X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/63a6927374492ef47c8fd6de67d0760ace4dd0ed..d018d3313032e12968a6add6800e51d412e2f602:/youtube_dl/extractor/ivi.py?ds=sidebyside diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index 4bdf55f..029878d 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -1,48 +1,51 @@ # encoding: utf-8 +from __future__ import unicode_literals import re import json from .common import InfoExtractor from ..utils import ( - compat_urllib_request, ExtractorError, + sanitized_Request, ) class IviIE(InfoExtractor): - IE_DESC = u'ivi.ru' - IE_NAME = u'ivi' - _VALID_URL = r'^https?://(?:www\.)?ivi\.ru/watch(?:/(?P[^/]+))?/(?P\d+)' + IE_DESC = 'ivi.ru' + IE_NAME = 'ivi' + _VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P\d+)' _TESTS = [ # Single movie { - u'url': u'http://www.ivi.ru/watch/53141', - u'file': u'53141.mp4', - u'md5': u'6ff5be2254e796ed346251d117196cf4', - u'info_dict': { - u'title': u'Иван Васильевич меняет профессию', - u'description': u'md5:14d8eda24e9d93d29b5857012c6d6346', - u'duration': 5498, - u'thumbnail': u'http://thumbs.ivi.ru/f20.vcp.digitalaccess.ru/contents/d/1/c3c885163a082c29bceeb7b5a267a6.jpg', + 'url': 'http://www.ivi.ru/watch/53141', + 'md5': '6ff5be2254e796ed346251d117196cf4', + 'info_dict': { + 'id': '53141', + 'ext': 'mp4', + 'title': 'Иван Васильевич меняет профессию', + 'description': 'md5:b924063ea1677c8fe343d8a72ac2195f', + 'duration': 5498, + 'thumbnail': 'http://thumbs.ivi.ru/f20.vcp.digitalaccess.ru/contents/d/1/c3c885163a082c29bceeb7b5a267a6.jpg', }, - u'skip': u'Only works from Russia', + 'skip': 'Only works from Russia', }, # Serial's serie { - u'url': u'http://www.ivi.ru/watch/dezhurnyi_angel/74791', - u'file': u'74791.mp4', - u'md5': u'3e6cc9a848c1d2ebcc6476444967baa9', - u'info_dict': { - u'title': u'Дежурный ангел - 1 серия', - u'duration': 2490, - u'thumbnail': u'http://thumbs.ivi.ru/f7.vcp.digitalaccess.ru/contents/8/e/bc2f6c2b6e5d291152fdd32c059141.jpg', + 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/9549', + 'md5': '221f56b35e3ed815fde2df71032f4b3e', + 'info_dict': { + 'id': '9549', + 'ext': 'mp4', + 'title': 'Двое из ларца - Серия 1', + 'duration': 2655, + 'thumbnail': 'http://thumbs.ivi.ru/f15.vcp.digitalaccess.ru/contents/8/4/0068dc0677041f3336b7c2baad8fc0.jpg', }, - u'skip': u'Only works from Russia', - } + 'skip': 'Only works from Russia', + } ] - + # Sorted by quality _known_formats = ['MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi', 'MP4-SHQ'] @@ -54,56 +57,63 @@ class IviIE(InfoExtractor): return m.group('description') if m is not None else None def _extract_comment_count(self, html): - m = re.search(u'(?s)\s*Комментарии:\s*(?P\d+)\s*', html) + m = re.search('(?s)\s*Комментарии:\s*(?P\d+)\s*', html) return int(m.group('commentcount')) if m is not None else 0 def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') + video_id = self._match_id(url) api_url = 'http://api.digitalaccess.ru/api/json/' - data = {u'method': u'da.content.get', - u'params': [video_id, {u'site': u's183', - u'referrer': u'http://www.ivi.ru/watch/%s' % video_id, - u'contentid': video_id - } - ] + data = { + 'method': 'da.content.get', + 'params': [ + video_id, { + 'site': 's183', + 'referrer': 'http://www.ivi.ru/watch/%s' % video_id, + 'contentid': video_id } + ] + } - request = compat_urllib_request.Request(api_url, json.dumps(data)) + request = sanitized_Request(api_url, json.dumps(data)) - video_json_page = self._download_webpage(request, video_id, u'Downloading video JSON') + video_json_page = self._download_webpage( + request, video_id, 'Downloading video JSON') video_json = json.loads(video_json_page) - if u'error' in video_json: - error = video_json[u'error'] - if error[u'origin'] == u'NoRedisValidData': - raise ExtractorError(u'Video %s does not exist' % video_id, expected=True) - raise ExtractorError(u'Unable to download video %s: %s' % (video_id, error[u'message']), expected=True) + if 'error' in video_json: + error = video_json['error'] + if error['origin'] == 'NoRedisValidData': + raise ExtractorError('Video %s does not exist' % video_id, expected=True) + raise ExtractorError( + 'Unable to download video %s: %s' % (video_id, error['message']), + expected=True) - result = video_json[u'result'] + result = video_json['result'] - formats = [{'url': x[u'url'], - 'format_id': x[u'content_format'] - } for x in result[u'files'] if