Skip to content

Fix for some LI profiles where there are only 2 elements #199

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

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Fix for some LI profiles where there are only 2 elements #199

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1cf008d
Fix for some LI profiles where there are only 2 elements
angelystor Nov 2, 2023
73ec99d
Fix for individuals who have hidden their education
angelystor Nov 2, 2023
8ff5eba
Add open to work with a default
angelystor Nov 2, 2023
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: 13 additions & 1 deletion linkedin_scraper/person.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,7 @@ def __init__(
close_on_complete=True,
time_to_wait_after_login=0,
):
self.open_to_work = None
self.linkedin_url = linkedin_url
self.name = name
self.about = about or []
Expand Down Expand Up @@ -127,6 +128,7 @@ def get_experiences(self):
position_summary_text = position_details_list[1] if len(position_details_list) > 1 else None
outer_positions = position_summary_details.find_element(By.XPATH,"*").find_elements(By.XPATH,"*")

work_times = ""
if len(outer_positions) == 4:
position_title = outer_positions[0].find_element(By.TAG_NAME,"span").text
company = outer_positions[1].find_element(By.TAG_NAME,"span").text
Expand All @@ -143,6 +145,11 @@ def get_experiences(self):
company = outer_positions[0].find_element(By.TAG_NAME,"span").text
work_times = outer_positions[1].find_element(By.TAG_NAME,"span").text
location = outer_positions[2].find_element(By.TAG_NAME,"span").text
elif len(outer_positions) == 2:
position_title = ""
company = outer_positions[0].find_element(By.TAG_NAME,"span").text
work_times = outer_positions[1].find_element(By.TAG_NAME,"span").text
location = ""

times = work_times.split("·")[0].strip() if work_times else ""
duration = work_times.split("·")[1].strip() if len(work_times.split("·")) > 1 else None
Expand Down Expand Up @@ -200,7 +207,12 @@ def get_educations(self):
main = self.wait_for_element_to_load(by=By.TAG_NAME, name="main")
self.scroll_to_half()
self.scroll_to_bottom()
main_list = self.wait_for_element_to_load(name="pvs-list", base=main)
try:
main_list = self.wait_for_element_to_load(name="pvs-list", base=main)
except:
# if education is hidden, this value will not be shown
return

for position in main_list.find_elements(By.CLASS_NAME,"pvs-entity"):
institution_logo_elem, position_details = position.find_elements(By.XPATH,"*")

Expand Down