KiEiGv17weizhSFnl6SbpAEY-2VSmQ5V6jm3hoMp2jemkuGCRkZeFstLDEPxlzFN7WM; __cf_bm=zGaVjIJw4irf40_7UVw54B6Ohm271RUX4Tc8KVScrbs-1697830777-0-AYv2GnKTnnCU+cY9xHbJunO0DwlLDO6SIBnC/s/qldpKsGK0rRAjD6y8lbyATT/KlS7g29OZaN4fbd0lrJg0KmWbIybZIzfWVLHSYePVuOhu; asst=1697829114.2; at=dFhXf64wsf2TlnWy41xLs7skJkuxgKToEGcjGtDfUvW4oEAJ4tTIR5dKQ8wbwT75aIaGgdCfvcb-da7vwrCGWscCncmfLFQpJ9l-LLwoRfk-pMsxHhd77wvf-W7I0HSm7-Q5lQJqI9WyNGRxOa-RpzBTf4L8_Et4-3FzjPaAoYY5pY1FhuwXbN5asGOAMW-p8cjpbfn3PumlIYuckguWnjrcY2F31YJ_1noeoHM9tCGpymANbqGXRkG6aXY7yCfVXtdgZU1K5SMeaSPZIuF_iLUxjc_corzpNiH6qq7BIAmh-e5Aa-g7cwpZcln1fmwTVw4uTMZf1eLIMTa9WzgqZNkvG-sGaq_XxKA_Wai6xTTkOHfRgm4632Ba2963wdJvkGmUUa3tb_L4_wTgk3eFnHp5JhghLfT2Pe3KidP-yX__vx8JOsqe3fndCkKXgVz7xQKe1Dur-sMNlGwi4LXfguTT2YUI8C5Miq3pj2IHc7dC97eyyAiAM4HvyGWfaXWZcei6oIGrOwMvYgy0AcwFry6SIP2SxLT5TrxinRRuem1r1IcOTJsMJyUPp1QsZ7bOyq9G_0060B4CPyovw5523hEuqLTM-R5e5yavY6C_1DHUyE15C3mrh7kdvmlGZeflnHqkFTEKwwOftm-Mv-CKD5Db9ABFGNxKB2FH7nDH67hfOvm4tGNMzceBPKYJ3wciTt9jK3wy39_7cOYVywfrZ-oLhw_XtsbGSSeGn3HytrfgSADAh2sT0Gg6eCC9Xy1vh-Za337SVLUDXZ73W2xJxxUHBkFzZs8L_Xndo5DsbpWhVs9IYUGyraJdqB3SLgDbAppIBCJl4fx6_DG8-xOQPBvuFMlTROe1JVdHOzXI1GElwFDTuH1pjkg4I2G0NhAbE06Y-1illQE; gdsid=1697828393025:1697831731408:99C30D94108AC3030D61C736DDCDF11C',
|
||||
"gd-csrf-token": "Ft6oHEWlRZrxDww95Cpazw:0pGUrkb2y3TyOpAIqF2vbPmUXoXVkD3oEGDVkvfeCerceQ5-n8mBg3BovySUIjmCPHCaW0H2nQVdqzbtsYqf4Q:wcqRqeegRUa9MVLJGyujVXB7vWFPjdaS1CtrrzJq-ok",
|
||||
"origin": "https://www.glassdoor.com",
|
||||
"referer": "https://www.glassdoor.com/",
|
||||
|
|
|
|||
|
|
@ -11,7 +11,6 @@ import requests
|
|||
from typing import Any
|
||||
from datetime import datetime
|
||||
|
||||
import urllib.parse
|
||||
from bs4 import BeautifulSoup
|
||||
from bs4.element import Tag
|
||||
from concurrent.futures import ThreadPoolExecutor, Future
|
||||
|
|
@ -22,7 +21,7 @@ from ..utils import (
|
|||
extract_emails_from_text,
|
||||
create_session,
|
||||
get_enum_from_job_type,
|
||||
modify_and_get_description
|
||||
logger
|
||||
)
|
||||
from ...jobs import (
|
||||
JobPost,
|
||||
|
|
@ -50,13 +49,14 @@ class IndeedScraper(Scraper):
|
|||
|
||||
def scrape_page(
|
||||
self, scraper_input: ScraperInput, page: int
|
||||
) -> tuple[list[JobPost], int]:
|
||||
) -> list[JobPost]:
|
||||
"""
|
||||
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
|
||||
"""
|
||||
job_list = []
|
||||
self.country = scraper_input.country
|
||||
domain = self.country.indeed_domain_value
|
||||
self.url = f"https://{domain}.indeed.com"
|
||||
|
|
@ -76,14 +76,14 @@ class IndeedScraper(Scraper):
|
|||
)
|
||||
except Exception as e:
|
||||
if "Proxy responded with" in str(e):
|
||||
raise IndeedException("bad proxy")
|
||||
raise IndeedException(str(e))
|
||||
logger.error(f'Indeed: Bad proxy')
|
||||
else:
|
||||
logger.error(f'Indeed: {str(e)}')
|
||||
return job_list
|
||||
|
||||
soup = BeautifulSoup(response.content, "html.parser")
|
||||
job_list = []
|
||||
total_num_jobs = IndeedScraper.total_jobs(soup)
|
||||
if "did not match any jobs" in response.text:
|
||||
return job_list, total_num_jobs
|
||||
return job_list
|
||||
|
||||
jobs = IndeedScraper.parse_jobs(
|
||||
soup
|
||||
|
|
@ -145,7 +145,7 @@ class IndeedScraper(Scraper):
|
|||
|
||||
job_list = [result.result() for result in job_results if result.result()]
|
||||
|
||||
return job_list, total_num_jobs
|
||||
return job_list
|
||||
|
||||
def scrape(self, scraper_input: ScraperInput) -> JobResponse:
|
||||
"""
|
||||
|
|
@ -153,7 +153,7 @@ class IndeedScraper(Scraper):
|
|||
:param scraper_input:
|
||||
:return: job_response
