[smotri] Add support for moderated (?) videos (Fixes #2030)

This commit is contained in:
Philipp Hagemeister 2013-12-23 03:44:47 +01:00
parent 8d0bdeba18
commit 7dbf5ae587

View File

@ -1,5 +1,6 @@
# encoding: utf-8 # encoding: utf-8
import os.path
import re import re
import json import json
import hashlib import hashlib
@ -10,6 +11,7 @@
compat_urllib_parse, compat_urllib_parse,
compat_urllib_request, compat_urllib_request,
ExtractorError, ExtractorError,
url_basename,
) )
@ -132,7 +134,16 @@ def _real_extract(self, url):
# We will extract some from the video web page instead # We will extract some from the video web page instead
video_page_url = 'http://' + mobj.group('url') video_page_url = 'http://' + mobj.group('url')
video_page = self._download_webpage(video_page_url, video_id, u'Downloading video page') video_page = self._download_webpage(video_page_url, video_id, u'Downloading video page')
# Warning if video is unavailable
warning = self._html_search_regex(
r'<div class="videoUnModer">(.*?)</div>', video_page,
u'warning messagef', default=None)
if warning is not None:
self._downloader.report_warning(
u'Video %s may not be available; smotri said: %s ' %
(video_id, warning))
# Adult content # Adult content
if re.search(u'EroConfirmText">', video_page) is not None: if re.search(u'EroConfirmText">', video_page) is not None:
self.report_age_confirmation() self.report_age_confirmation()
@ -148,7 +159,7 @@ def _real_extract(self, url):
# Extract the rest of meta data # Extract the rest of meta data
video_title = self._search_meta(u'name', video_page, u'title') video_title = self._search_meta(u'name', video_page, u'title')
if not video_title: if not video_title:
video_title = video_url.rsplit('/', 1)[-1] video_title = os.path.splitext(url_basename(video_url))[0]
video_description = self._search_meta(u'description', video_page) video_description = self._search_meta(u'description', video_page)
END_TEXT = u' на сайте Smotri.com' END_TEXT = u' на сайте Smotri.com'