-# coding: utf-8
-from __future__ import unicode_literals
-
import functools
import json
import re
+import urllib.parse
from .common import InfoExtractor
-from ..compat import compat_HTTPError
+from ..networking.exceptions import HTTPError
from ..utils import (
+ ExtractorError,
+ OnDemandPagedList,
age_restricted,
clean_html,
- ExtractorError,
int_or_none,
- OnDemandPagedList,
+ traverse_obj,
try_get,
unescapeHTML,
+ unsmuggle_url,
urlencode_postdata,
)
self._FAMILY_FILTER = ff == 'on' if ff else age_restricted(18, self.get_param('age_limit'))
self._set_dailymotion_cookie('ff', 'on' if self._FAMILY_FILTER else 'off')
+ def _get_token(self, xid):
+ cookies = self._get_dailymotion_cookies()
+ token = self._get_cookie_value(cookies, 'access_token') or self._get_cookie_value(cookies, 'client_token')
+ if token:
+ return token
+
+ data = {
+ 'client_id': 'f1a362d288c1b98099c7',
+ 'client_secret': 'eea605b96e01c796ff369935357eca920c5da4c5',
+ }
+ username, password = self._get_login_info()
+ if username:
+ data.update({
+ 'grant_type': 'password',
+ 'password': password,
+ 'username': username,
+ })
+ else:
+ data['grant_type'] = 'client_credentials'
+ try:
+ token = self._download_json(
+ 'https://graphql.api.dailymotion.com/oauth/token',
+ None, 'Downloading Access Token',
+ data=urlencode_postdata(data))['access_token']
+ except ExtractorError as e:
+ if isinstance(e.cause, HTTPError) and e.cause.status == 400:
+ raise ExtractorError(self._parse_json(
+ e.cause.response.read().decode(), xid)['error_description'], expected=True)
+ raise
+ self._set_dailymotion_cookie('access_token' if username else 'client_token', token)
+ return token
+
def _call_api(self, object_type, xid, object_fields, note, filter_extra=None):
if not self._HEADERS.get('Authorization'):
- cookies = self._get_dailymotion_cookies()
- token = self._get_cookie_value(cookies, 'access_token') or self._get_cookie_value(cookies, 'client_token')
- if not token:
- data = {
- 'client_id': 'f1a362d288c1b98099c7',
- 'client_secret': 'eea605b96e01c796ff369935357eca920c5da4c5',
- }
- username, password = self._get_login_info()
- if username:
- data.update({
- 'grant_type': 'password',
- 'password': password,
- 'username': username,
- })
- else:
- data['grant_type'] = 'client_credentials'
- try:
- token = self._download_json(
- 'https://graphql.api.dailymotion.com/oauth/token',
- None, 'Downloading Access Token',
- data=urlencode_postdata(data))['access_token']
- except ExtractorError as e:
- if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
- raise ExtractorError(self._parse_json(
- e.cause.read().decode(), xid)['error_description'], expected=True)
- raise
- self._set_dailymotion_cookie('access_token' if username else 'client_token', token)
- self._HEADERS['Authorization'] = 'Bearer ' + token
+ self._HEADERS['Authorization'] = f'Bearer {self._get_token(xid)}'
resp = self._download_json(
'https://graphql.api.dailymotion.com/', xid, note, data=json.dumps({
%s(xid: "%s"%s) {
%s
}
-}''' % (object_type, xid, ', ' + filter_extra if filter_extra else '', object_fields),
+}''' % (object_type, xid, ', ' + filter_extra if filter_extra else '', object_fields), # noqa: UP031
}).encode(), headers=self._HEADERS)
obj = resp['data'][object_type]
if not obj:
_VALID_URL = r'''(?ix)
https?://
(?:
- (?:(?:www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(?:(?:embed|swf|\#)/)?video|swf)|
+ (?:(?:www|touch|geo)\.)?dailymotion\.[a-z]{2,3}/(?:(?:(?:(?:embed|swf|\#)/)|player(?:/\w+)?\.html\?)?video|swf)|
(?:www\.)?lequipe\.fr/video
)
- /(?P<id>[^/?_]+)(?:.+?\bplaylist=(?P<playlist_id>x[0-9a-z]+))?
+ [/=](?P<id>[^/?_&]+)(?:.+?\bplaylist=(?P<playlist_id>x[0-9a-z]+))?
