Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Add url_search_order parameter to web2lrf DefaultProfile

Browse Source
This commit is contained in:
Kovid Goyal 2007-11-29 05:38:00 +00:00
parent a433be5ba5
commit 0746c9a34a
1 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
src/libprs500/ebooks/lrf/web/profiles/__init__.py
View File

@ -34,6 +34,7 @@ class DefaultProfile(object):
delay = 0 # Delay between consecutive downloads delay = 0 # Delay between consecutive downloads
timeout = 10 # Timeout for fetching files from server in seconds timeout = 10 # Timeout for fetching files from server in seconds
timefmt = ' [%a %d %b %Y]' # The format of the date shown on the first page timefmt = ' [%a %d %b %Y]' # The format of the date shown on the first page
url_search_order = ['guid', 'link'] # THe order of elements to search for a URL when parssing the RSS feed
pubdate_fmt = None # The format string used to parse the publication date in the RSS feed. If set to None some default heuristics are used, these may fail, in which case set this to the correct string or re-implement strptime in your subclass. pubdate_fmt = None # The format string used to parse the publication date in the RSS feed. If set to None some default heuristics are used, these may fail, in which case set this to the correct string or re-implement strptime in your subclass.
no_stylesheets = False # Download stylesheets only if False no_stylesheets = False # Download stylesheets only if False
match_regexps = [] # List of regular expressions that determines which links to follow match_regexps = [] # List of regular expressions that determines which links to follow
@ -172,9 +173,11 @@ class DefaultProfile(object):
continue continue
pubdate = pubdate.string pubdate = pubdate.string
pubdate = pubdate.replace('+0000', 'GMT') pubdate = pubdate.replace('+0000', 'GMT')
url = item.find('guid') for element in self.url_search_order:
if not url: url = item.find(element)
url = item.find('link') if url:
break
if not url or not url.string: if not url or not url.string:
self.logger.debug('Skipping article as it does not have a link url') self.logger.debug('Skipping article as it does not have a link url')
continue continue