ccppi/job-scrapper
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

added indeed suport

Browse Source 
start extracting date from "vor X days" where time = today-X
This commit is contained in:
ccppi
2024-07-23 14:55:37 +02:00
parent 8d59514ddf
commit 42d11c1c8d
5 changed files with 80 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
lib/scrap_jobs.py
View File

@@ -4,31 +4,43 @@ DEBUG = True
def log(*s):
if DEBUG:
print(s)
def indeed_com(url,session):
def scrap_indeed_com(url,entry,session):
log("[scrap_indeed_com] url: ",url)
jobs = []
if(session == 0):
with requests.Session() as session:
page = session.get(url)
log(page)
else:
# if(session == 0):
with requests.Session() as session:
session.headers = {
"User-Agent" : "Mozilla/5.0 (X11; Linux x86_64; rv:127.0) Gecko/20100101 Firefox/127.0"
}
page = session.get(url)
log(page)
# else:
# page = session.get(url)
# log(page)
soup = BeautifulSoup(page.content,"html.parser")
#print(soup.prettify())
results = soup.find_all("li",class_= 'css-5lfssm eu4oa1w0')
results = soup.find_all("li",class_= 'css-5lfssm eu4oa1w0') #top level list element
location = item("p",{'data-testid':'text-location'},0)
ar_location = finder(results,location,LOCATION_CLEANUP=1,ATTRS=1)
location = item("div",{'data-testid':'text-location'},0,"indeed location")
ar_location = finder(results,location,ATTRS=1,LOCATION_CLEANUP=1)
company = item("p",{'data-testid':'company-name'},0)
ar_company = finder(results,location,ATTRS=1)
company = item("span",{'data-testid':'company-name'},0,"indeed company")
ar_company = finder(results,company,ATTRS=1)
title = item("a",'jobTitle',0)
ar_title = finder(results,location)
title = item("a",'jcs-JobTitle',0,"indeed title")
ar_title = finder(results,title,GETCHILDREN="span")
date = item("span","Span-sc-1ybanni-0 Text__span-sc-1lu7urs-12 Text-sc-1lu7urs-13 krGudM hUhFmL",0)
ar_date = finder(results,date,CLEANDATE=1)
date = item("span",{'data-testid':'myJobsStateDate'},0,"indeed date")
ar_date = finder(results,date,ATTRS=1)
link = item("a",'jcs-JobTitle',0,"link")
ar_link = finder(results,link,LINK=1,BASEURL="https://ch.indeed.com")
tag = entry.tag#get from config
return arrayToClass(ar_title,ar_company,ar_location,ar_date,ar_link,tag)
def scrap_jobs(url,entry,session):
jobs = []
@@ -64,6 +76,28 @@ def scrap_jobs(url,entry,session):
tag = entry.tag#get from config
return arrayToClass(ar_title,ar_company,ar_location,ar_date,ar_link,tag)
def next_url_indeed_com(url,session,baseurl):
next_link_str = ''
if(session == 0):
with requests.Session() as session:
page = session.get(url)
else:
page = requests.get(url)
soup = BeautifulSoup(page.content,"html.parser")
result_next = soup.findAll("nav",attrs={"role":"navigation"})
next_=item("a",{'data-testid':'pagination-page-next'},0)
next_link = finder(result_next,next_,ATTRS=1,LINK=1)
if next_link:
if(next_link[0] != "NOTFound"):
next_link_str = str(next_link[0])
next_link_str = baseurl + next_link_str
log(next_link_str)
else:
return 0
if next_link_str != '':
return next_link_str
else:
return 0
def next_url_jobs_ch(url,session,baseurl):
next_link_str = ''
if(session == 0):