def get_jobs(self):
jobs = []
self.get_max_page()
for page_number in range(self.max_page):
page_soup = self.request_page(page_number=page_number)
vacancy_list = page_soup.find_all('div', 'vacancy-serp-item')
for vacancy in vacancy_list:
title = vacancy.find('a').text
link = vacancy.find('a')['href']
location = vacancy.find(
'span', 'vacancy-serp-item__meta-info').text.split(',')[0]
company = vacancy.find(
'div', 'vacancy-serp-item__meta-info-company').text
salary = vacancy.find(
'div', 'vacancy-serp-item__sidebar').find('span')
if salary is not None:
salary = salary.text
else:
salary = ''
description = vacancy.select(
'div[data-qa="vacancy-serp__vacancy_snippet_responsibility"]'
)[0].text
jobs.append(
Vacancy(title=title,
link=link,
location=location,
company=company,
salary=salary,
description=description))
return jobs
def get_jobs(self):
jobs = []
self.get_max_page()
for page_number in range(1, self.max_page + 1):
page_soup = self.request_page(page_number=page_number)
vacancy_list = page_soup.find_all('div', {'class': '-job'})
for vacancy in vacancy_list:
title = vacancy.find('h2').text
link = f'https://stackoverflow.com/{vacancy.find("h2").find("a")["href"]}'
company_data = vacancy.find('h3').find_all('span',
recursive=False)
location = company_data[1].text
company = company_data[0].text
jobs.append(
Vacancy(title=title,
link=link,
location=location,
company=company,
salary='',
description=''))
return jobs
}
companydb.insert(new_company_info)
company_object_id = companydb.find_one(
{"name": company})
company_object_id = company_object_id["_id"]
print(company_object_id)
print("done")
else:
company_object_id = companydb.find_one(
{"name": company})
company_object_id = company_object_id["_id"]
print("Company already exists: ",
company_object_id)
# Vacany User
vacancy_returned = Vacancy(vacancy_link, location_id,
cookies)
if vacancy_returned["Email"] == "":
if vacancy_returned["Phone_Number"] == "":
user_object_id = 100000000000000000000000
else:
check = userdb.find_one({
"phone":
vacancy_returned["Phone_Number"]
})
if check is None:
phone = vacancy_returned["Phone_Number"]
add = phone.split(" ", 1)
code = add[0]
code = code.replace("+", "")
number = add[1]
number = number.replace(" ", "")
try:
logo = Selector(response=page).xpath(f'/html/body/div[{div}]/div/img/@src').get()
logo = "https://www.worknet.am" + logo
except:
logo = ""
data = {
"company" : company,
"c_link" : c_link,
"position" : position,
"v_link" : v_link,
"logo" : logo
}
returned = Vacancy(v_link)
print(data)
# COMPANY DATA
# Check if company already exists in a collection
check = companydb.find_one({"name" : company})
if check is None:
new_company_info = {
"name" : company,
"url" : c_link,
"industry" : "1",
"logo" : logo,
"created_at" : datetime.datetime.utcnow(),
"websites" : returned["website"],
"custom_button_title": "Visit",
"custom_button_url": c_link
},
"country": "GE"
}
companydb.insert(new_company_info)
company_object_id = companydb.find_one({"name": company})
company_object_id = company_object_id["_id"]
print(company_object_id)
print("done")
else:
company_object_id = companydb.find_one({"name": company})
company_object_id = company_object_id["_id"]
print("Company already exists: ", company_object_id)
vacancy_returned = Vacancy(v_link, cookies)
# Vacancy User
if vacancy_returned["email"] == "":
user_object_id = 100000000000000000000000
else:
check = userdb.find_one(
{"email": vacancy_returned["email"]})
if check is None:
new_user_info = {
"email": vacancy_returned["email"],
"company_id": ObjectId(f"{company_object_id}"),
"created_at": datetime.datetime.utcnow()
}
userdb.insert(new_user_info)
user_object_id = userdb.find_one(
attrs={
'data-qa': 'vacancy-serp__vacancy-employer'
}).text
requirement = div.find(
"div",
attrs={
'data-qa': 'vacancy-serp__vacancy_snippet_requirement'
}).text
salary = div.find('div',
attrs={
'data-qa':
'vacancy-serp__vacancy-compensation'
}).text
vac = Vacancy(title=title,
href=href,
company=company,
requirement=requirement,
salary=salary)
vacancy_list.append(vac)
except:
pass
for i in vacancy_list:
print(i.get_title(), i.get_salary(), i.get_requirement())
data2 = {
"title": [x.get_title() for x in vacancy_list],
"href": [x.get_href() for x in vacancy_list],
"company": [x.get_company() for x in vacancy_list],
"requirement": [x.get_requirement() for x in vacancy_list],
session = requests.Session()
req = session.get(url, headers = headers)
if req.status_code == 200:
soup = bs(req.content, "html.parser")
divs = soup.find_all("div", attrs = {"data-qa":"vacancy-serp__vacancy"})
for div in divs:
try:
title = div.find("a", attrs = {"data-qa":"vacancy-serp__vacancy-title"}).text
company = div.find("a", attrs = {"data-qa":"vacancy-serp__vacancy-employer"}).text
salary = div.find("div", attrs = {"data-qa":"vacancy-serp__vacancy-compensation"}).text
vac = Vacancy(text_request, title, company, salary)
vac.salaryParse()
vac.save_to_db()
except:
pass
else:
print("ERROR!", req.status_code)