|
||||
"""
|
||||
job_list, total_results = self.scrape_page(scraper_input, 0)
|
||||
job_list = self.scrape_page(scraper_input, 0)
|
||||
pages_processed = 1
|
||||
|
||||
while len(self.seen_urls) < scraper_input.results_wanted:
|
||||
|
|
@ -167,7 +167,7 @@ class IndeedScraper(Scraper):
|
|||
]
|
||||
|
||||
for future in futures:
|
||||
jobs, _ = future.result()
|
||||
jobs = future.result()
|
||||
if jobs:
|
||||
job_list += jobs
|
||||
new_jobs = True
|
||||
|
|
@ -182,55 +182,7 @@ class IndeedScraper(Scraper):
|
|||
if len(self.seen_urls) > scraper_input.results_wanted:
|
||||
job_list = job_list[:scraper_input.results_wanted]
|
||||
|
||||
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}/m/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
|
||||
|
||||
try:
|
||||
soup = BeautifulSoup(response.text, 'html.parser')
|
||||
script_tags = soup.find_all('script')
|
||||
|
||||
job_description = ''
|
||||
for tag in script_tags:
|
||||
if 'window._initialData' in tag.text:
|
||||
json_str = tag.text
|
||||
json_str = json_str.split('window._initialData=')[1]
|
||||
json_str = json_str.rsplit(';', 1)[0]
|
||||
data = json.loads(json_str)
|
||||
job_description = data["jobInfoWrapperModel"]["jobInfoModel"]["sanitizedJobDescription"]
|
||||
break
|
||||
except (KeyError, TypeError, IndexError):
|
||||
return None
|
||||
|
||||
soup = BeautifulSoup(job_description, "html.parser")
|
||||
return modify_and_get_description(soup)
|
||||
return JobResponse(jobs=job_list)
|
||||
|
||||
@staticmethod
|
||||
def get_job_type(job: dict) -> list[JobType] | None:
|
||||
|
|
@ -330,24 +282,6 @@ class IndeedScraper(Scraper):
|
|||
"Could not find any results for the search"
|
||||
)
|
||||
|
||||
@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 {
|
||||
|
|
@ -380,7 +314,7 @@ class IndeedScraper(Scraper):
|
|||
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))
|
||||
sc_values.append("jt({})".format(scraper_input.job_type.value[0]))
|
||||
|
||||
if sc_values:
|
||||
params["sc"] = "0kf:" + "".join(sc_values) + ";"
|
||||
|
|
@ -406,7 +340,7 @@ class IndeedScraper(Scraper):
|
|||
taxonomy["label"] == "remote" and len(taxonomy["attributes"]) > 0
|
||||
for taxonomy in job.get("taxonomyAttributes", [])
|
||||
)
|
||||
return is_remote_in_attributes or is_remote_in_description or is_remote_in_location
|
||||
return is_remote_in_attributes or is_remote_in_description or is_remote_in_location or is_remote_in_taxonomy
|
||||
|
||||
def get_job_details(self, job_keys: list[str]) -> dict:
|
||||
"""
|
||||
|
|
|
|||
|
|
@ -31,8 +31,7 @@ from ..utils import (
|
|||
count_urgent_words,
|
||||
extract_emails_from_text,
|
||||
get_enum_from_job_type,
|
||||
currency_parser,
|
||||
modify_and_get_description
|
||||
currency_parser
|
||||
)
|
||||
|
||||
|
||||
|
|
@ -236,10 +235,15 @@ class LinkedInScraper(Scraper):
|
|||
div_content = soup.find(
|
||||
"div", class_=lambda x: x and "show-more-less-html__markup" in x
|
||||
)
|
||||
|
||||
description = None
|
||||
if div_content:
|
||||
description = modify_and_get_description(div_content)
|
||||
if div_content is not None:
|
||||
def remove_attributes(tag):
|
||||
for attr in list(tag.attrs):
|
||||
del tag[attr]
|
||||
return tag
|
||||
|
||||
div_content = remove_attributes(div_content)
|
||||
description = div_content.prettify(formatter="html")
|
||||
|
||||
def get_job_type(
|
||||
soup_job_type: BeautifulSoup,
|
||||
|
|
|
|||
|
|
@ -1,4 +1,5 @@
|
|||
import re
|
||||
import logging
|
||||
import numpy as np
|
||||
|
||||
import tls_client
|
||||
|
