You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
youtube-dl/youtube_dl/extractor/dailymotion.py

111 lines
4.2 KiB
Python

import re
import json
import itertools
from .common import InfoExtractor
from ..utils import (
compat_urllib_request,
get_element_by_attribute,
get_element_by_id,
ExtractorError,
)
class DailymotionIE(InfoExtractor):
"""Information Extractor for Dailymotion"""
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/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"Alex and Van .",
u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
}
}
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'
# Retrieve video webpage to extract further information
request = compat_urllib_request.Request(url)
request.add_header('Cookie', 'family_filter=off')
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')
video_upload_date = None
mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
if mobj is not None:
video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
embed_page = self._download_webpage(embed_url, video_id,
u'Downloading embed page')
info = self._search_regex(r'var info = ({.*?}),', embed_page, 'video info')
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]
return [{
'id': video_id,
'url': video_url,
'uploader': video_uploader,
'upload_date': video_upload_date,
'title': self._og_search_title(webpage),
'ext': video_extension,
'thumbnail': info['thumbnail_url']
}]
class DailymotionPlaylistIE(InfoExtractor):
_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')
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)
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))
if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
break
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,
}