From a14001a5a13b1639dc98b75b0775d251487aad1d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?D=C3=A9stin=20Reed?= Date: Wed, 17 Aug 2016 16:02:59 +0200 Subject: [PATCH] [Filmweb] Add extractor --- youtube_dl/extractor/extractors.py | 2 ++ youtube_dl/extractor/filmweb.py | 45 ++++++++++++++++++++++++ youtube_dl/extractor/twentythreevideo.py | 45 ++++++++++++++++++++++++ 3 files changed, 92 insertions(+) create mode 100644 youtube_dl/extractor/filmweb.py create mode 100644 youtube_dl/extractor/twentythreevideo.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 91bd3287c..04125d9f2 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -345,6 +345,7 @@ from .filmon import ( FilmOnIE, FilmOnChannelIE, ) +from .filmweb import FilmwebIE from .firsttv import FirstTVIE from .fivemin import FiveMinIE from .fivetv import FiveTVIE @@ -1120,6 +1121,7 @@ from .tvplayer import TVPlayerIE from .tweakers import TweakersIE from .twentyfourvideo import TwentyFourVideoIE from .twentymin import TwentyMinutenIE +from .twentythreevideo import TwentyThreeVideoIE from .twitch import ( TwitchVideoIE, TwitchChapterIE, diff --git a/youtube_dl/extractor/filmweb.py b/youtube_dl/extractor/filmweb.py new file mode 100644 index 000000000..a3d9f872e --- /dev/null +++ b/youtube_dl/extractor/filmweb.py @@ -0,0 +1,45 @@ +from __future__ import unicode_literals + +from .twentythreevideo import TwentyThreeVideoIE + + +class FilmwebIE(TwentyThreeVideoIE): + IE_NAME = 'Filmweb' + _VALID_URL = r'https?://(?:www\.)?filmweb\.no/trailere/article(?P\d+).ece' + _TEST = { + 'url': 'http://www.filmweb.no/trailere/article1264921.ece', + 'md5': 'e353f47df98e557d67edaceda9dece89', + 'info_dict': { + 'id': '1264921', + 'title': 'Det som en gang var', + 'ext': 'mp4', + 'description': 'Trailer: Scener fra et vennskap', + } + } + + _CLIENT_NAME = 'filmweb' + _CLIENT_ID = '12732917' + _EMBED_BASE_URL = 'http://www.filmweb.no/template/ajax/json_trailerEmbed.jsp?articleId=%s&autoplay=true' + + def _real_extract(self, url): + article_id = self._match_id(url) + webpage = self._download_webpage(url, article_id) + + title = self._search_regex(r'var\s+jsTitle\s*=\s*escape\("([^"]+)"\);', + webpage, 'title', fatal=True) + + format_url = self._proto_relative_url( + self._html_search_regex(r'"(//filmweb\.23video\.com/[^"]+)"', + self._download_json(self._EMBED_BASE_URL % article_id, + article_id)['embedCode'], 'format url')) + + formats = self._extract_formats(format_url, self._CLIENT_ID) + self._sort_formats(formats) + + return { + 'id': article_id, + 'title': title, + 'alt_title': self._og_search_title(webpage), + 'formats': formats, + 'description': self._og_search_description(webpage), + } diff --git a/youtube_dl/extractor/twentythreevideo.py b/youtube_dl/extractor/twentythreevideo.py new file mode 100644 index 000000000..2bad2dbd6 --- /dev/null +++ b/youtube_dl/extractor/twentythreevideo.py @@ -0,0 +1,45 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class TwentyThreeVideoIE(InfoExtractor): + IE_NAME = '23video' + _VALID_URL = r'https?://(?:www\.)?(?P[\w-]+)\.23video\.com/v.ihtml/player.html.*photo_id=(?P\d+)' + _TEST = {} + + _URL_TEMPLATE = 'https://%s.23video.com/%s/%s/%s/%s/download-video.mp4' + _FORMATS = { + 'video_hd': { + 'width': 1280, + 'height': 720, + }, + 'video_medium': { + 'width': 640, + 'height': 360, + }, + 'video_mobile_high': { + 'width': 320, + 'height': 180, + } + } + + def _extract_formats(self, url, client_id): + client_name = self._search_regex(r'([a-z]+)\.23video\.com', url, 'client name') + video_id = self._search_regex(r'photo%5fid=([^?&]+)', url, 'video id') + token = self._search_regex(r'token=([^?&]+)', url, 'token') + + formats = [] + for format_key in self._FORMATS.keys(): + formats.append({ + 'url': self._URL_TEMPLATE % (client_name, client_id, video_id, + token, format_key), + 'width': self._FORMATS.get(format_key, {}).get('width'), + 'height': self._FORMATS.get(format_key, {}).get('height'), + }) + + return formats + + def _real_extract(self, url): + # TODO: Find out how to extract client_id + raise NotImplementedError('Not able to extract the `client_id`')