Compare commits

...

3 Commits

Author SHA1 Message Date
Philipp Hagemeister
d6d5028922 release 2014.07.11.2 2014-07-11 13:34:48 +02:00
Philipp Hagemeister
38ad119f97 [screencast] Add new extractor (Fixes #3236) 2014-07-11 13:34:19 +02:00
Philipp Hagemeister
4e415288d7 [criterion] Simplify and modernize 2014-07-11 13:21:32 +02:00
4 changed files with 77 additions and 25 deletions

View File

@@ -248,6 +248,7 @@ from .rutube import (
from .rutv import RUTVIE
from .savefrom import SaveFromIE
from .scivee import SciVeeIE
from .screencast import ScreencastIE
from .servingsys import ServingSysIE
from .sina import SinaIE
from .slideshare import SlideshareIE

View File

@@ -1,40 +1,43 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import determine_ext
class CriterionIE(InfoExtractor):
_VALID_URL = r'https?://www\.criterion\.com/films/(\d*)-.+'
_VALID_URL = r'https?://www\.criterion\.com/films/(?P<id>[0-9]+)-.+'
_TEST = {
u'url': u'http://www.criterion.com/films/184-le-samourai',
u'file': u'184.mp4',
u'md5': u'bc51beba55685509883a9a7830919ec3',
u'info_dict': {
u"title": u"Le Samouraï",
u"description" : u'md5:a2b4b116326558149bef81f76dcbb93f',
'url': 'http://www.criterion.com/films/184-le-samourai',
'md5': 'bc51beba55685509883a9a7830919ec3',
'info_dict': {
'id': '184',
'ext': 'mp4',
'title': 'Le Samouraï',
'description': 'md5:a2b4b116326558149bef81f76dcbb93f',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
final_url = self._search_regex(r'so.addVariable\("videoURL", "(.+?)"\)\;',
webpage, 'video url')
title = self._html_search_regex(r'<meta content="(.+?)" property="og:title" />',
webpage, 'video title')
description = self._html_search_regex(r'<meta name="description" content="(.+?)" />',
webpage, 'video description')
thumbnail = self._search_regex(r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
webpage, 'thumbnail url')
final_url = self._search_regex(
r'so.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
title = self._og_search_title(webpage)
description = self._html_search_regex(
r'<meta name="description" content="(.+?)" />',
webpage, 'video description')
thumbnail = self._search_regex(
r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
webpage, 'thumbnail url')
return {'id': video_id,
'url' : final_url,
'title': title,
'ext': determine_ext(final_url),
'description': description,
'thumbnail': thumbnail,
}
return {
'id': video_id,
'url': final_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
}

View File

@@ -0,0 +1,48 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
compat_parse_qs,
compat_urllib_request,
)
class ScreencastIE(InfoExtractor):
_VALID_URL = r'https?://www\.screencast\.com/t/(?P<id>[a-zA-Z0-9]+)'
_TEST = {
'url': 'http://www.screencast.com/t/3ZEjQXlT',
'md5': '917df1c13798a3e96211dd1561fded83',
'info_dict': {
'id': '3ZEjQXlT',
'ext': 'm4v',
'title': 'Color Measurement with Ocean Optics Spectrometers',
'description': 'md5:240369cde69d8bed61349a199c5fb153',
'thumbnail': 're:^https?://.*\.jpg$'
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
flash_vars_s = self._html_search_regex(
r'<param name="flashVars" value="([^"]+)"', webpage, 'flash vars')
flash_vars = compat_parse_qs(flash_vars_s)
thumbnail = flash_vars.get('thumb', [None])[0]
video_url_raw = compat_urllib_request.quote(flash_vars['content'][0])
video_url = video_url_raw.replace('http%3A', 'http:')
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
return {
'id': video_id,
'url': video_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
}

View File

@@ -1,2 +1,2 @@
__version__ = '2014.07.11.1'
__version__ = '2014.07.11.2'