Merge remote-tracking branch 'origin/master'

This commit is contained in:
Philipp Hagemeister 2014-03-09 18:08:16 +01:00
commit 9e55e37a2e
10 changed files with 131 additions and 36 deletions

View file

@ -0,0 +1,44 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import FakeYDL
from youtube_dl.extractor.common import InfoExtractor
from youtube_dl.extractor import YoutubeIE, get_info_extractor
class TestIE(InfoExtractor):
pass
class TestInfoExtractor(unittest.TestCase):
def setUp(self):
self.ie = TestIE(FakeYDL())
def test_ie_key(self):
self.assertEqual(get_info_extractor(YoutubeIE.ie_key()), YoutubeIE)
def test_html_search_regex(self):
html = '<p id="foo">Watch this <a href="http://www.youtube.com/watch?v=BaW_jenozKc">video</a></p>'
search = lambda re, *args: self.ie._html_search_regex(re, html, *args)
self.assertEqual(search(r'<p id="foo">(.+?)</p>', 'foo'), 'Watch this video')
def test_opengraph(self):
ie = self.ie
html = '''
<meta name="og:title" content='Foo'/>
<meta content="Some video's description " name="og:description"/>
<meta property='og:image' content='http://domain.com/pic.jpg?key1=val1&amp;key2=val2'/>
'''
self.assertEqual(ie._og_search_title(html), 'Foo')
self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
if __name__ == '__main__':
unittest.main()

View file

@ -99,7 +99,7 @@ class TestPlaylists(unittest.TestCase):
result = ie.extract('http://www.ustream.tv/channel/young-americans-for-liberty') result = ie.extract('http://www.ustream.tv/channel/young-americans-for-liberty')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['id'], '5124905') self.assertEqual(result['id'], '5124905')
self.assertTrue(len(result['entries']) >= 11) self.assertTrue(len(result['entries']) >= 6)
def test_soundcloud_set(self): def test_soundcloud_set(self):
dl = FakeYDL() dl = FakeYDL()

View file

@ -370,6 +370,9 @@ class YoutubeDL(object):
Print the message to stderr, it will be prefixed with 'WARNING:' Print the message to stderr, it will be prefixed with 'WARNING:'
If stderr is a tty file the 'WARNING:' will be colored If stderr is a tty file the 'WARNING:' will be colored
''' '''
if self.params.get('logger') is not None:
self.params['logger'].warning(message)
else:
if self._err_file.isatty() and os.name != 'nt': if self._err_file.isatty() and os.name != 'nt':
_msg_header = '\033[0;33mWARNING:\033[0m' _msg_header = '\033[0;33mWARNING:\033[0m'
else: else:

View file

@ -35,15 +35,15 @@ class CollegeHumorIE(InfoExtractor):
}, },
# embedded youtube video # embedded youtube video
{ {
'url': 'http://www.collegehumor.com/embed/6950457', 'url': 'http://www.collegehumor.com/embed/6950306',
'info_dict': { 'info_dict': {
'id': 'W5gMp3ZjYg4', 'id': 'Z-bao9fg6Yc',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Funny Dogs Protecting Babies Compilation 2014 [NEW HD]', 'title': 'Young Americans Think President John F. Kennedy Died THIS MORNING IN A CAR ACCIDENT!!!',
'uploader': 'FunnyPlox TV', 'uploader': 'Mark Dice',
'uploader_id': 'funnyploxtv', 'uploader_id': 'MarkDice',
'description': 'md5:7ded37421526d54afdf005e25bc2b7a3', 'description': 'md5:62c3dab9351fac7bb44b53b69511d87f',
'upload_date': '20140128', 'upload_date': '20140127',
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,