'''
IE_NAME = 'dailymotion'
+ _EMBED_REGEX = [r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1']
_TESTS = [{
'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news',
'md5': '074b95bdee76b9e3654137aee9c79dfe',
'id': 'x5kesuj',
'ext': 'mp4',
'title': 'Office Christmas Party Review – Jason Bateman, Olivia Munn, T.J. Miller',
- 'description': 'Office Christmas Party Review - Jason Bateman, Olivia Munn, T.J. Miller',
+ 'description': 'Office Christmas Party Review - Jason Bateman, Olivia Munn, T.J. Miller',
'duration': 187,
'timestamp': 1493651285,
'upload_date': '20170501',
'uploader': 'Deadline',
'uploader_id': 'x1xm8ri',
'age_limit': 0,
+ 'view_count': int,
+ 'like_count': int,
+ 'tags': ['hollywood', 'celeb', 'celebrity', 'movies', 'red carpet'],
+ 'thumbnail': r're:https://(?:s[12]\.)dmcdn\.net/v/K456B1aXqIx58LKWQ/x1080',
+ },
+ }, {
+ 'url': 'https://geo.dailymotion.com/player.html?video=x89eyek&mute=true',
+ 'md5': 'e2f9717c6604773f963f069ca53a07f8',
+ 'info_dict': {
+ 'id': 'x89eyek',
+ 'ext': 'mp4',
+ 'title': "En quête d'esprit du 27/03/2022",
+ 'description': 'md5:66542b9f4df2eb23f314fc097488e553',
+ 'duration': 2756,
+ 'timestamp': 1648383669,
+ 'upload_date': '20220327',
+ 'uploader': 'CNEWS',
+ 'uploader_id': 'x24vth',
+ 'age_limit': 0,
+ 'view_count': int,
+ 'like_count': int,
+ 'tags': ['en_quete_d_esprit'],
+ 'thumbnail': r're:https://(?:s[12]\.)dmcdn\.net/v/Tncwi1YNg_RUl7ueu/x1080',
},
}, {
'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
}, {
'url': 'https://www.dailymotion.com/video/x3z49k?playlist=xv4bw',
'only_matching': True,
+ }, {
+ 'url': 'https://geo.dailymotion.com/player/x86gw.html?video=k46oCapRs4iikoz9DWy',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://geo.dailymotion.com/player/xakln.html?video=x8mjju4&customConfig%5BcustomParams%5D=%2Ffr-fr%2Ftennis%2Fwimbledon-mens-singles%2Farticles-video',
+ 'only_matching': True,
}]
_GEO_BYPASS = False
_COMMON_MEDIA_FIELDS = '''description
}
xid'''
- @staticmethod
- def _extract_urls(webpage):
- urls = []
- # Look for embedded Dailymotion player
+ @classmethod
+ def _extract_embed_urls(cls, url, webpage):
# https://developer.dailymotion.com/player#player-parameters
- for mobj in re.finditer(
- r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage):
- urls.append(unescapeHTML(mobj.group('url')))
+ yield from super()._extract_embed_urls(url, webpage)
for mobj in re.finditer(
r'(?s)DM\.player\([^,]+,\s*{.*?video[\'"]?\s*:\s*["\']?(?P<id>[0-9a-zA-Z]+).+?}\s*\);', webpage):
- urls.append('https://www.dailymotion.com/embed/video/' + mobj.group('id'))
- return urls
+ yield from 'https://www.dailymotion.com/embed/video/' + mobj.group('id')
def _real_extract(self, url):
+ url, smuggled_data = unsmuggle_url(url)
video_id, playlist_id = self._match_valid_url(url).groups()
if playlist_id:
- if not self.get_param('noplaylist'):
- self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % playlist_id)
+ if self._yes_playlist(playlist_id, video_id):
return self.url_result(
'http://www.dailymotion.com/playlist/' + playlist_id,
'DailymotionPlaylist', playlist_id)
- self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
password = self.get_param('videopassword')
media = self._call_api(
%s
audienceCount
isOnAir
- }''' % (self._COMMON_MEDIA_FIELDS, self._COMMON_MEDIA_FIELDS), 'Downloading media JSON metadata',
- 'password: "%s"' % self.get_param('videopassword') if password else None)
+ }''' % (self._COMMON_MEDIA_FIELDS, self._COMMON_MEDIA_FIELDS), 'Downloading media JSON metadata', # noqa: UP031
+ 'password: "{}"'.format(self.get_param('videopassword')) if password else None)
xid = media['xid']
metadata = self._download_json(
'https://www.dailymotion.com/player/metadata/video/' + xid,
