# encoding: utf-8
+from __future__ import unicode_literals
+
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
+ int_or_none,
)
+
class CinemassacreIE(InfoExtractor):
- _VALID_URL = r'(?:http://)?(?:www\.)?(?P<url>cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/.+?)(?:[/?].*)?'
- _TESTS = [{
- u'url': u'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
- u'file': u'19911.mp4',
- u'info_dict': {
- u'upload_date': u'20121110',
- u'title': u'“Angry Video Game Nerd: The Movie” – Trailer',
- u'description': u'md5:fb87405fcb42a331742a0dce2708560b',
- },
- u'params': {
- u'skip_download': True,
- },
- },
- {
- u'url': u'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
- u'file': u'521be8ef82b16.mp4',
- u'info_dict': {
- u'upload_date': u'20131002',
- u'title': u'The Mummy’s Hand (1940)',
- },
- u'params': {
- u'skip_download': True,
+ _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)'
+ _TESTS = [
+ {
+ 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
+ 'md5': 'fde81fbafaee331785f58cd6c0d46190',
+ 'info_dict': {
+ 'id': '19911',
+ 'ext': 'mp4',
+ 'upload_date': '20121110',
+ 'title': '“Angry Video Game Nerd: The Movie” – Trailer',
+ 'description': 'md5:fb87405fcb42a331742a0dce2708560b',
+ },
},
- }]
+ {
+ 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
+ 'md5': 'd72f10cd39eac4215048f62ab477a511',
+ 'info_dict': {
+ 'id': '521be8ef82b16',
+ 'ext': 'mp4',
+ 'upload_date': '20131002',
+ 'title': 'The Mummy’s Hand (1940)',
+ },
+ }
+ ]
- def _real_extract(self,url):
+ def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
+ display_id = mobj.group('display_id')
- webpage_url = u'http://' + mobj.group('url')
- webpage = self._download_webpage(webpage_url, None) # Don't know video id yet
+ webpage = self._download_webpage(url, display_id)
video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
- mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/(?:embed|player)\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
+ mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P<full_video_id>(?:Cinemassacre-)?(?P<video_id>.+?)))"', webpage)
if not mobj:
- raise ExtractorError(u'Can\'t extract embed url and video id')
- playerdata_url = mobj.group(u'embed_url')
- video_id = mobj.group(u'video_id')
+ raise ExtractorError('Can\'t extract embed url and video id')
+ playerdata_url = mobj.group('embed_url')
+ video_id = mobj.group('video_id')
+ full_video_id = mobj.group('full_video_id')
- video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|',
- webpage, u'title')
- video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>',
- webpage, u'description', flags=re.DOTALL, fatal=False)
- if len(video_description) == 0:
- video_description = None
-
- playerdata = self._download_webpage(playerdata_url, video_id)
- base_url = self._html_search_regex(r'\'streamer\': \'(?P<base_url>rtmp://[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3})/(?:vod|Cinemassacre)\'',
- playerdata, u'base_url')
- base_url += '/Cinemassacre/'
- # Important: The file names in playerdata are not used by the player and even wrong for some videos
- sd_file = 'Cinemassacre-%s_high.mp4' % video_id
- hd_file = 'Cinemassacre-%s.mp4' % video_id
- video_thumbnail = 'http://image.screenwavemedia.com/Cinemassacre/Cinemassacre-%s_thumb_640x360.jpg' % video_id
-
- formats = [{
- 'id': video_id,
- 'url': base_url + hd_file,
- 'format': 'hd',
- 'ext': 'mp4',
- 'title': video_title,
- 'description': video_description,
- 'upload_date': video_date,
- 'thumbnail': video_thumbnail,
- },
- {
- 'id': video_id,
- 'url': base_url + sd_file,
- 'ext': 'mp4',
- 'format': 'sd',
- 'title': video_title,
- 'description': video_description,
- 'upload_date': video_date,
- 'thumbnail': video_thumbnail,
- }]
-
- if self._downloader.params.get('listformats', None):
- self._print_formats(formats)
- return
+ video_title = self._html_search_regex(
+ r'<title>(?P<title>.+?)\|', webpage, 'title')
+ video_description = self._html_search_regex(
+ r'<div class="entry-content">(?P<description>.+?)</div>',
+ webpage, 'description', flags=re.DOTALL, fatal=False)
+ video_thumbnail = self._og_search_thumbnail(webpage)
+
+ playerdata = self._download_webpage(playerdata_url, video_id, 'Downloading player webpage')
- req_format = self._downloader.params.get('format', 'best')
- self.to_screen(u'Format: %s' % req_format)
+ vidurl = self._search_regex(
+ r'\'vidurl\'\s*:\s*"([^\']+)"', playerdata, 'vidurl').replace('\\/', '/')
- if req_format is None or req_format == 'best':
- return [formats[0]]
- elif req_format == 'worst':
- return [formats[-1]]
- elif req_format in ('-1', 'all'):
- return formats
+ videolist_url = None
+
+ mobj = re.search(r"'videoserver'\s*:\s*'(?P<videoserver>[^']+)'", playerdata)
+ if mobj:
+ videoserver = mobj.group('videoserver')
+ mobj = re.search(r'\'vidid\'\s*:\s*"(?P<vidid>[^\']+)"', playerdata)
+ vidid = mobj.group('vidid') if mobj else full_video_id
+ videolist_url = 'http://%s/vod/smil:%s.smil/jwplayer.smil' % (videoserver, vidid)
else:
- format = self._specific( req_format, formats )
- if format is None:
- raise ExtractorError(u'Requested format not available')
- return [format]
+ mobj = re.search(r"file\s*:\s*'(?P<smil>http.+?/jwplayer\.smil)'", playerdata)
+ if mobj:
+ videolist_url = mobj.group('smil')
- def _print_formats(self, formats):
- """Print all available formats"""
- print(u'Available formats:')
- print(u'ext\t\tformat')
- print(u'---------------------------------')
- for format in formats:
- print(u'%s\t\t%s' % (format['ext'], format['format']))
+ if videolist_url:
+ videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML')
+ formats = []
+ baseurl = vidurl[:vidurl.rfind('/') +1]
+ for video in videolist.findall('.//video'):
+ src = video.get('src')
+ if not src:
+ continue
+ file_ = src.partition(':')[-1]
+ width = int_or_none(video.get('width'))
+ height = int_or_none(video.get('height'))
+ bitrate = int_or_none(video.get('system-bitrate'))
+ format = {
+ 'url': baseurl + file_,
+ 'format_id': src.rpartition('.')[0].rpartition('_')[-1],
+ }
+ if width or height:
+ format.update({
+ 'tbr': bitrate // 1000 if bitrate else None,
+ 'width': width,
+ 'height': height,
+ })
+ else:
+ format.update({
+ 'abr': bitrate // 1000 if bitrate else None,
+ 'vcodec': 'none',
+ })
+ formats.append(format)
+ self._sort_formats(formats)
+ else:
+ formats = [{
+ 'url': vidurl,
+ }]
- def _specific(self, req_format, formats):
- for x in formats:
- if x["format"] == req_format:
- return x
- return None
+ return {
+ 'id': video_id,
+ 'title': video_title,
+ 'formats': formats,
+ 'description': video_description,
+ 'upload_date': video_date,
+ 'thumbnail': video_thumbnail,
+ }
projects / youtube-dl / blobdiff