Skip to content

Updated to work with latest LinkedIn #120

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 1, 2022
Merged

Updated to work with latest LinkedIn #120

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 12 additions & 2 deletions linkedin_scraper/company.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,8 +42,10 @@ class Company(Scraper):
company_type = None
company_size = None
specialties = None
showcase_pages =[]
showcase_pages = []
affiliated_companies = []
employees = []
headcount = None

def __init__(self, linkedin_url = None, name = None, about_us =None, website = None, headquarters = None, founded = None, industry = None, company_type = None, company_size = None, specialties = None, showcase_pages =[], affiliated_companies = [], driver = None, scrape = True, get_employees = True, close_on_complete = True):
self.linkedin_url = linkedin_url
Expand Down Expand Up @@ -205,7 +207,7 @@ def scrape_logged_in(self, get_employees = True, close_on_complete = True):
section_id = 3
#section ID is no longer needed, we are using class name now.
#grid = driver.find_elements_by_tag_name("section")[section_id]
grid = driver.find_element_by_class_name("artdeco-card.p4.mb3")
grid = driver.find_element_by_class_name("artdeco-card.p5.mb4")
print(grid)
descWrapper = grid.find_elements_by_tag_name("p")
if len(descWrapper) > 0:
Expand Down Expand Up @@ -236,6 +238,13 @@ def scrape_logged_in(self, get_employees = True, close_on_complete = True):
elif txt == 'Specialties':
self.specialties = "\n".join(values[i+x_off].text.strip().split(", "))

grid = driver.find_element_by_class_name("mt1")
spans = grid.find_elements_by_tag_name("span")
for span in spans:
txt = span.text.strip()
if "See all" in txt and "employees on LinkedIn" in txt:
self.headcount = int(txt.replace("See all", "").replace("employees on LinkedIn", "").strip())

driver.execute_script("window.scrollTo(0, Math.ceil(document.body.scrollHeight/2));")


Expand Down Expand Up @@ -346,6 +355,7 @@ def __repr__(self):
_output['founded'] = self.founded
_output['affiliated_companies'] = self.affiliated_companies
_output['employees'] = self.employees
_output['headcount'] = self.headcount

return json.dumps(_output).replace('\n', '')

2 changes: 1 addition & 1 deletion linkedin_scraper/person.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
from selenium.webdriver.support import expected_conditions as EC
from .objects import Experience, Education, Scraper, Interest, Accomplishment, Contact
import os
from linkedin_scraper import selectors
import selectors


class Person(Scraper):
Expand Down