Skip to content

sel edge url fix #33

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: main
Choose a base branch
from
+10 −8
Open

sel edge url fix #33

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
bd47d0a
updated date selector
timf34 May 10, 2025
143fcb8
selenium edge url not found fix
dsouzaankit Aug 12, 2025
42246c8
Merge branch 'timf34:main' into selEdge1
dsouzaankit Aug 12, 2025
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
18 changes: 10 additions & 8 deletions substack_scraper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,13 +20,13 @@
from urllib.parse import urlparse
from config import EMAIL, PASSWORD

USE_PREMIUM: bool = False # Set to True if you want to login to Substack and convert paid for posts
BASE_SUBSTACK_URL: str = "https://www.thefitzwilliam.com/" # Substack you want to convert to markdown
USE_PREMIUM: bool = True # Set to True if you want to login to Substack and convert paid for posts
BASE_SUBSTACK_URL: str = "https://premSubstk.io/" # Substack you want to convert to markdown
BASE_MD_DIR: str = "substack_md_files" # Name of the directory we'll save the .md essay files
BASE_HTML_DIR: str = "substack_html_pages" # Name of the directory we'll save the .html essay files
HTML_TEMPLATE: str = "author_template.html" # HTML template to use for the author page
JSON_DATA_DIR: str = "data"
NUM_POSTS_TO_SCRAPE: int = 3 # Set to 0 if you want all posts
NUM_POSTS_TO_SCRAPE: int = 0 # Set to 0 if you want all posts


def extract_main_part(url: str) -> str:
Expand Down Expand Up @@ -381,12 +381,14 @@ def __init__(
if user_agent:
options.add_argument(f'user-agent={user_agent}') # Pass this if running headless and blocked by captcha

if edge_driver_path:
service = Service(executable_path=edge_driver_path)
else:
service = Service(EdgeChromiumDriverManager().install())
# if edge_driver_path:
# service = Service(executable_path=edge_driver_path)
# else:
# service = Service(EdgeChromiumDriverManager().install())

self.driver = webdriver.Edge(service=service, options=options)
os.environ["SE_DRIVER_MIRROR_URL"] = "https://msedgedriver.microsoft.com"
self.driver = webdriver.Edge()
# self.driver = webdriver.Edge(service=service, options=options)
self.login()

def login(self) -> None:
Expand Down