X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/0652569e481a8cf0995a00635ef62143fa779add..1918d37666ea9185c49ca84e64f58e4ff2a422c9:/youtube_dl/extractor/dramafever.py diff --git a/youtube_dl/extractor/dramafever.py b/youtube_dl/extractor/dramafever.py index 38e6597..6b60e54 100644 --- a/youtube_dl/extractor/dramafever.py +++ b/youtube_dl/extractor/dramafever.py @@ -1,27 +1,27 @@ -# encoding: utf-8 +# coding: utf-8 from __future__ import unicode_literals import itertools -from .common import InfoExtractor +from .amp import AMPIE from ..compat import ( compat_HTTPError, - compat_urllib_parse, - compat_urllib_request, compat_urlparse, ) from ..utils import ( ExtractorError, clean_html, - determine_ext, int_or_none, - parse_iso8601, + remove_end, + sanitized_Request, + urlencode_postdata ) -class DramaFeverBaseIE(InfoExtractor): +class DramaFeverBaseIE(AMPIE): _LOGIN_URL = 'https://www.dramafever.com/accounts/login/' _NETRC_MACHINE = 'dramafever' + _GEO_COUNTRIES = ['US', 'CA'] _CONSUMER_SECRET = 'DA59dtVXYLxajktV' @@ -51,15 +51,15 @@ class DramaFeverBaseIE(InfoExtractor): 'password': password, } - request = compat_urllib_request.Request( - self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8')) + request = sanitized_Request( + self._LOGIN_URL, urlencode_postdata(login_form)) response = self._download_webpage( - request, None, 'Logging in as %s' % username) + request, None, 'Logging in') if all(logout_pattern not in response for logout_pattern in ['href="/accounts/logout/"', '>Log out<']): error = self._html_search_regex( - r'(?s)class="hidden-xs prompt"[^>]*>(.+?)<', + r'(?s)]+\bclass="hidden-xs prompt"[^>]*>(.+?)[0-9]+/[0-9]+)(?:/|$)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P[0-9]+/[0-9]+)(?:/|$)' + _TESTS = [{ 'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/', 'info_dict': { 'id': '4512.1', 'ext': 'flv', - 'title': 'Cooking with Shin 4512.1', + 'title': 'Cooking with Shin', 'description': 'md5:a8eec7942e1664a6896fcd5e1287bfd0', - 'thumbnail': 're:^https?://.*\.jpg', + 'episode': 'Episode 1', + 'episode_number': 1, + 'thumbnail': r're:^https?://.*\.jpg', 'timestamp': 1404336058, 'upload_date': '20140702', - 'duration': 343, - } - } + 'duration': 344, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'http://www.dramafever.com/drama/4826/4/Mnet_Asian_Music_Awards_2015/?ap=1', + 'info_dict': { + 'id': '4826.4', + 'ext': 'flv', + 'title': 'Mnet Asian Music Awards 2015', + 'description': 'md5:3ff2ee8fedaef86e076791c909cf2e91', + 'episode': 'Mnet Asian Music Awards 2015 - Part 3', + 'episode_number': 4, + 'thumbnail': r're:^https?://.*\.jpg', + 'timestamp': 1450213200, + 'upload_date': '20151215', + 'duration': 5359, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'https://www.dramafever.com/zh-cn/drama/4972/15/Doctor_Romantic/', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url).replace('/', '.') try: - feed = self._download_json( - 'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id, - video_id, 'Downloading episode JSON')['channel']['item'] + info = self._extract_feed_info( + 'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError): - raise ExtractorError( - 'Currently unavailable in your country.', expected=True) + self.raise_geo_restricted( + msg='Currently unavailable in your country', + countries=self._GEO_COUNTRIES) raise - media_group = feed.get('media-group', {}) - - formats = [] - for media_content in media_group['media-content']: - src = media_content.get('@attributes', {}).get('url') - if not src: - continue - ext = determine_ext(src) - if ext == 'f4m': - formats.extend(self._extract_f4m_formats( - src, video_id, f4m_id='hds')) - elif ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - src, video_id, 'mp4', m3u8_id='hls')) - else: - formats.append({ - 'url': src, - }) - self._sort_formats(formats) - - title = media_group.get('media-title') - description = media_group.get('media-description') - duration = int_or_none(media_group['media-content'][0].get('@attributes', {}).get('duration')) - thumbnail = self._proto_relative_url( - media_group.get('media-thumbnail', {}).get('@attributes', {}).get('url')) - timestamp = parse_iso8601(feed.get('pubDate'), ' ') - - subtitles = {} - for media_subtitle in media_group.get('media-subTitle', []): - lang = media_subtitle.get('@attributes', {}).get('lang') - href = media_subtitle.get('@attributes', {}).get('href') - if not lang or not href: - continue - subtitles[lang] = [{ - 'ext': 'ttml', - 'url': href, - }] + # title is postfixed with video id for some reason, removing + if info.get('title'): + info['title'] = remove_end(info['title'], video_id).strip() series_id, episode_number = video_id.split('.') episode_info = self._download_json( @@ -143,29 +136,29 @@ class DramaFeverIE(DramaFeverBaseIE): video_id, 'Downloading episode info JSON', fatal=False) if episode_info: value = episode_info.get('value') - if value: - subfile = value[0].get('subfile') or value[0].get('new_subfile') - if subfile and subfile != 'http://www.dramafever.com/st/': - subtitles.setdefault('English', []).append({ - 'ext': 'srt', - 'url': subfile, - }) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'timestamp': timestamp, - 'duration': duration, - 'formats': formats, - 'subtitles': subtitles, - } + if isinstance(value, list): + for v in value: + if v.get('type') == 'Episode': + subfile = v.get('subfile') or v.get('new_subfile') + if subfile and subfile != 'http://www.dramafever.com/st/': + info.setdefault('subtitles', {}).setdefault('English', []).append({ + 'ext': 'srt', + 'url': subfile, + }) + episode_number = int_or_none(v.get('number')) + episode_fallback = 'Episode' + if episode_number: + episode_fallback += ' %d' % episode_number + info['episode'] = v.get('title') or episode_fallback + info['episode_number'] = episode_number + break + + return info class DramaFeverSeriesIE(DramaFeverBaseIE): IE_NAME = 'dramafever:series' - _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$' + _VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$' _TESTS = [{ 'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/', 'info_dict': {