yt-dlp/youtube_dl/extractor/cinemassacre.py
Jaime Marquínez Ferrándiz 47610c4d3e [cinemassacre] Fix extraction
Now we download over http, we don't need rtmpdump.
2014-02-24 14:35:26 +01:00

80 lines
3.0 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# encoding: utf-8
import re
from .common import InfoExtractor
from ..utils import (
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'md5': u'fde81fbafaee331785f58cd6c0d46190',
u'info_dict': {
u'upload_date': u'20121110',
u'title': u'“Angry Video Game Nerd: The Movie” Trailer',
u'description': u'md5:fb87405fcb42a331742a0dce2708560b',
},
},
{
u'url': u'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
u'file': u'521be8ef82b16.mp4',
u'md5': u'd72f10cd39eac4215048f62ab477a511',
u'info_dict': {
u'upload_date': u'20131002',
u'title': u'The Mummys Hand (1940)',
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
webpage_url = u'http://' + mobj.group('url')
webpage = self._download_webpage(webpage_url, None) # Don't know video id yet
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/[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')
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)
sd_url = self._html_search_regex(r'file: \'(?P<sd_file>[^\']+)\', label: \'SD\'', playerdata, u'sd_file')
hd_url= self._html_search_regex(r'file: \'(?P<hd_file>[^\']+)\', label: \'HD\'', playerdata, u'hd_file')
video_thumbnail = self._html_search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, u'thumbnail', fatal=False)
formats = [
{
'url': sd_url,
'ext': 'mp4',
'format': 'sd',
'format_id': 'sd',
},
{
'url': hd_url,
'ext': 'mp4',
'format': 'hd',
'format_id': 'hd',
},
]
return {
'id': video_id,
'title': video_title,
'formats': formats,
'description': video_description,
'upload_date': video_date,
'thumbnail': video_thumbnail,
}