jens/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[cinemassacre] Modernize

Browse source
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-02-24 14:44:29 +01:00
parent 47610c4d3e
commit 5bb67dbfea
1 changed files with 31 additions and 29 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

60
youtube_dl/extractor/cinemassacre.py
View file

@ -1,4 +1,5 @@
# encoding: utf-8 # encoding: utf-8
from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -8,51 +9,52 @@ from ..utils import (
class CinemassacreIE(InfoExtractor): 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})/.+?)(?:[/?].*)?' _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})/.+?'
_TESTS = [{ _TESTS = [
u'url': u'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', {
u'file': u'19911.mp4', 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
u'md5': u'fde81fbafaee331785f58cd6c0d46190', 'file': '19911.mp4',
u'info_dict': { 'md5': 'fde81fbafaee331785f58cd6c0d46190',
u'upload_date': u'20121110', 'info_dict': {
u'title': u'“Angry Video Game Nerd: The Movie” – Trailer', 'upload_date': '20121110',
u'description': u'md5:fb87405fcb42a331742a0dce2708560b', 'title': '“Angry Video Game Nerd: The Movie” – Trailer',
'description': 'md5:fb87405fcb42a331742a0dce2708560b',
},
}, },
}, {
{ 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
u'url': u'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', 'file': '521be8ef82b16.mp4',
u'file': u'521be8ef82b16.mp4', 'md5': 'd72f10cd39eac4215048f62ab477a511',
u'md5': u'd72f10cd39eac4215048f62ab477a511', 'info_dict': {
u'info_dict': { 'upload_date': '20131002',
u'upload_date': u'20131002', 'title': 'The Mummy’s Hand (1940)',
u'title': u'The Mummy’s Hand (1940)', },
}, }
}] ]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
webpage_url = u'http://' + mobj.group('url') webpage = self._download_webpage(url, None) # Don't know video id yet
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') 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) 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: if not mobj:
raise ExtractorError(u'Can\'t extract embed url and video id') raise ExtractorError('Can\'t extract embed url and video id')
playerdata_url = mobj.group(u'embed_url') playerdata_url = mobj.group('embed_url')
video_id = mobj.group(u'video_id') video_id = mobj.group('video_id')
video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|', video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|',
webpage, u'title') webpage, 'title')
video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>', video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>',
webpage, u'description', flags=re.DOTALL, fatal=False) webpage, 'description', flags=re.DOTALL, fatal=False)
if len(video_description) == 0: if len(video_description) == 0:
video_description = None video_description = None
playerdata = self._download_webpage(playerdata_url, video_id) 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') sd_url = self._html_search_regex(r'file: \'(?P<sd_file>[^\']+)\', label: \'SD\'', playerdata, 'sd_file')
hd_url= self._html_search_regex(r'file: \'(?P<hd_file>[^\']+)\', label: \'HD\'', playerdata, u'hd_file') hd_url = self._html_search_regex(r'file: \'(?P<hd_file>[^\']+)\', label: \'HD\'', playerdata, 'hd_file')
video_thumbnail = self._html_search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, u'thumbnail', fatal=False) video_thumbnail = self._html_search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False)
formats = [ formats = [
{ {