nojhan/weboob-devel
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[twitter] fix comments parsing

Browse source
This commit is contained in:
Bezleputh 2015-08-24 13:36:58 +02:00
commit 87f89178fc
1 changed files with 7 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

10
modules/twitter/pages.py
View file

@ -104,18 +104,22 @@ class ThreadPage(HTMLPage):
@method @method
class iter_comments(ListElement): class iter_comments(ListElement):
item_xpath = '//ol[@id="stream-items-id"]/li/div' item_xpath = '//ol[@id="stream-items-id"]/li/ol/div/li/div'
class item(ItemElement): class item(ItemElement):
klass = Message klass = Message
obj_id = Regexp(Link('./div/div/a[@class="details with-icn js-details"]'), '/.+/status/(.+)') obj_id = Regexp(Link('./div/div/small/a', default=''), '/.+/status/(.+)', default=None)
obj_title = Regexp(CleanText('./div/p', replace=[('@ ', '@'), ('# ', '#'), ('http:// ', 'http://')]), obj_title = Regexp(CleanText('./div/p', replace=[('@ ', '@'), ('# ', '#'), ('http:// ', 'http://')]),
'(.{50}|.+).+') '(.{50}|.+).+')
obj_content = CleanText('./div/p', replace=[('@ ', '@'), ('# ', '#'), ('http:// ', 'http://')]) obj_content = CleanText('./div/p', replace=[('@ ', '@'), ('# ', '#'), ('http:// ', 'http://')])
obj_sender = Regexp(Link('./div/div/a[@class="details with-icn js-details"]'), '/(.+)/status/.+') obj_sender = Regexp(Link('./div/div/small/a', default=''), '/(.+)/status/.+', default=None)
obj_date = DatetimeFromTimestamp(Attr('./div/div[@class="stream-item-header"]/small/a/span | ./div/div[@class="ProfileTweet-authorDetails"]/span/a/span', 'data-time')) obj_date = DatetimeFromTimestamp(Attr('./div/div[@class="stream-item-header"]/small/a/span | ./div/div[@class="ProfileTweet-authorDetails"]/span/a/span', 'data-time'))
def validate(self, obj):
return obj.id is not None
class SearchPage(HTMLPage): class SearchPage(HTMLPage):
def get_trends_token(self): def get_trends_token(self):