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

[twitter] follow timelines while hastags querying

Browse source
This commit is contained in:
Bezleputh 2014-06-03 01:07:17 +02:00
commit d5ef80ead3
2 changed files with 5 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

7
modules/twitter/browser.py
View file

@ -20,8 +20,8 @@
from weboob.tools.browser2 import LoginBrowser, URL, need_login
from weboob.tools.browser import BrowserIncorrectPassword
from weboob.capabilities.messages import Message
from .pages import LoginPage, LoginErrorPage, ThreadPage, TwitterBasePage, Tweet, TrendsPage,\
TimelinePage, HomeTimelinePage, SearchTimelinePage
from .pages import LoginPage, LoginErrorPage, ThreadPage, Tweet, TrendsPage,\
TimelinePage, HomeTimelinePage, SearchTimelinePage
__all__ = ['TwitterBrowser']
@ -34,7 +34,6 @@ class TwitterBrowser(LoginBrowser):
login_error = URL(u'login/error.+', LoginErrorPage)
tweet = URL(u'i/tweet/create', Tweet)
trends = URL(u'trends', TrendsPage)
hashtag = URL(u'hashtag/(?P<path>.+)\?f=realtime', TwitterBasePage)
search = URL(u'i/search/timeline', SearchTimelinePage)
profil = URL(u'i/profiles/show/(?P<path>.+)/timeline/with_replies', HomeTimelinePage)
timeline = URL(u'i/timeline', TimelinePage)
@ -115,7 +114,7 @@ class TwitterBrowser(LoginBrowser):
return self.profil.go(path=path).iter_threads()
def get_tweets_from_hashtag(self, path):
return self.hashtag.go(path=path.lstrip('#')).iter_threads()
return self.get_tweets_from_search(u'#%s' % path if not path.startswith('#') else path)
def get_tweets_from_search(self, path):
params = {'q': "%s" % path,

21
modules/twitter/pages.py
View file

@ -27,7 +27,7 @@ from weboob.tools.browser2.page import HTMLPage, JsonPage, method, ListElement,
from weboob.tools.browser2.filters import CleanText, Format, Link, Regexp, Env, DateTime, Attr, Filter
from weboob.capabilities.messages import Thread, Message
from weboob.capabilities.base import CapBaseObject
__all__ = ['LoginPage', 'LoginErrorPage', 'ThreadPage', 'TwitterBasePage', 'Tweet', 'TrendsPage', 'TimelinePage', 'HomeTimelinePage', 'SearchTimelinePage']
__all__ = ['LoginPage', 'LoginErrorPage', 'ThreadPage', 'Tweet', 'TrendsPage', 'TimelinePage', 'HomeTimelinePage', 'SearchTimelinePage']
class DatetimeFromTimestamp(Filter):
@ -55,24 +55,7 @@ class TwitterJsonHTMLPage(JsonPage):
self.doc = html.parse(StringIO(self.doc['items_html']), parser)
class TwitterBasePage(HTMLPage):
@method
class iter_threads(ListElement):
item_xpath = '//*[@data-item-type="tweet"]/div'
class item(ItemElement):
klass = Thread
obj_id = Regexp(Link('./div/div/a[@class="details with-icn js-details"]|./div/div/span/a[@class="ProfileTweet-timestamp js-permalink js-nav js-tooltip"]'), '/(.+)/status/(.+)', '\\1#\\2')
obj_title = Format('%s \n\t %s',
CleanText('./div/div[@class="stream-item-header"]/a|./div/div[@class="ProfileTweet-authorDetails"]/a',
replace=[('@ ', '@'), ('# ', '#'), ('http:// ', 'http://')]),
CleanText('./div/p',
replace=[('@ ', '@'), ('# ', '#'), ('http:// ', 'http://')]))
obj_date = DatetimeFromTimestamp(Attr('./div/div[@class="stream-item-header"]/small/a/span|./div/div/span/a[@class="ProfileTweet-timestamp js-permalink js-nav js-tooltip"]/span', 'data-time'))
class LoginPage(TwitterBasePage):
class LoginPage(HTMLPage):
def login(self, login, passwd):
form = self.get_form(xpath='//form[@action="https://twitter.com/sessions"]')
form['session[username_or_email]'] = login