Skip to content

bugs fixed and minor improvements in get_title and get_site_name #46

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 1 commit into
base: master
Choose a base branch
from
Open

bugs fixed and minor improvements in get_title and get_site_name #46

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
29 changes: 14 additions & 15 deletions scraper/scrape.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,18 +4,14 @@
def get_title(html):
"""Scrape page title."""
title = None
if html.title.string:
title = html.title.string
elif html.find("meta", property="og:title"):
description = html.find("meta", property="og:title").get('content')
if html.find("meta", property="og:title"):
title = html.find("meta", property="og:title").get('content')
elif html.find("meta", property="twitter:title"):
description = html.find("meta", property="twitter:title").get('content')
title = html.find("meta", property="twitter:title").get('content')
elif html.find("title"):
title = html.find("title").string
elif html.find("h1"):
title = html.find("h1").string
elif html.find_all("h1"):
title = html.find_all("h1")[0].string
if title:
title = title.split('|')[0]
return title


Expand Down Expand Up @@ -52,13 +48,16 @@ def get_image(html):
def get_site_name(html, url):
"""Scrape site name."""
if html.find("meta", property="og:site_name"):
sitename = html.find("meta", property="og:site_name").get('content')
elif html.find("meta", property='twitter:title'):
sitename = html.find("meta", property="twitter:title").get('content')
site_name = html.find("meta", property="og:site_name").get('content')
elif html.find("meta", property='twitter:site'):
site_name = html.find("meta", property="twitter:site").get('content')
else:
sitename = url.split('//')[1]
return sitename.split('/')[0].rsplit('.')[1].capitalize()
return sitename
site_name = url.split('//')[1]
if site_name.split('/')[0].rsplit('.')[0] == 'www':
return site_name.split('/')[0].rsplit('.')[1]
else:
return site_name.split('/')[0].rsplit('.')[0]
return site_name


def get_favicon(html, url):
Expand Down