X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/7df4343e553a9942a290e5e1dffe931261ab844e..dbb40c34b0cf975d3c249affe5fc8865fd7a3d5d:/youtube_dl/extractor/lifenews.py diff --git a/youtube_dl/extractor/lifenews.py b/youtube_dl/extractor/lifenews.py index 42cb6e3..42e263b 100644 --- a/youtube_dl/extractor/lifenews.py +++ b/youtube_dl/extractor/lifenews.py @@ -1,164 +1,234 @@ -# encoding: utf-8 +# coding: utf-8 from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_urlparse +from ..compat import ( + compat_str, + compat_urlparse, +) from ..utils import ( determine_ext, - int_or_none, - unified_strdate, ExtractorError, + int_or_none, + parse_iso8601, + remove_end, ) class LifeNewsIE(InfoExtractor): - IE_NAME = 'lifenews' - IE_DESC = 'LIFE | NEWS' - _VALID_URL = r'http://lifenews\.ru/(?:mobile/)?(?P<section>news|video)/(?P<id>\d+)' + IE_NAME = 'life' + IE_DESC = 'Life.ru' + _VALID_URL = r'https?://life\.ru/t/[^/]+/(?P<id>\d+)' _TESTS = [{ - 'url': 'http://lifenews.ru/news/126342', - 'md5': 'e1b50a5c5fb98a6a544250f2e0db570a', + # single video embedded via video/source + 'url': 'https://life.ru/t/новоÑÑи/98736', + 'md5': '77c95eaefaca216e32a76a343ad89d23', 'info_dict': { - 'id': '126342', + 'id': '98736', 'ext': 'mp4', - 'title': 'ÐÐÐ ÑазÑÑÐºÐ¸Ð²Ð°ÐµÑ Ð¼ÑжÑин, оÑÑавивÑÐ¸Ñ Ð² IKEA ÑÑÐ¼ÐºÑ Ñ Ð°Ð²ÑомаÑом', - 'description': 'ÐамеÑÑ Ð½Ð°Ð±Ð»ÑÐ´ÐµÐ½Ð¸Ñ Ð³Ð¸Ð¿ÐµÑмаÑкеÑа заÑикÑиÑовали ÑÑÐ¾Ð¸Ñ Ð¼ÑжÑин, ÑпÑÑÑавÑÐ¸Ñ Ð¾ÑÑжейнÑй аÑÑенал в камеÑе Ñ ÑанениÑ.', - 'thumbnail': 're:http://.*\.jpg', - 'upload_date': '20140130', + 'title': 'ÐÑжÑина наÑел дома аÑÑ Ð¸Ð² обоÑонного завода', + 'description': 'md5:3b06b1b39b5e2bea548e403d99b8bf26', + 'timestamp': 1344154740, + 'upload_date': '20120805', + 'view_count': int, } }, { - # video in <iframe> - 'url': 'http://lifenews.ru/news/152125', + # single video embedded via iframe + 'url': 'https://life.ru/t/новоÑÑи/152125', 'md5': '77d19a6f0886cd76bdbf44b4d971a273', 'info_dict': { 'id': '152125', 'ext': 'mp4', 'title': 'РСеÑи поÑвилоÑÑ Ð²Ð¸Ð´ÐµÐ¾ Ð·Ð°Ñ Ð²Ð°Ñа «ÐÑавÑм ÑекÑоÑом» ÐºÐ¾Ð»Ñ Ð¾Ð·Ð½ÑÑ Ð¿Ð¾Ð»ÐµÐ¹ ', 'description': 'ÐиÑели двÑÑ Ð¿Ð¾Ñелков ÐнепÑопеÑÑовÑкой облаÑÑи не пÑоÑÑили Ñадикалам ÑгÑÐ¾Ð·Ñ Ð»Ð¸ÑÐµÐ½Ð¸Ñ Ð¿Ð»Ð¾Ð´Ð¾ÑоднÑÑ Ð·ÐµÐ¼ÐµÐ»Ñ Ð¸ поÑли в лобовÑÑ. ', + 'timestamp': 1427961840, 'upload_date': '20150402', - 'uploader': 'embed.life.ru', + 'view_count': int, } }, { - 'url': 'http://lifenews.ru/news/153461', - 'md5': '9b6ef8bc0ffa25aebc8bdb40d89ab795', + # two videos embedded via iframe + 'url': 'https://life.ru/t/новоÑÑи/153461', 'info_dict': { 'id': '153461', - 'ext': 'mp4', 'title': 'Ð ÐоÑкве ÑпаÑли поÑеÑÑвÑегоÑÑ Ð¼ÐµÐ´Ð²ÐµÐ¶Ð¾Ð½ÐºÐ°, коÑоÑÑй ÑпÑÑÑалÑÑ Ð½Ð° деÑеве', 'description': 'ÐаленÑкий Ñ Ð¸Ñник не Ñмог найÑи доÑÐ¾Ð³Ñ Ð´Ð¾Ð¼Ð¾Ð¹ и обÑел вÑеменное ÑбежиÑе на Ñополе недалеко Ð¾Ñ Ð¶Ð¸Ð»Ð¾Ð³Ð¾ маÑÑива, пока его не наÑла ÑоÑедÑÐºÐ°Ñ Ñобака.', - 'upload_date': '20150505', - 'uploader': 'embed.life.ru', - } + 'timestamp': 1430825520, + 'view_count': int, + }, + 'playlist': [{ + 'md5': '9b6ef8bc0ffa25aebc8bdb40d89ab795', + 'info_dict': { + 'id': '153461-video1', + 'ext': 'mp4', + 'title': 'Ð ÐоÑкве ÑпаÑли поÑеÑÑвÑегоÑÑ Ð¼ÐµÐ´Ð²ÐµÐ¶Ð¾Ð½ÐºÐ°, коÑоÑÑй ÑпÑÑÑалÑÑ Ð½Ð° деÑеве (Ðидео 1)', + 'description': 'ÐаленÑкий Ñ Ð¸Ñник не Ñмог найÑи доÑÐ¾Ð³Ñ Ð´Ð¾Ð¼Ð¾Ð¹ и обÑел вÑеменное ÑбежиÑе на Ñополе недалеко Ð¾Ñ Ð¶Ð¸Ð»Ð¾Ð³Ð¾ маÑÑива, пока его не наÑла ÑоÑедÑÐºÐ°Ñ Ñобака.', + 'timestamp': 1430825520, + 'upload_date': '20150505', + }, + }, { + 'md5': 'ebb3bf3b1ce40e878d0d628e93eb0322', + 'info_dict': { + 'id': '153461-video2', + 