[adultswim] Updated to work with new site format (fixes #4317)

This commit is contained in:
cryptonaut 2014-12-05 21:49:41 -08:00
parent 0df23ba9f9
commit 7115599121

View file

@ -2,123 +2,147 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import json
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class AdultSwimIE(InfoExtractor): class AdultSwimIE(InfoExtractor):
_VALID_URL = r'https?://video\.adultswim\.com/(?P<path>.+?)(?:\.html)?(?:\?.*)?(?:#.*)?$' _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?'
_TEST = {
'url': 'http://video.adultswim.com/rick-and-morty/close-rick-counters-of-the-rick-kind.html?x=y#title', _TESTS = [{
'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
'playlist': [
{
'md5': '247572debc75c7652f253c8daa51a14d',
'info_dict': {
'id': 'rQxZvXQ4ROaSOqq-or2Mow-0',
'ext': 'flv',
'title': 'Rick and Morty - Pilot Part 1',
'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
},
},
{
'md5': '77b0e037a4b20ec6b98671c4c379f48d',
'info_dict': {
'id': 'rQxZvXQ4ROaSOqq-or2Mow-3',
'ext': 'flv',
'title': 'Rick and Morty - Pilot Part 4',
'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
},
},
],
'info_dict': {
'title': 'Rick and Morty - Pilot',
'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
}
}, {
'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
'playlist': [ 'playlist': [
{ {
'md5': '4da359ec73b58df4575cd01a610ba5dc', 'md5': '2eb5c06d0f9a1539da3718d897f13ec5',
'info_dict': { 'info_dict': {
'id': '8a250ba1450996e901453d7f02ca02f5', 'id': '-t8CamQlQ2aYZ49ItZCFog-0',
'ext': 'flv', 'ext': 'flv',
'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 1', 'title': 'American Dad - Putting Francine Out of Business',
'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', 'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
'uploader': 'Rick and Morty', },
'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
}
},
{
'md5': 'ffbdf55af9331c509d95350bd0cc1819',
'info_dict': {
'id': '8a250ba1450996e901453d7f4bd102f6',
'ext': 'flv',
'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 2',
'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
'uploader': 'Rick and Morty',
'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
}
},
{
'md5': 'b92409635540304280b4b6c36bd14a0a',
'info_dict': {
'id': '8a250ba1450996e901453d7fa73c02f7',
'ext': 'flv',
'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 3',
'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
'uploader': 'Rick and Morty',
'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
}
},
{
'md5': 'e8818891d60e47b29cd89d7b0278156d',
'info_dict': {
'id': '8a250ba1450996e901453d7fc8ba02f8',
'ext': 'flv',
'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 4',
'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
'uploader': 'Rick and Morty',
'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
}
} }
] ],
} 'info_dict': {
'title': 'American Dad - Putting Francine Out of Business',
'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
},
}]
_video_extensions = { @staticmethod
'3500': 'flv', def find_video_info(collection, slug):
'640': 'mp4', for video in collection.get('videos'):
'150': 'mp4', if video.get('slug') == slug:
'ipad': 'm3u8', return video
'iphone': 'm3u8'
} @staticmethod
_video_dimensions = { def find_collection_by_linkURL(collections, linkURL):
'3500': (1280, 720), for collection in collections:
'640': (480, 270), if collection.get('linkURL') == linkURL:
'150': (320, 180) return collection
}
@staticmethod
def find_collection_containing_video(collections, slug):
for collection in collections:
for video in collection.get('videos'):
if video.get('slug') == slug:
return collection, video
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_path = mobj.group('path') show_path = mobj.group('show_path')
episode_path = mobj.group('episode_path')
is_playlist = True if mobj.group('is_playlist') else False
webpage = self._download_webpage(url, video_path) webpage = self._download_webpage(url, episode_path)
episode_id = self._html_search_regex(
r'<link rel="video_src" href="http://i\.adultswim\.com/adultswim/adultswimtv/tools/swf/viralplayer.swf\?id=([0-9a-f]+?)"\s*/?\s*>',
webpage, 'episode_id')
title = self._og_search_title(webpage)
