From: Adam Malcontenti-Wilson Date: Mon, 19 May 2014 11:25:58 +0000 (+1000) Subject: [adultswim] Add new extractor X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=commitdiff_plain;h=48fbb1003d901ef30654db8910b6f617efc49fb4;p=youtube-dl [adultswim] Add new extractor --- diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 3503c76b7..5f9ae7a3e 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -1,5 +1,6 @@ from .academicearth import AcademicEarthCourseIE from .addanime import AddAnimeIE +from .adultswim import AdultSwimIE from .aftonbladet import AftonbladetIE from .anitube import AnitubeIE from .aol import AolIE diff --git a/youtube_dl/extractor/adultswim.py b/youtube_dl/extractor/adultswim.py new file mode 100644 index 000000000..e61916fde --- /dev/null +++ b/youtube_dl/extractor/adultswim.py @@ -0,0 +1,100 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + +class AdultSwimIE(InfoExtractor): + _VALID_URL = r'https?://video\.adultswim\.com/(?P.+?)(?:\.html)?(?:\?.*)?(?:#.*)?$' + _TEST = { + 'url': 'http://video.adultswim.com/rick-and-morty/close-rick-counters-of-the-rick-kind.html?x=y#title', + 'md5': '4a90c63a07537ec9383175b330dfeab4', + 'info_dict': { + 'id': '8a250ba1450996e901453d7e9caf02f3', + 'title': 'Rick and Morty Close Rick-Counters of the Rick Kind', + 'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', + } + } + + _available_formats = ['150', '640', '3500'] + + _video_extensions = { + '3500': 'flv', + '640': 'mp4', + '150': 'mp4', + 'ipad': 'm3u8', + 'iphone': 'm3u8' + } + _video_dimensions = { + '3500': (1280, 720), + '640': (480, 270), + '150': (320, 180) + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_path = mobj.group('path') + + webpage = self._download_webpage(url, video_path) + episode_id = self._html_search_regex(r'', webpage, 'episode_id') + title = self._html_search_regex(r'', webpage, 'title') + + index_url = 'http://asfix.adultswim.com/asfix-svc/episodeSearch/getEpisodesByIDs?networkName=AS&ids=%s' % episode_id + idoc = self._download_xml(index_url, title, 'Downloading episode index', 'Unable to download episode index') + + episode_el = idoc.find('.//episode') + show_title = episode_el.attrib.get('collectionTitle') + episode_title = episode_el.attrib.get('title') + thumbnail = episode_el.attrib.get('thumbnailUrl') + description = episode_el.find('./description').text.strip() + + entries = [] + segment_els = episode_el.findall('./segments/segment') + + for part_num, segment_el in enumerate(segment_els): + segment_id = segment_el.attrib.get('id') + segment_title = '%s %s part %d' % (show_title, episode_title, part_num + 1) + thumbnail = segment_el.attrib.get('thumbnailUrl') + duration = segment_el.attrib.get('duration') + + segment_url = 'http://asfix.adultswim.com/asfix-svc/episodeservices/getCvpPlaylist?networkName=AS&id=%s' % segment_id + idoc = self._download_xml(segment_url, segment_title, 'Downloading segment information', 'Unable to download segment information') + + formats = [] + file_els = idoc.findall('.//files/file') + + for file_el in file_els: + bitrate = file_el.attrib.get('bitrate') + type = file_el.attrib.get('type') + width, height = self._video_dimensions.get(bitrate, (None, None)) + formats.append({ + 'format_id': '%s-%s' % (bitrate, type), + 'url': file_el.text, + 'ext': self._video_extensions.get(bitrate, 'mp4'), + 'tbr': bitrate, + 'height': height, + 'width': width + }) + + self._sort_formats(formats) + + entries.append({ + 'id': segment_id, + 'title': segment_title, + 'formats': formats, + 'uploader': show_title, + 'thumbnail': thumbnail, + 'duration': duration, + 'description': description + }) + + return { + '_type': 'playlist', + 'id': episode_id, + 'display_id': video_path, + 'entries': entries, + 'title': '%s %s' % (show_title, episode_title), + 'description': description, + 'thumbnail': thumbnail + }