x[u'content_format'] in self._known_formats] - formats.sort(key=lambda fmt: self._known_formats.index(fmt['format_id'])) + formats = [{ + 'url': x['url'], + 'format_id': x['content_format'], + 'preference': self._known_formats.index(x['content_format']), + } for x in result['files'] if x['content_format'] in self._known_formats] - if len(formats) == 0: - self._downloader.report_warning(u'No media links available for %s' % video_id) - return + self._sort_formats(formats) - duration = result[u'duration'] - compilation = result[u'compilation'] - title = result[u'title'] + if not formats: + raise ExtractorError('No media links available for %s' % video_id) - title = '%s - %s' % (compilation, title) if compilation is not None else title + duration = result['duration'] + compilation = result['compilation'] + title = result['title'] - previews = result[u'preview'] + title = '%s - %s' % (compilation, title) if compilation is not None else title + + previews = result['preview'] previews.sort(key=lambda fmt: self._known_thumbnails.index(fmt['content_format'])) - thumbnail = previews[-1][u'url'] if len(previews) > 0 else None + thumbnail = previews[-1]['url'] if len(previews) > 0 else None - video_page = self._download_webpage(url, video_id, u'Downloading video page') + video_page = self._download_webpage(url, video_id, 'Downloading video page') description = self._extract_description(video_page) comment_count = self._extract_comment_count(video_page) @@ -119,9 +129,24 @@ class IviIE(InfoExtractor): class IviCompilationIE(InfoExtractor): - IE_DESC = u'ivi.ru compilations' - IE_NAME = u'ivi:compilation' - _VALID_URL = r'^https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P[a-z\d_-]+)(?:/season(?P\d+))?$' + IE_DESC = 'ivi.ru compilations' + IE_NAME = 'ivi:compilation' + _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P[a-z\d_-]+)(?:/season(?P\d+))?$' + _TESTS = [{ + 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa', + 'info_dict': { + 'id': 'dvoe_iz_lartsa', + 'title': 'Двое из ларца (2006 - 2008)', + }, + 'playlist_mincount': 24, + }, { + 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/season1', + 'info_dict': { + 'id': 'dvoe_iz_lartsa/season1', + 'title': 'Двое из ларца (2006 - 2008) 1 сезон', + }, + 'playlist_mincount': 12, + }] def _extract_entries(self, html, compilation_id): return [self.url_result('http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), 'Ivi') @@ -132,23 +157,24 @@ class IviCompilationIE(InfoExtractor): compilation_id = mobj.group('compilationid') season_id = mobj.group('seasonid') - if season_id is not None: # Season link - season_page = self._download_webpage(url, compilation_id, u'Downloading season %s web page' % season_id) + if season_id is not None: # Season link + season_page = self._download_webpage(url, compilation_id, 'Downloading season %s web page' % season_id) playlist_id = '%s/season%s' % (compilation_id, season_id) - playlist_title = self._html_search_meta(u'title', season_page, u'title') + playlist_title = self._html_search_meta('title', season_page, 'title') entries = self._extract_entries(season_page, compilation_id) - else: # Compilation link - compilation_page = self._download_webpage(url, compilation_id, u'Downloading compilation web page') + else: # Compilation link + compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page') playlist_id = compilation_id - playlist_title = self._html_search_meta(u'title', compilation_page, u'title') + playlist_title = self._html_search_meta('title', compilation_page, 'title') seasons = re.findall(r'[^<]+' % compilation_id, compilation_page) - if len(seasons) == 0: # No seasons in this compilation + if len(seasons) == 0: # No seasons in this compilation entries = self._extract_entries(compilation_page, compilation_id) else: entries = [] for season_id in seasons: - season_page = self._download_webpage('http://www.ivi.ru/watch/%s/season%s' % (compilation_id, season_id), - compilation_id, u'Downloading season %s web page' % season_id) + season_page = self._download_webpage( + 'http://www.ivi.ru/watch/%s/season%s' % (compilation_id, season_id), + compilation_id, 'Downloading season %s web page' % season_id) entries.extend(self._extract_entries(season_page, compilation_id)) - return self.playlist_result(entries, playlist_id, playlist_title) \ No newline at end of file + return self.playlist_result(entries, playlist_id, playlist_title)