View file

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -6,13 +8,14 @@ from .common import InfoExtractor
class GamekingsIE(InfoExtractor): class GamekingsIE(InfoExtractor):
_VALID_URL = r'http://www\.gamekings\.tv/videos/(?P<name>[0-9a-z\-]+)' _VALID_URL = r'http://www\.gamekings\.tv/videos/(?P<name>[0-9a-z\-]+)'
_TEST = { _TEST = {
u"url": u"http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/", 'url': 'http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/',
u'file': u'20130811.mp4',
# MD5 is flaky, seems to change regularly # MD5 is flaky, seems to change regularly
#u'md5': u'2f32b1f7b80fdc5cb616efb4f387f8a3', # 'md5': '2f32b1f7b80fdc5cb616efb4f387f8a3',
u'info_dict': { u'info_dict': {
u"title": u"Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review", 'id': '20130811',
u"description": u"Melle en Steven hebben voor de review een week in de rechtbank doorbracht met Phoenix Wright: Ace Attorney - Dual Destinies.", 'ext': 'mp4',
'title': 'Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review',
'description': 'md5:632e61a9f97d700e83f43d77ddafb6a4',
} }
} }

View file

@ -5,9 +5,12 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
compat_urllib_parse, compat_urllib_parse,
compat_urllib_request,
ExtractorError, ExtractorError,
find_xpath_attr, find_xpath_attr,
fix_xml_ampersands, fix_xml_ampersands,
HEADRequest,
unescapeHTML,
url_basename, url_basename,
RegexNotFoundError, RegexNotFoundError,
) )
@ -18,6 +21,7 @@ def _media_xml_tag(tag):
class MTVServicesInfoExtractor(InfoExtractor): class MTVServicesInfoExtractor(InfoExtractor):
_MOBILE_TEMPLATE = None
@staticmethod @staticmethod
def _id_from_uri(uri): def _id_from_uri(uri):
return uri.split(':')[-1] return uri.split(':')[-1]
@ -39,9 +43,29 @@ class MTVServicesInfoExtractor(InfoExtractor):
else: else:
return thumb_node.attrib['url'] return thumb_node.attrib['url']
def _extract_video_formats(self, mdoc): def _extract_mobile_video_formats(self, mtvn_id):
if re.match(r'.*/error_country_block\.swf$', mdoc.find('.//src').text) is not None: webpage_url = self._MOBILE_TEMPLATE % mtvn_id
raise ExtractorError('This video is not available from your country.', expected=True) req = compat_urllib_request.Request(webpage_url)
# Otherwise we get a webpage that would execute some javascript
req.add_header('Youtubedl-user-agent', 'curl/7')
webpage = self._download_webpage(req, mtvn_id,
'Downloading mobile page')
metrics_url = unescapeHTML(self._search_regex(r'<a href="(http://metrics.+?)"', webpage, 'url'))
req = HEADRequest(metrics_url)
response = self._request_webpage(req, mtvn_id, 'Resolving url')
url = response.geturl()
# Transform the url to get the best quality:
url = re.sub(r'.+pxE=mp4', 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=0+_pxK=18639+_pxE=mp4', url, 1)
return [{'url': url,'ext': 'mp4'}]
def _extract_video_formats(self, mdoc, mtvn_id):
if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4)$', mdoc.find('.//src').text) is not None:
if mtvn_id is not None and self._MOBILE_TEMPLATE is not None:
self.to_screen('The normal version is not available from your '
'country, trying with the mobile version')
return self._extract_mobile_video_formats(mtvn_id)
raise ExtractorError('This video is not available from your country.',
expected=True)
formats = [] formats = []
for rendition in mdoc.findall('.//rendition'): for rendition in mdoc.findall('.//rendition'):
@ -94,9 +118,16 @@ class MTVServicesInfoExtractor(InfoExtractor):
raise ExtractorError('Could not find video title') raise ExtractorError('Could not find video title')
title = title.strip() title = title.strip()
# This a short id that's used in the webpage urls
mtvn_id = None
mtvn_id_node = find_xpath_attr(itemdoc, './/{http://search.yahoo.com/mrss/}category',
'scheme', 'urn:mtvn:id')
if mtvn_id_node is not None:
mtvn_id = mtvn_id_node.text
return { return {
'title': title, 'title': title,
'formats': self._extract_video_formats(mediagen_doc), 'formats': self._extract_video_formats(mediagen_doc, mtvn_id),
'id': video_id, 'id': video_id,
'thumbnail': self._get_thumbnail_url(uri, itemdoc), 'thumbnail': self._get_thumbnail_url(uri, itemdoc),
'description': description, 'description': description,

