X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/3ae74f711947d73bf6627bf312edeec41cec85c3..d2e1a98478a93d5d191b83a9aa545df270ebf323:/youtube_dl/extractor/dailymotion.py diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 1ea449c..42b20a4 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -1,51 +1,110 @@ +# coding: utf-8 +from __future__ import unicode_literals + import re import json import itertools from .common import InfoExtractor -from ..utils import ( - compat_urllib_request, - get_element_by_attribute, - get_element_by_id, +from ..compat import ( + compat_str, + compat_urllib_request, +) +from ..utils import ( ExtractorError, + int_or_none, + orderedSet, + str_to_int, + unescapeHTML, ) -class DailymotionIE(InfoExtractor): + +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): """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"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[^/?_]+)' + 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)[^<]+?]+?>([^<]+?)', - # Looking for official user - r'<(?:span|a) .*?rel="author".*?>([^<]+?)[\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'
([0-9]{2})-([0-9]{2})-([0-9]{4})
', webpage) @@ -54,57 +113,139 @@ class DailymotionIE(InfoExtractor): 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') + 'Downloading embed page') + info = self._search_regex(r'var info = ({.*?}),$', embed_page, + 'video info', flags=re.MULTILINE) info = json.loads(info) + 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 = self.extract_subtitles(video_id, webpage) + + 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)]*>(.*?)', 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_subtitles(self, video_id, webpage): + try: + 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'], [{'url': l['url'], 'ext': 'srt'}]) for l in info['list']) + return sub_lang_list + self._downloader.report_warning('video doesn\'t have subtitles') + return {} + + +class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): + IE_NAME = 'dailymotion:playlist' + _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P.+?)/' + _MORE_PAGES_INDICATOR = r'(?s)
.*?.+?)/' - _MORE_PAGES_INDICATOR = r'' + 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') - 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_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), + } - 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 +class DailymotionUserIE(DailymotionPlaylistIE): + IE_NAME = 'dailymotion:user' + _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P[^/]+)' + _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, + }] - 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, - } + 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'' % re.escape(user), + webpage, 'user')) + + return { + '_type': 'playlist', + 'id': user, + 'title': full_user, + 'entries': self._extract_entries(user), + }