'ext': 'mp4', + 'title': 'Ð ÐоÑкве ÑпаÑли поÑеÑÑвÑегоÑÑ Ð¼ÐµÐ´Ð²ÐµÐ¶Ð¾Ð½ÐºÐ°, коÑоÑÑй ÑпÑÑÑалÑÑ Ð½Ð° деÑеве (Ðидео 2)', + 'description': 'ÐаленÑкий Ñ Ð¸Ñник не Ñмог найÑи доÑÐ¾Ð³Ñ Ð´Ð¾Ð¼Ð¾Ð¹ и обÑел вÑеменное ÑбежиÑе на Ñополе недалеко Ð¾Ñ Ð¶Ð¸Ð»Ð¾Ð³Ð¾ маÑÑива, пока его не наÑла ÑоÑедÑÐºÐ°Ñ Ñобака.', + 'timestamp': 1430825520, + 'upload_date': '20150505', + }, + }], + }, { + 'url': 'https://life.ru/t/новоÑÑи/213035', + 'only_matching': True, + }, { + 'url': 'https://life.ru/t/%D0%BD%D0%BE%D0%B2%D0%BE%D1%81%D1%82%D0%B8/153461', + 'only_matching': True, }, { - 'url': 'http://lifenews.ru/video/13035', + 'url': 'https://life.ru/t/новоÑÑи/411489/manuel_vals_nazval_frantsiiu_tsieliu_nomier_odin_dlia_ighil', 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - section = mobj.group('section') - - webpage = self._download_webpage( - 'http://lifenews.ru/%s/%s' % (section, video_id), - video_id, 'Downloading page') - - videos = re.findall(r'<video.*?poster="(?P<poster>[^"]+)".*?src="(?P<video>[^"]+)".*?></video>', webpage) - iframe_link = self._html_search_regex( - '<iframe[^>]+src=["\']([^"\']+)["\']', webpage, 'iframe link', default=None) - if not videos and not iframe_link: + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + video_urls = re.findall( + r'<video[^>]+><source[^>]+src=["\'](.+?)["\']', webpage) + + iframe_links = re.findall( + r'<iframe[^>]+src=["\']((?:https?:)?//embed\.life\.ru/(?:embed|video)/.+?)["\']', + webpage) + + if not video_urls and not iframe_links: raise ExtractorError('No media links available for %s' % video_id) - title = self._og_search_title(webpage) - TITLE_SUFFIX = ' - ÐеÑвÑй по ÑÑоÑнÑм новоÑÑÑм â LIFE | NEWS' - if title.endswith(TITLE_SUFFIX): - title = title[:-len(TITLE_SUFFIX)] + title = remove_end( + self._og_search_title(webpage), + ' - Life.ru') description = self._og_search_description(webpage) view_count = self._html_search_regex( - r'<div class=\'views\'>\s*(\d+)\s*</div>', webpage, 'view count', fatal=False) - comment_count = self._html_search_regex( - r'<div class=\'comments\'>\s*<span class=\'counter\'>\s*(\d+)\s*</span>', webpage, 'comment count', fatal=False) + r'<div[^>]+class=(["\']).*?\bhits-count\b.*?\1[^>]*>\s*(?P<value>\d+)\s*</div>', + webpage, 'view count', fatal=False, group='value') - upload_date = self._html_search_regex( - r'<time datetime=\'([^\']+)\'>', webpage, 'upload date', fatal=False) - if upload_date is not None: - upload_date = unified_strdate(upload_date) + timestamp = parse_iso8601(self._search_regex( + r'<time[^>]+datetime=(["\'])(?P<value>.+?)\1', + webpage, 'upload date', fatal=False, group='value')) common_info = { 'description': description, 'view_count': int_or_none(view_count), - 'comment_count': int_or_none(comment_count), - 'upload_date': upload_date, + 'timestamp': timestamp, } - def make_entry(video_id, media, video_number=None): + def make_entry(video_id, video_url, index=None): cur_info = dict(common_info) cur_info.update({ - 'id': video_id, - 'url': media[1], - 'thumbnail': media[0], - 'title': title if video_number is None else '%s-video%s' % (title, video_number), + 'id': video_id if not index else '%s-video%s' % (video_id, index), + 'url': video_url, + 'title': title if not index else '%s (Ðидео %s)' % (title, index), }) return cur_info - if iframe_link: - iframe_link = self._proto_relative_url(iframe_link, 'http:') - cur_info = dict(common_info) - cur_info.update({ - '_type': 'url_transparent', - 'id': video_id, - 'title': title, - 'url': iframe_link, - }) + def