xid, 'Downloading metadata JSON',
- query={'app': 'com.dailymotion.neon'})
+ query=traverse_obj(smuggled_data, 'query') or {'app': 'com.dailymotion.neon'})
error = metadata.get('error')
if error:
allowed_countries = try_get(media, lambda x: x['geoblockedCountries']['allowed'], list)
self.raise_geo_restricted(msg=title, countries=allowed_countries)
raise ExtractorError(
- '%s said: %s' % (self.IE_NAME, title), expected=True)
+ f'{self.IE_NAME} said: {title}', expected=True)
title = metadata['title']
is_live = media.get('isOnAir')
continue
if media_type == 'application/x-mpegURL':
formats.extend(self._extract_m3u8_formats(
- media_url, video_id, 'mp4',
- 'm3u8' if is_live else 'm3u8_native',
- m3u8_id='hls', fatal=False))
+ media_url, video_id, 'mp4', live=is_live, m3u8_id='hls', fatal=False))
else:
f = {
'url': media_url,
f['url'] = f['url'].split('#')[0]
if not f.get('fps') and f['format_id'].endswith('@60'):
f['fps'] = 60
- self._sort_formats(formats)
subtitles = {}
subtitles_data = try_get(metadata, lambda x: x['subtitles']['data'], dict) or {}
}
}
}''' % ('false' if self._FAMILY_FILTER else 'true', self._PAGE_SIZE, page),
- 'Downloading page %d' % page)['videos']
+ f'Downloading page {page}')['videos']
for edge in videos['edges']:
node = edge['node']
yield self.url_result(
}]
_OBJECT_TYPE = 'collection'
+ @classmethod
+ def _extract_embed_urls(cls, url, webpage):
+ # Look for embedded Dailymotion playlist player (#3822)
+ for mobj in re.finditer(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1',
+ webpage):
+ for p in re.findall(r'list\[\]=/playlist/([^/]+)/', unescapeHTML(mobj.group('url'))):
+ yield f'//dailymotion.com/playlist/{p}'
+
+
+class DailymotionSearchIE(DailymotionPlaylistBaseIE):
+ IE_NAME = 'dailymotion:search'
+ _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/search/(?P<id>[^/?#]+)/videos'
+ _PAGE_SIZE = 20
+ _TESTS = [{
+ 'url': 'http://www.dailymotion.com/search/king of turtles/videos',
+ 'info_dict': {
+ 'id': 'king of turtles',
+ 'title': 'king of turtles',
+ },
+ 'playlist_mincount': 90,
+ }]
+ _SEARCH_QUERY = 'query SEARCH_QUERY( $query: String! $page: Int $limit: Int ) { search { videos( query: $query first: $limit page: $page ) { edges { node { xid } } } } } '
+
+ def _call_search_api(self, term, page, note):
+ if not self._HEADERS.get('Authorization'):
+ self._HEADERS['Authorization'] = f'Bearer {self._get_token(term)}'
+ resp = self._download_json(
+ 'https://graphql.api.dailymotion.com/', None, note, data=json.dumps({
+ 'operationName': 'SEARCH_QUERY',
+ 'query': self._SEARCH_QUERY,
+ 'variables': {
+ 'limit': 20,
+ 'page': page,
+ 'query': term,
+ },
+ }).encode(), headers=self._HEADERS)
+ obj = traverse_obj(resp, ('data', 'search', {dict}))
+ if not obj:
+ raise ExtractorError(
+ traverse_obj(resp, ('errors', 0, 'message', {str})) or 'Could not fetch search data')
+
+ return obj
+
+ def _fetch_page(self, term, page):
+ page += 1
+ response = self._call_search_api(term, page, f'Searching "{term}" page {page}')
+ for xid in traverse_obj(response, ('videos', 'edges', ..., 'node', 'xid')):
+ yield self.url_result(f'https://www.dailymotion.com/video/{xid}', DailymotionIE, xid)
+
+ def _real_extract(self, url):
+ term = urllib.parse.unquote_plus(self._match_id(url))
+ return self.playlist_result(
+ OnDemandPagedList(functools.partial(self._fetch_page, term), self._PAGE_SIZE), term, term)
+
class DailymotionUserIE(DailymotionPlaylistBaseIE):
IE_NAME = 'dailymotion:user'
- _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist)/)(?:(?:old/)?user/)?(?P<id>[^/]+)'
+ _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist|search)/)(?:(?:old/)?user/)?(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.dailymotion.com/user/nqtv',
'info_dict': {