1
0
Fork 0
mirror of https://github.com/blackjack4494/yt-dlc.git synced 2024-12-23 00:07:49 +00:00

[dailymotion] Disable the family filter in the playlists (fixes #1524)

This commit is contained in:
Jaime Marquínez Ferrándiz 2013-09-29 12:44:02 +02:00
parent 9c15e9de84
commit 70922df8b5

View file

@ -14,8 +14,15 @@ from ..utils import (
ExtractorError, ExtractorError,
) )
class DailymotionBaseInfoExtractor(InfoExtractor):
@staticmethod
def _build_request(url):
"""Build a request with the family filter disabled"""
request = compat_urllib_request.Request(url)
request.add_header('Cookie', 'family_filter=off')
return request
class DailymotionIE(SubtitlesInfoExtractor): class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
"""Information Extractor for Dailymotion""" """Information Extractor for Dailymotion"""
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)' _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)'
@ -40,8 +47,7 @@ class DailymotionIE(SubtitlesInfoExtractor):
url = 'http://www.dailymotion.com/video/%s' % video_id url = 'http://www.dailymotion.com/video/%s' % video_id
# Retrieve video webpage to extract further information # Retrieve video webpage to extract further information
request = compat_urllib_request.Request(url) request = self._build_request(url)
request.add_header('Cookie', 'family_filter=off')
webpage = self._download_webpage(request, video_id) webpage = self._download_webpage(request, video_id)
# Extract URL, uploader and title from webpage # Extract URL, uploader and title from webpage
@ -113,7 +119,7 @@ class DailymotionIE(SubtitlesInfoExtractor):
return {} return {}
class DailymotionPlaylistIE(InfoExtractor): class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
IE_NAME = u'dailymotion:playlist' IE_NAME = u'dailymotion:playlist'
_VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/' _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
_MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/playlist/.+?".*?>.*?</a>.*?</div>' _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/playlist/.+?".*?>.*?</a>.*?</div>'
@ -122,7 +128,8 @@ class DailymotionPlaylistIE(InfoExtractor):
def _extract_entries(self, id): def _extract_entries(self, id):
video_ids = [] video_ids = []
for pagenum in itertools.count(1): for pagenum in itertools.count(1):
webpage = self._download_webpage(self._PAGE_TEMPLATE % (id, pagenum), request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum))
webpage = self._download_webpage(request,
id, u'Downloading page %s' % pagenum) id, u'Downloading page %s' % pagenum)
playlist_el = get_element_by_attribute(u'class', u'video_list', webpage) playlist_el = get_element_by_attribute(u'class', u'video_list', webpage)