X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ffirsttv.py;h=88bca100763337011a444369543a1479296e097e;hb=1058f56e96316e778ed74ad008949c634a582e84;hp=3410daa98860f1e923cfc4e8c3db20436bbb9a50;hpb=5f6a1245ffa9276c1af59b0835afeef67e2fb5b1;p=youtube-dl diff --git a/youtube_dl/extractor/firsttv.py b/youtube_dl/extractor/firsttv.py index 3410daa98..88bca1007 100644 --- a/youtube_dl/extractor/firsttv.py +++ b/youtube_dl/extractor/firsttv.py @@ -1,60 +1,134 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import int_or_none +from ..compat import compat_xpath +from ..utils import ( + int_or_none, + qualities, + unified_strdate, + xpath_attr, + xpath_element, + xpath_text, + xpath_with_ns, +) class FirstTVIE(InfoExtractor): - IE_NAME = 'firsttv' - IE_DESC = 'Видеоархив - Первый канал' - _VALID_URL = r'http://(?:www\.)?1tv\.ru/videoarchive/(?P\d+)' + IE_NAME = '1tv' + IE_DESC = 'Первый канал' + _VALID_URL = r'https?://(?:www\.)?1tv\.ru/(?:[^/]+/)+p?(?P\d+)' - _TEST = { - 'url': 'http://www.1tv.ru/videoarchive/73390', - 'md5': '3de6390cf0cca4a5eae1d1d83895e5ad', + _TESTS = [{ + # single format via video_materials.json API + 'url': 'http://www.1tv.ru/prj/inprivate/vypusk/35930', + 'md5': '82a2777648acae812d58b3f5bd42882b', + 'info_dict': { + 'id': '35930', + 'ext': 'mp4', + 'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015', + 'description': 'md5:357933adeede13b202c7c21f91b871b2', + 'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$', + 'upload_date': '20150212', + 'duration': 2694, + }, + }, { + # multiple formats via video_materials.json API + 'url': 'http://www.1tv.ru/video_archive/projects/dobroeutro/p113641', + 'info_dict': { + 'id': '113641', + 'ext': 'mp4', + 'title': 'Весенняя аллергия. Доброе утро. Фрагмент выпуска от 07.04.2016', + 'description': 'md5:8dcebb3dded0ff20fade39087fd1fee2', + 'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$', + 'upload_date': '20160407', + 'duration': 179, + 'formats': 'mincount:3', + }, + 'params': { + 'skip_download': True, + }, + }, { + # single format only available via ONE_ONLINE_VIDEOS.archive_single_xml API + 'url': 'http://www.1tv.ru/video_archive/series/f7552/p47038', + 'md5': '519d306c5b5669761fd8906c39dbee23', 'info_dict': { - 'id': '73390', + 'id': '47038', 'ext': 'mp4', - 'title': 'Олимпийские канатные дороги', - 'description': 'md5:cc730d2bf4215463e37fff6a1e277b13', - 'thumbnail': 'http://img1.1tv.ru/imgsize640x360/PR20140210114657.JPG', - 'duration': 149, + 'title': '"Побег". Второй сезон. 3 серия', + 'description': 'md5:3abf8f6b9bce88201c33e9a3d794a00b', + 'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$', + 'upload_date': '20120516', + 'duration': 3080, }, - 'skip': 'Only works from Russia', - } + }, { + 'url': 'http://www.1tv.ru/videoarchive/9967', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) + + # Videos with multiple formats only available via this API + video = self._download_json( + 'http://www.1tv.ru/video_materials.json?legacy_id=%s' % video_id, + video_id, fatal=False) + + description, thumbnail, upload_date, duration = [None] * 4 - webpage = self._download_webpage(url, video_id, 'Downloading page') + if video: + item = video[0] + title = item['title'] + quality = qualities(('ld', 'sd', 'hd', )) + formats = [{ + 'url': f['src'], + 'format_id': f.get('name'), + 'quality': quality(f.get('name')), + } for f in item['mbr'] if f.get('src')] + thumbnail = item.get('poster') + else: + # Some videos are not available via video_materials.json + video = self._download_xml( + 'http://www.1tv.ru/owa/win/ONE_ONLINE_VIDEOS.archive_single_xml?pid=%s' % video_id, + video_id) - video_url = self._html_search_regex( - r'''(?s)jwplayer\('flashvideoportal_1'\)\.setup\({.*?'file': '([^']+)'.*?}\);''', webpage, 'video URL') + NS_MAP = { + 'media': 'http://search.yahoo.com/mrss/', + } - title = self._html_search_regex( - r'
\s*

([^<]*)', webpage, 'title') - description = self._html_search_regex( - r'
\s*
 
\s*

([^<]*)

', webpage, 'description', fatal=False) + item = xpath_element(video, './channel/item', fatal=True) + title = xpath_text(item, './title', fatal=True) + formats = [{ + 'url': content.attrib['url'], + } for content in item.findall( + compat_xpath(xpath_with_ns('./media:content', NS_MAP))) if content.attrib.get('url')] + thumbnail = xpath_attr( + item, xpath_with_ns('./media:thumbnail', NS_MAP), 'url') - thumbnail = self._og_search_thumbnail(webpage) - duration = self._og_search_property('video:duration', webpage, 'video duration', fatal=False) + self._sort_formats(formats) - like_count = self._html_search_regex(r'title="Понравилось".*?/> \[(\d+)\]', - webpage, 'like count', fatal=False) - dislike_count = self._html_search_regex(r'title="Не понравилось".*?/> \[(\d+)\]', - webpage, 'dislike count', fatal=False) + webpage = self._download_webpage(url, video_id, 'Downloading page', fatal=False) + if webpage: + title = self._html_search_regex( + (r'
\s*

([^<]*)', + r"'title'\s*:\s*'([^']+)'"), + webpage, 'title', default=None) or title + description = self._html_search_regex( + r'
\s*
 
\s*

([^<]*)

', + webpage, 'description', default=None) or self._html_search_meta( + 'description', webpage, 'description') + thumbnail = thumbnail or self._og_search_thumbnail(webpage) + duration = int_or_none(self._html_search_meta( + 'video:duration', webpage, 'video duration', fatal=False)) + upload_date = unified_strdate(self._html_search_meta( + 'ya:ovs:upload_date', webpage, 'upload date', fatal=False)) return { 'id': video_id, - 'url': video_url, 'thumbnail': thumbnail, 'title': title, 'description': description, + 'upload_date': upload_date, 'duration': int_or_none(duration), - 'like_count': int_or_none(like_count), - 'dislike_count': int_or_none(dislike_count), + 'formats': formats }