View file

@ -54,6 +54,7 @@ class SoundcloudIE(InfoExtractor):
'id': '47127627', 'id': '47127627',
'ext': 'mp3', 'ext': 'mp3',
'title': 'Goldrushed', 'title': 'Goldrushed',
'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com',
'uploader': 'The Royal Concept', 'uploader': 'The Royal Concept',
'upload_date': '20120521', 'upload_date': '20120521',
}, },

View file

@ -1,10 +1,15 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .mtv import MTVServicesInfoExtractor from .mtv import MTVServicesInfoExtractor
class SpikeIE(MTVServicesInfoExtractor): class SpikeIE(MTVServicesInfoExtractor):
_VALID_URL = r'https?://www\.spike\.com/(video-clips|episodes)/.+' _VALID_URL = r'''(?x)https?://
(www\.spike\.com/(video-clips|episodes)/.+|
m\.spike\.com/videos/video.rbml\?id=(?P<mobile_id>[^&]+))
'''
_TEST = { _TEST = {
'url': 'http://www.spike.com/video-clips/lhtu8m/auction-hunters-can-allen-ride-a-hundred-year-old-motorcycle', 'url': 'http://www.spike.com/video-clips/lhtu8m/auction-hunters-can-allen-ride-a-hundred-year-old-motorcycle',
'md5': '1a9265f32b0c375793d6c4ce45255256', 'md5': '1a9265f32b0c375793d6c4ce45255256',
@ -17,3 +22,11 @@ class SpikeIE(MTVServicesInfoExtractor):
} }
_FEED_URL = 'http://www.spike.com/feeds/mrss/' _FEED_URL = 'http://www.spike.com/feeds/mrss/'
_MOBILE_TEMPLATE = 'http://m.spike.com/videos/video.rbml?id=%s'
def _real_extract(self, url):
mobj = re.search(self._VALID_URL, url)
mobile_id = mobj.group('mobile_id')
if mobile_id is not None:
url = 'http://www.spike.com/video-clips/%s' % mobile_id
return super(SpikeIE, self)._real_extract(url)

View file

@ -1,22 +1,23 @@
from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from .internetvideoarchive import InternetVideoArchiveIE from .internetvideoarchive import InternetVideoArchiveIE
from ..utils import ( from ..utils import compat_urlparse
compat_urlparse,
)
class VideoDetectiveIE(InfoExtractor): class VideoDetectiveIE(InfoExtractor):
_VALID_URL = r'https?://www\.videodetective\.com/[^/]+/[^/]+/(?P<id>\d+)' _VALID_URL = r'https?://www\.videodetective\.com/[^/]+/[^/]+/(?P<id>\d+)'
_TEST = { _TEST = {
u'url': u'http://www.videodetective.com/movies/kick-ass-2/194487', 'url': 'http://www.videodetective.com/movies/kick-ass-2/194487',
u'file': u'194487.mp4', 'info_dict': {
u'info_dict': { 'id': '194487',
u'title': u'KICK-ASS 2', 'ext': 'mp4',
u'description': u'md5:65ba37ad619165afac7d432eaded6013', 'title': 'KICK-ASS 2',
u'duration': 135, 'description': 'md5:65ba37ad619165afac7d432eaded6013',
'duration': 135,
}, },
} }
@ -26,5 +27,4 @@ class VideoDetectiveIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
og_video = self._og_search_video_url(webpage) og_video = self._og_search_video_url(webpage)
query = compat_urlparse.urlparse(og_video).query query = compat_urlparse.urlparse(og_video).query
return self.url_result(InternetVideoArchiveIE._build_url(query), return self.url_result(InternetVideoArchiveIE._build_url(query), ie=InternetVideoArchiveIE.ie_key())
ie=InternetVideoArchiveIE.ie_key())

View file

@ -13,7 +13,7 @@ class VubeIE(InfoExtractor):
_TEST = { _TEST = {
'url': 'http://vube.com/Chiara+Grispo+Video+Channel/YL2qNPkqon', 'url': 'http://vube.com/Chiara+Grispo+Video+Channel/YL2qNPkqon',
'md5': 'f81dcf6d0448e3291f54380181695821', 'md5': 'db7aba89d4603dadd627e9d1973946fe',
'info_dict': { 'info_dict': {
'id': 'YL2qNPkqon', 'id': 'YL2qNPkqon',
'ext': 'mp4', 'ext': 'mp4',