+# coding: utf-8
+from __future__ import unicode_literals
+
import re
import json
import itertools
-import socket
from .common import InfoExtractor
-from .subtitles import NoAutoSubtitlesIE
+from .subtitles import SubtitlesInfoExtractor
from ..utils import (
- compat_http_client,
- compat_urllib_error,
compat_urllib_request,
compat_str,
- get_element_by_attribute,
- get_element_by_id,
-
+ orderedSet,
+ str_to_int,
+ int_or_none,
ExtractorError,
+ unescapeHTML,
)
-class DailymotionIE(NoAutoSubtitlesIE):
+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')
+ request.add_header('Cookie', 'ff=off')
+ return request
+
+
+class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
"""Information Extractor for Dailymotion"""
- _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)'
- IE_NAME = u'dailymotion'
- _TEST = {
- u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
- u'file': u'x33vw9.mp4',
- u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
- u'info_dict': {
- u"uploader": u"Amphora Alex and Van .",
- u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
+ _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)'
+ IE_NAME = 'dailymotion'
+
+ _FORMATS = [
+ ('stream_h264_ld_url', 'ld'),
+ ('stream_h264_url', 'standard'),
+ ('stream_h264_hq_url', 'hq'),
+ ('stream_h264_hd_url', 'hd'),
+ ('stream_h264_hd1080_url', 'hd180'),
+ ]
+
+ _TESTS = [
+ {
+ 'url': 'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
+ 'md5': '392c4b85a60a90dc4792da41ce3144eb',
+ 'info_dict': {
+ 'id': 'x33vw9',
+ 'ext': 'mp4',
+ 'uploader': 'Amphora Alex and Van .',
+ 'title': 'Tutoriel de Youtubeur"DL DES VIDEO DE YOUTUBE"',
+ }
+ },
+ # Vevo video
+ {
+ 'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
+ 'info_dict': {
+ 'title': 'Roar (Official)',
+ 'id': 'USUV71301934',
+ 'ext': 'mp4',
+ 'uploader': 'Katy Perry',
+ 'upload_date': '20130905',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ 'skip': 'VEVO is only available in some countries',
+ },
+ # age-restricted video
+ {
+ 'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
+ 'md5': '0d667a7b9cebecc3c89ee93099c4159d',
+ 'info_dict': {
+ 'id': 'xyh2zz',
+ 'ext': 'mp4',
+ 'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
+ 'uploader': 'HotWaves1012',
+ 'age_limit': 18,
+ }
}
- }
+ ]
def _real_extract(self, url):
- # Extract id and simplified title from URL
- mobj = re.match(self._VALID_URL, url)
-
- video_id = mobj.group(1).split('_')[0].split('?')[0]
-
- video_extension = 'mp4'
+ video_id = self._match_id(url)
url = 'http://www.dailymotion.com/video/%s' % video_id
# Retrieve video webpage to extract further information
- request = compat_urllib_request.Request(url)
- request.add_header('Cookie', 'family_filter=off')
+ request = self._build_request(url)
webpage = self._download_webpage(request, video_id)
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
- video_uploader = self._search_regex([r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>',
- # Looking for official user
- r'<(?:span|a) .*?rel="author".*?>([^<]+?)</'],
- webpage, 'video uploader')
+ # It may just embed a vevo video:
+ m_vevo = re.search(
+ r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?video=(?P<id>[\w]*)',
+ webpage)
+ if m_vevo is not None:
+ vevo_id = m_vevo.group('id')
+ self.to_screen('Vevo video detected: %s' % vevo_id)
+ return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
+
+ age_limit = self._rta_search(webpage)
video_upload_date = None
mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
embed_page = self._download_webpage(embed_url, video_id,
- u'Downloading embed page')
+ 'Downloading embed page')
info = self._search_regex(r'var info = ({.*?}),$', embed_page,
- 'video info', flags=re.MULTILINE)
+ 'video info', flags=re.MULTILINE)
info = json.loads(info)
-
- # TODO: support choosing qualities
-
- for key in ['stream_h264_hd1080_url','stream_h264_hd_url',
- 'stream_h264_hq_url','stream_h264_url',
- 'stream_h264_ld_url']:
- if info.get(key):#key in info and info[key]:
- max_quality = key
- self.to_screen(u'Using %s' % key)
- break
- else:
- raise ExtractorError(u'Unable to extract video URL')
- video_url = info[max_quality]
+ if info.get('error') is not None:
+ msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title']
+ raise ExtractorError(msg, expected=True)
+
+ formats = []
+ for (key, format_id) in self._FORMATS:
+ video_url = info.get(key)
+ if video_url is not None:
+ m_size = re.search(r'H264-(\d+)x(\d+)', video_url)
+ if m_size is not None:
+ width, height = map(int_or_none, (m_size.group(1), m_size.group(2)))
+ else:
+ width, height = None, None
+ formats.append({
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'format_id': format_id,
+ 'width': width,
+ 'height': height,
+ })
+ if not formats:
+ raise ExtractorError('Unable to extract video URL')
# subtitles
- video_subtitles = None