make_video_entry(video_id, video_url, index=None): + video_url = compat_urlparse.urljoin(url, video_url) + return make_entry(video_id, video_url, index) + + def make_iframe_entry(video_id, video_url, index=None): + video_url = self._proto_relative_url(video_url, 'http:') + cur_info = make_entry(video_id, video_url, index) + cur_info['_type'] = 'url_transparent' return cur_info - if len(videos) == 1: - return make_entry(video_id, videos[0]) - else: - return [make_entry(video_id, media, video_number + 1) for video_number, media in enumerate(videos)] + if len(video_urls) == 1 and not iframe_links: + return make_video_entry(video_id, video_urls[0]) + + if len(iframe_links) == 1 and not video_urls: + return make_iframe_entry(video_id, iframe_links[0]) + + entries = [] + + if video_urls: + for num, video_url in enumerate(video_urls, 1): + entries.append(make_video_entry(video_id, video_url, num)) + + if iframe_links: + for num, iframe_link in enumerate(iframe_links, len(video_urls) + 1): + entries.append(make_iframe_entry(video_id, iframe_link, num)) + + playlist = common_info.copy() + playlist.update(self.playlist_result(entries, video_id, title, description)) + return playlist class LifeEmbedIE(InfoExtractor): IE_NAME = 'life:embed' - _VALID_URL = r'http://embed\.life\.ru/embed/(?P<id>[\da-f]{32})' + _VALID_URL = r'https?://embed\.life\.ru/(?:embed|video)/(?P<id>[\da-f]{32})' - _TEST = { + _TESTS = [{ 'url': 'http://embed.life.ru/embed/e50c2dec2867350528e2574c899b8291', 'md5': 'b889715c9e49cb1981281d0e5458fbbe', 'info_dict': { 'id': 'e50c2dec2867350528e2574c899b8291', 'ext': 'mp4', 'title': 'e50c2dec2867350528e2574c899b8291', - 'thumbnail': 're:http://.*\.jpg', + 'thumbnail': r're:http://.*\.jpg', } - } + }, { + # with 1080p + 'url': 'https://embed.life.ru/video/e50c2dec2867350528e2574c899b8291', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + thumbnail = None formats = [] - for video_url in re.findall(r'"file"\s*:\s*"([^"]+)', webpage): - video_url = compat_urlparse.urljoin(url, video_url) - ext = determine_ext(video_url) - if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - video_url, video_id, 'mp4', m3u8_id='m3u8')) - else: - formats.append({ - 'url': video_url, - 'format_id': ext, - 'preference': 1, - }) + + def extract_m3u8(manifest_url): + formats.extend(self._extract_m3u8_formats( + manifest_url, video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='m3u8')) + + def extract_original(original_url): + formats.append({ + 'url': original_url, + 'format_id': determine_ext(original_url, None), + 'preference': 1, + }) + + playlist = self._parse_json( + self._search_regex( + r'options\s*=\s*({.+?});', webpage, 'options', default='{}'), + video_id).get('playlist', {}) + if playlist: + master = playlist.get('master') + if isinstance(master, compat_str) and determine_ext(master) == 'm3u8': + extract_m3u8(compat_urlparse.urljoin(url, master)) + original = playlist.get('original') + if isinstance(original, compat_str): + extract_original(original) + thumbnail = playlist.get('image') + + # Old rendition fallback + if not formats: + for video_url in re.findall(r'"file"\s*:\s*"([^"]+)', webpage): + video_url = compat_urlparse.urljoin(url, video_url) + if determine_ext(video_url) == 'm3u8': + extract_m3u8(video_url) + else: + extract_original(video_url) + self._sort_formats(formats) - thumbnail = self._search_regex( + thumbnail = thumbnail or self._search_regex( r'"image"\s*:\s*"([^"]+)', webpage, 'thumbnail', default=None) return {