mirror of https://github.com/Bunsly/JobSpy
parent
36733c9d99
commit
95be776646
|
@ -58,8 +58,12 @@ class JobPost(BaseModel):
|
||||||
|
|
||||||
|
|
||||||
class JobResponse(BaseModel):
|
class JobResponse(BaseModel):
|
||||||
job_count: int
|
success: bool
|
||||||
page: int = 1
|
error: str = None
|
||||||
total_pages: int
|
|
||||||
|
total_pages: int = None
|
||||||
|
job_count: int = None
|
||||||
|
|
||||||
|
page: int = None
|
||||||
|
jobs: list[JobPost] = []
|
||||||
|
|
||||||
jobs: list[JobPost]
|
|
||||||
|
|
|
@ -1,6 +1,6 @@
|
||||||
from pydantic import BaseModel
|
from pydantic import BaseModel
|
||||||
from enum import Enum
|
from enum import Enum
|
||||||
from ..jobs import JobResponse
|
from ..jobs import JobResponse, JobPost
|
||||||
|
|
||||||
|
|
||||||
class Site(Enum):
|
class Site(Enum):
|
||||||
|
@ -13,13 +13,11 @@ class ScraperInput(BaseModel):
|
||||||
location: str
|
location: str
|
||||||
search_term: str
|
search_term: str
|
||||||
distance: int = 25
|
distance: int = 25
|
||||||
|
results_wanted: int = 15 #: TODO: implement
|
||||||
page: int = 1
|
|
||||||
|
|
||||||
|
|
||||||
class Scraper: #: to be used as a child class
|
class Scraper: #: to be used as a child class
|
||||||
def __init__(self, site: Site):
|
def __init__(self, site: Site):
|
||||||
self.site = site
|
self.site = site
|
||||||
|
|
||||||
def scrape(self, scraper_input: ScraperInput) -> JobResponse:
|
def scrape(self, scraper_input: ScraperInput) -> JobResponse: ...
|
||||||
...
|
|
||||||
|
|
|
@ -10,6 +10,10 @@ from api.core.jobs import *
|
||||||
from api.core.scrapers import Scraper, ScraperInput, Site
|
from api.core.scrapers import Scraper, ScraperInput, Site
|
||||||
|
|
||||||
|
|
||||||
|
class ParsingException(Exception):
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
class IndeedScraper(Scraper):
|
class IndeedScraper(Scraper):
|
||||||
def __init__(self):
|
def __init__(self):
|
||||||
site = Site(Site.INDEED)
|
site = Site(Site.INDEED)
|
||||||
|
@ -25,7 +29,7 @@ class IndeedScraper(Scraper):
|
||||||
"q": scraper_input.search_term,
|
"q": scraper_input.search_term,
|
||||||
"l": scraper_input.location,
|
"l": scraper_input.location,
|
||||||
"filter": 0,
|
"filter": 0,
|
||||||
"start": 0 if scraper_input.page is None else (scraper_input.page - 1) * 10,
|
"start": 0,
|
||||||
"radius": scraper_input.distance,
|
"radius": scraper_input.distance,
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -38,12 +42,25 @@ class IndeedScraper(Scraper):
|
||||||
|
|
||||||
soup = BeautifulSoup(response.content, "html.parser")
|
soup = BeautifulSoup(response.content, "html.parser")
|
||||||
|
|
||||||
jobs = IndeedScraper.parse_jobs(soup)
|
try:
|
||||||
|
jobs = IndeedScraper.parse_jobs(soup)
|
||||||
|
except ParsingException:
|
||||||
|
return JobResponse(
|
||||||
|
success=False,
|
||||||
|
error="Failed to parse jobs.",
|
||||||
|
)
|
||||||
|
|
||||||
total_num_jobs = IndeedScraper.total_jobs(soup)
|
total_num_jobs = IndeedScraper.total_jobs(soup)
|
||||||
total_pages = ceil(total_num_jobs / 15)
|
total_pages = ceil(total_num_jobs / 15)
|
||||||
|
|
||||||
job_list: list[JobPost] = []
|
job_list: list[JobPost] = []
|
||||||
# page_number = jobs["metaData"]["mosaicProviderJobCardsModel"]["pageNumber"]
|
if not jobs.get('metaData', {}).get("mosaicProviderJobCardsModel", {}).get("results"):
|
||||||
|
return JobResponse(
|
||||||
|
success=False,
|
||||||
|
error="No jobs found",
|
||||||
|
)
|
||||||
|
|
||||||
|
page_number = jobs["metaData"]["mosaicProviderJobCardsModel"]["pageNumber"]
|
||||||
for job in jobs["metaData"]["mosaicProviderJobCardsModel"]["results"]:
|
for job in jobs["metaData"]["mosaicProviderJobCardsModel"]["results"]:
|
||||||
snippet_html = BeautifulSoup(job["snippet"], "html.parser")
|
snippet_html = BeautifulSoup(job["snippet"], "html.parser")
|
||||||
|
|
||||||
|
@ -94,9 +111,10 @@ class IndeedScraper(Scraper):
|
||||||
job_list.append(job_post)
|
job_list.append(job_post)
|
||||||
|
|
||||||
job_response = JobResponse(
|
job_response = JobResponse(
|
||||||
|
success=True,
|
||||||
jobs=job_list,
|
jobs=job_list,
|
||||||
job_count=total_num_jobs,
|
job_count=total_num_jobs,
|
||||||
page=scraper_input.page,
|
page=page_number,
|
||||||
total_pages=total_pages,
|
total_pages=total_pages,
|
||||||
)
|
)
|
||||||
return job_response
|
return job_response
|
||||||
|
@ -116,7 +134,14 @@ class IndeedScraper(Scraper):
|
||||||
return None
|
return None
|
||||||
|
|
||||||
@staticmethod
|
@staticmethod
|
||||||
def parse_jobs(soup):
|
def parse_jobs(soup: BeautifulSoup) -> dict:
|
||||||
|
"""
|
||||||
|
Parses the jobs from the soup object
|
||||||
|
|
||||||
|
:param soup:
|
||||||
|
:return: jobs
|
||||||
|
"""
|
||||||
|
|
||||||
script_tag = IndeedScraper.find_mosaic_script(soup)
|
script_tag = IndeedScraper.find_mosaic_script(soup)
|
||||||
|
|
||||||
if script_tag:
|
if script_tag:
|
||||||
|
@ -130,11 +155,9 @@ class IndeedScraper(Scraper):
|
||||||
jobs = json.loads(m.group(1).strip())
|
jobs = json.loads(m.group(1).strip())
|
||||||
return jobs
|
return jobs
|
||||||
else:
|
else:
|
||||||
return {"message": f"Could not find mosaic provider job cards data"}
|
raise ParsingException("Could not find mosaic provider job cards data")
|
||||||
else:
|
else:
|
||||||
return {
|
raise ParsingException("Could not find a script tag containing mosaic provider data")
|
||||||
"message": f"Could not find a script tag containing mosaic provider data"
|
|
||||||
}
|
|
||||||
|
|
||||||
@staticmethod
|
@staticmethod
|
||||||
def total_jobs(soup):
|
def total_jobs(soup):
|
||||||
|
|
Loading…
Reference in New Issue