- video_webpage = None
-
- if self._downloader.params.get('writesubtitles', False) or self._downloader.params.get('allsubtitles', False):
- video_subtitles = self._extract_subtitles(video_id)
- elif self._downloader.params.get('writeautomaticsub', False):
- video_subtitles = self._request_automatic_caption(video_id, video_webpage)
-
+ video_subtitles = self.extract_subtitles(video_id, webpage)
if self._downloader.params.get('listsubtitles', False):
- self._list_available_subtitles(video_id)
+ self._list_available_subtitles(video_id, webpage)
return
- return [{
- 'id': video_id,
- 'url': video_url,
- 'uploader': video_uploader,
- 'upload_date': video_upload_date,
- 'title': self._og_search_title(webpage),
- 'ext': video_extension,
- 'subtitles': video_subtitles,
- 'thumbnail': info['thumbnail_url']
- }]
-
- def _get_available_subtitles(self, video_id):
- request = compat_urllib_request.Request('https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id)
+ view_count = str_to_int(self._search_regex(
+ r'video_views_count[^>]+>\s+([\d\.,]+)',
+ webpage, 'view count', fatal=False))
+
+ title = self._og_search_title(webpage, default=None)
+ if title is None:
+ title = self._html_search_regex(
+ r'(?s)<span\s+id="video_title"[^>]*>(.*?)</span>', webpage,
+ 'title')
+
+ return {
+ 'id': video_id,
+ 'formats': formats,
+ 'uploader': info['owner.screenname'],
+ 'upload_date': video_upload_date,
+ 'title': title,
+ 'subtitles': video_subtitles,
+ 'thumbnail': info['thumbnail_url'],
+ 'age_limit': age_limit,
+ 'view_count': view_count,
+ }
+
+ def _get_available_subtitles(self, video_id, webpage):
try:
- sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
+ sub_list = self._download_webpage(
+ 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
+ video_id, note=False)
+ except ExtractorError as err:
+ self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err))
return {}
info = json.loads(sub_list)
if (info['total'] > 0):
sub_lang_list = dict((l['language'], l['url']) for l in info['list'])
return sub_lang_list
- self._downloader.report_warning(u'video doesn\'t have subtitles')
+ self._downloader.report_warning('video doesn\'t have subtitles')
return {}
-class DailymotionPlaylistIE(InfoExtractor):
+class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
+ IE_NAME = 'dailymotion:playlist'
_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>'
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- playlist_id = mobj.group('id')
+ _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"'
+ _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'
+ _TESTS = [{
+ 'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q',
+ 'info_dict': {
+ 'title': 'SPORT',
+ },
+ 'playlist_mincount': 20,
+ }]
+
+ def _extract_entries(self, id):
video_ids = []
-
for pagenum in itertools.count(1):
- webpage = self._download_webpage('https://www.dailymotion.com/playlist/%s/%s' % (playlist_id, pagenum),
- playlist_id, u'Downloading page %s' % pagenum)
+ request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum))
+ webpage = self._download_webpage(request,
+ id, 'Downloading page %s' % pagenum)
- playlist_el = get_element_by_attribute(u'class', u'video_list', webpage)
- video_ids.extend(re.findall(r'data-id="(.+?)" data-ext-id', playlist_el))
+ video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage))
- if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
+ if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
break
+ return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
+ for video_id in orderedSet(video_ids)]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ playlist_id = mobj.group('id')
+ webpage = self._download_webpage(url, playlist_id)
+
+ return {
+ '_type': 'playlist',
+ 'id': playlist_id,
+ 'title': self._og_search_title(webpage),
+ 'entries': self._extract_entries(playlist_id),
+ }
+
- entries = [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
- for video_id in video_ids]
- return {'_type': 'playlist',
- 'id': playlist_id,
- 'title': get_element_by_id(u'playlist_name', webpage),
- 'entries': entries,
- }
+class DailymotionUserIE(DailymotionPlaylistIE):
+ IE_NAME = 'dailymotion:user'
+ _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
+ _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
+ _TESTS = [{
+ 'url': 'https://www.dailymotion.com/user/nqtv',
+ 'info_dict': {
+ 'id': 'nqtv',
+ 'title': 'Rémi Gaillard',
+ },
+ 'playlist_mincount': 100,
+ }]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ user = mobj.group('user')
+ webpage = self._download_webpage(url, user)
+ full_user = unescapeHTML(self._html_search_regex(
+ r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user),
+ webpage, 'user'))
+
+ return {
+ '_type': 'playlist',
+ 'id': user,
+ 'title': full_user,
+ 'entries': self._extract_entries(user),
+ }
projects / youtube-dl / blobdiff