X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ffirsttv.py;h=c6fb67057b79132d3f40f75587642353c717e933;hb=ec85ded83cbfa652ba94cb080aab52d8b270212a;hp=6e015ca163d19d08b209bb4c679896304c6d794b;hpb=9347fddbfc81114f85fecc72e8452813ef130fdb;p=youtube-dl diff --git a/youtube_dl/extractor/firsttv.py b/youtube_dl/extractor/firsttv.py index 6e015ca16..c6fb67057 100644 --- a/youtube_dl/extractor/firsttv.py +++ b/youtube_dl/extractor/firsttv.py @@ -1,81 +1,128 @@ -# encoding: utf-8 +# coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import int_or_none +from ..compat import ( + compat_str, + compat_urlparse, +) +from ..utils import ( + int_or_none, + qualities, + unified_strdate, +) class FirstTVIE(InfoExtractor): IE_NAME = '1tv' IE_DESC = 'Первый канал' - _VALID_URL = r'http://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P.+)' + _VALID_URL = r'https?://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P[^/?#]+)' _TESTS = [{ - 'url': 'http://www.1tv.ru/videoarchive/73390', - 'md5': '777f525feeec4806130f4f764bc18a4f', + # single format + 'url': 'http://www.1tv.ru/shows/naedine-so-vsemi/vypuski/gost-lyudmila-senchina-naedine-so-vsemi-vypusk-ot-12-02-2015', + 'md5': 'a1b6b60d530ebcf8daacf4565762bbaf', 'info_dict': { - 'id': '73390', + 'id': '40049', 'ext': 'mp4', - 'title': 'Олимпийские канатные дороги', - 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', - 'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$', - 'duration': 149, - 'like_count': int, - 'dislike_count': int, + 'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015', + 'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$', + 'upload_date': '20150212', + 'duration': 2694, }, - 'skip': 'Only works from Russia', }, { - 'url': 'http://www.1tv.ru/prj/inprivate/vypusk/35930', - 'md5': 'a1b6b60d530ebcf8daacf4565762bbaf', + # multiple formats + 'url': 'http://www.1tv.ru/shows/dobroe-utro/pro-zdorove/vesennyaya-allergiya-dobroe-utro-fragment-vypuska-ot-07042016', 'info_dict': { - 'id': '35930', + 'id': '364746', 'ext': 'mp4', - 'title': 'Наедине со всеми. Людмила Сенчина', - 'description': 'md5:89553aed1d641416001fe8d450f06cb9', - 'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$', - 'duration': 2694, + 'title': 'Весенняя аллергия. Доброе утро. Фрагмент выпуска от 07.04.2016', + 'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$', + 'upload_date': '20160407', + 'duration': 179, + 'formats': 'mincount:3', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'http://www.1tv.ru/news/issue/2016-12-01/14:00', + 'info_dict': { + 'id': '14:00', + 'title': 'Выпуск новостей в 14:00 1 декабря 2016 года. Новости. Первый канал', + 'description': 'md5:2e921b948f8c1ff93901da78ebdb1dfd', }, - 'skip': 'Only works from Russia', + 'playlist_count': 13, + }, { + 'url': 'http://www.1tv.ru/shows/tochvtoch-supersezon/vystupleniya/evgeniy-dyatlov-vladimir-vysockiy-koni-priveredlivye-toch-v-toch-supersezon-fragment-vypuska-ot-06-11-2016', + 'only_matching': True, }] def _real_extract(self, url): - video_id = self._match_id(url) + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + playlist_url = compat_urlparse.urljoin(url, self._search_regex( + r'data-playlist-url=(["\'])(?P(?:(?!\1).)+)\1', + webpage, 'playlist url', group='url')) + + parsed_url = compat_urlparse.urlparse(playlist_url) + qs = compat_urlparse.parse_qs(parsed_url.query) + item_ids = qs.get('videos_ids[]') or qs.get('news_ids[]') + + items = self._download_json(playlist_url, display_id) + + if item_ids: + items = [ + item for item in items + if item.get('uid') and compat_str(item['uid']) in item_ids] + else: + items = [items[0]] - webpage = self._download_webpage(url, video_id, 'Downloading page') + entries = [] + QUALITIES = ('ld', 'sd', 'hd', ) - video_url = self._html_search_regex( - r'''(?s)(?:jwplayer\('flashvideoportal_1'\)\.setup\({|var\s+playlistObj\s*=).*?'file'\s*:\s*'([^']+)'.*?}\);''', - webpage, 'video URL') + for item in items: + title = item['title'] + quality = qualities(QUALITIES) + formats = [] + for f in item.get('mbr', []): + src = f.get('src') + if not src or not isinstance(src, compat_str): + continue + tbr = int_or_none(self._search_regex( + r'_(\d{3,})\.mp4', src, 'tbr', default=None)) + formats.append({ + 'url': src, + 'format_id': f.get('name'), + 'tbr': tbr, + 'quality': quality(f.get('name')), + }) + self._sort_formats(formats) + + thumbnail = item.get('poster') or self._og_search_thumbnail(webpage) + duration = int_or_none(item.get('duration') or 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', default=None)) + + entries.append({ + 'id': compat_str(item.get('id') or item['uid']), + 'thumbnail': thumbnail, + 'title': title, + 'upload_date': upload_date, + 'duration': int_or_none(duration), + 'formats': formats + }) title = self._html_search_regex( - [r'
\s*

([^<]*)', - r"'title'\s*:\s*'([^']+)'"], webpage, 'title') + (r'
\s*

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

([^<]*)

', webpage, 'description', default=None) or self._html_search_meta( - 'description', webpage, 'description') - - thumbnail = self._og_search_thumbnail(webpage) - duration = self._og_search_property( - 'video:duration', webpage, - 'video duration', fatal=False) - - like_count = self._html_search_regex( - r'title="Понравилось".*?/> \[(\d+)\]', - webpage, 'like count', default=None) - dislike_count = self._html_search_regex( - r'title="Не понравилось".*?/> \[(\d+)\]', - webpage, 'dislike count', default=None) + 'description', webpage, 'description', default=None) - return { - 'id': video_id, - 'url': video_url, - 'thumbnail': thumbnail, - 'title': title, - 'description': description, - 'duration': int_or_none(duration), - 'like_count': int_or_none(like_count), - 'dislike_count': int_or_none(dislike_count), - } + return self.playlist_result(entries, display_id, title, description)