index_url = 'http://asfix.adultswim.com/asfix-svc/episodeSearch/getEpisodesByIDs?networkName=AS&ids=%s' % episode_id # Extract the value of `bootstrappedData` from the Javascript in the page.
idoc = self._download_xml(index_url, title, 'Downloading episode index', 'Unable to download episode index') bootstrappedDataJS = self._search_regex(r'var bootstrappedData = ({.*});', webpage, episode_path)
episode_el = idoc.find('.//episode') try:
show_title = episode_el.attrib.get('collectionTitle') bootstrappedData = json.loads(bootstrappedDataJS)
episode_title = episode_el.attrib.get('title') except ValueError as ve:
thumbnail = episode_el.attrib.get('thumbnailUrl') errmsg = '%s: Failed to parse JSON ' % episode_path
description = episode_el.find('./description').text.strip() raise ExtractorError(errmsg, cause=ve)
# Downloading videos from a /videos/playlist/ URL needs to be handled differently.
# NOTE: We are only downloading one video (the current one) not the playlist
if is_playlist:
collections = bootstrappedData['playlists']['collections']
collection = self.find_collection_by_linkURL(collections, show_path)
video_info = self.find_video_info(collection, episode_path)
show_title = video_info['showTitle']
segment_ids = [video_info['videoPlaybackID']]
else:
collections = bootstrappedData['show']['collections']
collection, video_info = self.find_collection_containing_video(collections, episode_path)
show = bootstrappedData['show']
show_title = show['title']
segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
episode_id = video_info['id']
episode_title = video_info['title']
episode_description = video_info['description']
episode_duration = video_info.get('duration')
entries = [] entries = []
segment_els = episode_el.findall('./segments/segment') for part_num, segment_id in enumerate(segment_ids):
segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=mobile' % segment_id
for part_num, segment_el in enumerate(segment_els): segment_title = '%s - %s' % (show_title, episode_title)
segment_id = segment_el.attrib.get('id') if len(segment_ids) > 1:
segment_title = '%s %s part %d' % (show_title, episode_title, part_num + 1) segment_title += ' Part %d' % (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( idoc = self._download_xml(
segment_url, segment_title, segment_url, segment_title,
'Downloading segment information', 'Unable to download segment information') 'Downloading segment information', 'Unable to download segment information')
segment_duration = idoc.find('.//trt').text.strip()
formats = [] formats = []
file_els = idoc.findall('.//files/file') file_els = idoc.findall('.//files/file')
for file_el in file_els: for file_el in file_els:
bitrate = file_el.attrib.get('bitrate') bitrate = file_el.attrib.get('bitrate')
type = file_el.attrib.get('type') ftype = file_el.attrib.get('type')
width, height = self._video_dimensions.get(bitrate, (None, None))
formats.append({ formats.append({
'format_id': '%s-%s' % (bitrate, type), 'format_id': '%s_%s' % (bitrate, ftype),
'url': file_el.text, 'url': file_el.text.strip(),
'ext': self._video_extensions.get(bitrate, 'mp4'),
# The bitrate may not be a number (for example: 'iphone') # The bitrate may not be a number (for example: 'iphone')
'tbr': int(bitrate) if bitrate.isdigit() else None, 'tbr': int(bitrate) if bitrate.isdigit() else None,
'height': height, 'quality': 1 if ftype == 'hd' else -1
'width': width
}) })
self._sort_formats(formats) self._sort_formats(formats)
@ -127,18 +151,16 @@ def _real_extract(self, url):
'id': segment_id, 'id': segment_id,
'title': segment_title, 'title': segment_title,
'formats': formats, 'formats': formats,
'uploader': show_title, 'duration': segment_duration,
'thumbnail': thumbnail, 'description': episode_description
'duration': duration,
'description': description
}) })
return { return {
'_type': 'playlist', '_type': 'playlist',
'id': episode_id, 'id': episode_id,
'display_id': video_path, 'display_id': episode_path,
'entries': entries, 'entries': entries,
'title': '%s %s' % (show_title, episode_title), 'title': '%s - %s' % (show_title, episode_title),
'description': description, 'description': episode_description,
'thumbnail': thumbnail 'duration': episode_duration
} }