|
@ -7,14 +8,14 @@ from requests.adapters import HTTPAdapter, Retry
|
|||
|
||||
from ..jobs import JobType
|
||||
|
||||
|
||||
def modify_and_get_description(soup):
|
||||
for li in soup.find_all('li'):
|
||||
li.string = "- " + li.get_text()
|
||||
|
||||
description = soup.get_text(separator='\n').strip()
|
||||
description = re.sub(r'\n+', '\n', description)
|
||||
return description
|
||||
logger = logging.getLogger("JobSpy")
|
||||
if not logger.handlers:
|
||||
logger.setLevel(logging.ERROR)
|
||||
console_handler = logging.StreamHandler()
|
||||
console_handler.setLevel(logging.ERROR)
|
||||
formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
|
||||
console_handler.setFormatter(formatter)
|
||||
logger.addHandler(console_handler)
|
||||
|
||||
|
||||
def count_urgent_words(description: str) -> int:
|
||||
|
|
@ -79,6 +80,7 @@ def get_enum_from_job_type(job_type_str: str) -> JobType | None:
|
|||
res = job_type
|
||||
return res
|
||||
|
||||
|
||||
def currency_parser(cur_str):
|
||||
# Remove any non-numerical characters
|
||||
# except for ',' '.' or '-' (e.g. EUR)
|
||||
|
|
@ -94,3 +96,5 @@ def currency_parser(cur_str):
|
|||
num = float(cur_str)
|
||||
|
||||
return np.round(num, 2)
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -9,13 +9,12 @@ import time
|
|||
from datetime import datetime, timezone
|
||||
from typing import Optional, Tuple, Any
|
||||
|
||||
from bs4 import BeautifulSoup
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
|
||||
from .. import Scraper, ScraperInput, Site
|
||||
from ..exceptions import ZipRecruiterException
|
||||
from ...jobs import JobPost, Compensation, Location, JobResponse, JobType, Country
|
||||
from ..utils import count_urgent_words, extract_emails_from_text, create_session, modify_and_get_description
|
||||
from ..utils import count_urgent_words, extract_emails_from_text, create_session
|
||||
|
||||
|
||||
class ZipRecruiterScraper(Scraper):
|
||||
|
|
@ -107,9 +106,7 @@ class ZipRecruiterScraper(Scraper):
|
|||
return
|
||||
self.seen_urls.add(job_url)
|
||||
|
||||
job_description_html = job.get("job_description", "").strip()
|
||||
description_soup = BeautifulSoup(job_description_html, "html.parser")
|
||||
description = modify_and_get_description(description_soup)
|
||||
description = job.get("job_description", "").strip()
|
||||
|
||||
company = job.get("hiring_company", {}).get("name")
|
||||
country_value = "usa" if job.get("job_country") == "US" else "canada"
|
||||
|
|
@ -168,25 +165,16 @@ class ZipRecruiterScraper(Scraper):
|
|||
if scraper_input.hours_old:
|
||||
fromage = max(scraper_input.hours_old // 24, 1) if scraper_input.hours_old else None
|
||||
params['days'] = fromage
|
||||
job_type_value = None
|
||||
job_type_map = {
|
||||
JobType.FULL_TIME: 'full_time',
|
||||
JobType.PART_TIME: 'part_time'
|
||||
}
|
||||
if scraper_input.job_type:
|
||||
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
|
||||
params['employment_type'] = job_type_map[scraper_input.job_type] if scraper_input.job_type in job_type_map else scraper_input.job_type.value[0]
|
||||
if scraper_input.easy_apply:
|
||||
params['zipapply'] = 1
|
||||
|
||||
if job_type_value:
|
||||
params[
|
||||
"refine_by_employment"
|
||||
] = f"employment_type:employment_type:{job_type_value}"
|
||||
|
||||
if scraper_input.is_remote:
|
||||
params["refine_by_location_type"] = "only_remote"
|
||||
|
||||
params["remote"] = 1
|
||||
if scraper_input.distance:
|
||||
params["radius"] = scraper_input.distance
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue