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

Clean newlines in tags and titles

Browse Source
This commit is contained in:
Arun Prakash Jana 2018-08-05 18:16:03 +05:30
parent 5801b8c7e1
commit e0265a5341
No known key found for this signature in database
GPG Key ID: A75979F35C080412
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
buku.py
View File

@ -891,8 +891,8 @@ class BukuDb:
def refreshdb(self, index, threads):
"""Refresh ALL records in the database.
Fetch title for eachbookmark from the web and update the records.
Doesn't update the record if title is empty.
Fetch title for each bookmark from the web and update the records.
Doesn't update the record if fetched title is empty.
Notes
-----
@ -2927,7 +2927,7 @@ def parse_decoded_page(page):
soup = BeautifulSoup(page, 'html5lib')
try:
title = soup.find('title').text.strip()
title = soup.find('title').text.strip().replace('\n', ' ')
except Exception as e:
pass
@ -2946,7 +2946,7 @@ def parse_decoded_page(page):
keywords = soup.find('meta', attrs={'name':'keywords'}) or soup.find('meta', attrs={'name':'Keywords'})
try:
if keywords:
keys = keywords.get('content').strip()
keys = keywords.get('content').strip().replace('\n', ' ')
except Exception as e:
pass
@ -3121,7 +3121,7 @@ def network_handler(url, http_head=False):
return ('', '', '', 1, 0)
if page_title is None:
return ('', page_desc, page_keys, 0, 0)
return (page_title.strip().replace('\n', ''), page_desc, page_keys, 0, 0)
return (page_title, page_desc, page_keys, 0, 0)
def parse_tags(keywords=[]):