pjht/buku
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

More meta tags to look for page description

Browse Source
This commit is contained in:
Arun Prakash Jana 2018-08-05 21:52:42 +05:30
parent cc6151a775
commit 62923397b3
No known key found for this signature in database
GPG Key ID: A75979F35C080412
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
buku.py
View File

@ -2951,18 +2951,22 @@ def parse_decoded_page(page):
try: try:
title = soup.find('title').text.strip().replace('\n', ' ') title = soup.find('title').text.strip().replace('\n', ' ')
except Exception as e: except Exception as e:
logdbg(e)
pass pass
description = (soup.find('meta', attrs={'name':'og:description'}) or description = (soup.find('meta', attrs={'name':'og:description'}) or
soup.find('meta', attrs={'property':'description'}) or
soup.find('meta', attrs={'name':'description'}) or
soup.find('meta', attrs={'name':'og:Description'}) or soup.find('meta', attrs={'name':'og:Description'}) or
soup.find('meta', attrs={'property':'og:description'}) or
soup.find('meta', attrs={'property':'og:Description'}) or
soup.find('meta', attrs={'property':'description'}) or
soup.find('meta', attrs={'property':'Description'}) or soup.find('meta', attrs={'property':'Description'}) or
soup.find('meta', attrs={'name':'description'}) or
soup.find('meta', attrs={'name':'Description'})) soup.find('meta', attrs={'name':'Description'}))
try: try:
if description: if description:
desc = description.get('content').strip() desc = description.get('content').strip()
except Exception as e: except Exception as e:
logdbg(e)
pass pass
keywords = soup.find('meta', attrs={'name':'keywords'}) or soup.find('meta', attrs={'name':'Keywords'}) keywords = soup.find('meta', attrs={'name':'keywords'}) or soup.find('meta', attrs={'name':'Keywords'})
@ -2970,6 +2974,7 @@ def parse_decoded_page(page):
if keywords: if keywords:
keys = keywords.get('content').strip().replace('\n', ' ') keys = keywords.get('content').strip().replace('\n', ' ')
except Exception as e: except Exception as e:
logdbg(e)
pass pass
logdbg('title: %s' % title) logdbg('title: %s' % title)