# encoding: utf-8
+from __future__ import unicode_literals
import re
from .common import InfoExtractor
ExtractorError,
)
+
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'“Angry Video Game Nerd: The Movie” is...', # Description is too long
- },
- 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/',
+ 'file': '19911.mp4',
+ 'md5': '782f8504ca95a0eba8fc9177c373eec7',
+ 'info_dict': {
+ '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',
+ 'file': '521be8ef82b16.mp4',
+ 'md5': 'dec39ee5118f8d9cc067f45f9cbe3a35',
+ 'info_dict': {
+ '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\?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')
- 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)
- req_format = self._downloader.params.get('format', 'best')
- self.to_screen(u'Format: %s' % req_format)
+ playerdata = self._download_webpage(playerdata_url, video_id)
- 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
- else:
- format = self._specific( req_format, formats )
- if format is None:
- raise ExtractorError(u'Requested format not available')
- return [format]
+ sd_url = self._html_search_regex(r'file: \'([^\']+)\', label: \'SD\'', playerdata, 'sd_file')
+ hd_url = self._html_search_regex(
+ r'file: \'([^\']+)\', label: \'HD\'', playerdata, 'hd_file',
+ default=None)
+ video_thumbnail = self._html_search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False)
- 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']))
+ formats = [{
+ 'url': sd_url,
+ 'ext': 'mp4',
+ 'format': 'sd',
+ 'format_id': 'sd',
+ 'quality': 1,
+ }]
+ if hd_url:
+ formats.append({
+ 'url': hd_url,
+ 'ext': 'mp4',
+ 'format': 'hd',
+ 'format_id': 'hd',
+ 'quality': 2,
+ })
+ self._sort_formats(formats)
- 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,
+ }