Merge remote-tracking branch 'upstream/master'

Conflicts:
	youtube_dl/extractor/jeuxvideo.py
This commit is contained in:
Pierre Rudloff 2013-08-22 12:52:05 +02:00
commit 8d212e604a
17 changed files with 300 additions and 62 deletions

View File

@ -50,6 +50,7 @@ class TestAllURLsMatching(unittest.TestCase):
self.assertEqual(YoutubeIE()._extract_id('http://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc')
self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc')
self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc'), 'BaW_jenozKc')
self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch_popup?v=BaW_jenozKc'), 'BaW_jenozKc')
def test_no_duplicates(self):
ies = gen_extractors()

View File

@ -79,9 +79,13 @@ class FileDownloader(object):
rate = float(current) / dif
eta = int((float(total) - float(current)) / rate)
(eta_mins, eta_secs) = divmod(eta, 60)
if eta_mins > 99:
return '--:--'
return '%02d:%02d' % (eta_mins, eta_secs)
(eta_hours, eta_mins) = divmod(eta_mins, 60)
if eta_hours > 99:
return '--:--:--'
if eta_hours == 0:
return '%02d:%02d' % (eta_mins, eta_secs)
else:
return '%02d:%02d:%02d' % (eta_hours, eta_mins, eta_secs)
@staticmethod
def calc_speed(start, now, bytes):

View File

@ -51,13 +51,16 @@ from .myspass import MySpassIE
from .myvideo import MyVideoIE
from .nba import NBAIE
from .ooyala import OoyalaIE
from .pbs import PBSIE
from .photobucket import PhotobucketIE
from .pornotube import PornotubeIE
from .rbmaradio import RBMARadioIE
from .redtube import RedTubeIE
from .ringtv import RingTVIE
from .roxwel import RoxwelIE
from .rtlnow import RTLnowIE
from .sina import SinaIE
from .slashdot import SlashdotIE
from .soundcloud import SoundcloudIE, SoundcloudSetIE
from .spiegel import SpiegelIE
from .stanfordoc import StanfordOpenClassroomIE

View File

@ -4,6 +4,7 @@ import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse_urlparse,
determine_ext,
ExtractorError,
)
@ -12,7 +13,7 @@ from ..utils import (
class CollegeHumorIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$'
_TEST = {
_TESTS = [{
u'url': u'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
u'file': u'6902724.mp4',
u'md5': u'1264c12ad95dca142a9f0bf7968105a0',
@ -20,7 +21,16 @@ class CollegeHumorIE(InfoExtractor):
u'title': u'Comic-Con Cosplay Catastrophe',
u'description': u'Fans get creative this year at San Diego. Too creative. And yes, that\'s really Joss Whedon.',
},
}
},
{
u'url': u'http://www.collegehumor.com/video/3505939/font-conference',
u'file': u'3505939.mp4',
u'md5': u'c51ca16b82bb456a4397987791a835f5',
u'info_dict': {
u'title': u'Font Conference',
u'description': u'This video wasn\'t long enough, so we made it double-spaced.',
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@ -49,25 +59,29 @@ class CollegeHumorIE(InfoExtractor):
info['description'] = videoNode.findall('./description')[0].text
info['title'] = videoNode.findall('./caption')[0].text
info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
manifest_url = videoNode.findall('./file')[0].text
next_url = videoNode.findall('./file')[0].text
except IndexError:
raise ExtractorError(u'Invalid metadata XML file')
manifest_url += '?hdcore=2.10.3'
manifestXml = self._download_webpage(manifest_url, video_id,
u'Downloading XML manifest',
u'Unable to download video info XML')
if next_url.endswith(u'manifest.f4m'):
manifest_url = next_url + '?hdcore=2.10.3'
manifestXml = self._download_webpage(manifest_url, video_id,
u'Downloading XML manifest',
u'Unable to download video info XML')
adoc = xml.etree.ElementTree.fromstring(manifestXml)
try:
media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0]
node_id = media_node.attrib['url']
video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
except IndexError as err:
raise ExtractorError(u'Invalid manifest file')
adoc = xml.etree.ElementTree.fromstring(manifestXml)
try:
media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0]
node_id = media_node.attrib['url']
video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
except IndexError as err:
raise ExtractorError(u'Invalid manifest file')
url_pr = compat_urllib_parse_urlparse(info['thumbnail'])
info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','')
info['ext'] = 'mp4'
else:
# Old-style direct links
info['url'] = next_url
info['ext'] = determine_ext(info['url'])
url_pr = compat_urllib_parse_urlparse(info['thumbnail'])
info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','')
info['ext'] = 'mp4'
return [info]
return info

View File

@ -77,7 +77,13 @@ class InfoExtractor(object):
@classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
return re.match(cls._VALID_URL, url) is not None
# This does not use has/getattr intentionally - we want to know whether
# we have cached the regexp for *this* class, whereas getattr would also
# match the superclass
if '_VALID_URL_RE' not in cls.__dict__:
cls._VALID_URL_RE = re.compile(cls._VALID_URL)
return cls._VALID_URL_RE.match(url) is not None
@classmethod
def working(cls):

View File

@ -21,17 +21,14 @@ class FunnyOrDieIE(InfoExtractor):
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
video_url = self._html_search_regex(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"',
video_url = self._search_regex(r'type: "video/mp4", src: "(.*?)"',
webpage, u'video URL', flags=re.DOTALL)
title = self._html_search_regex((r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>",
r'<title>(?P<title>[^<]+?)</title>'), webpage, 'title', flags=re.DOTALL)
info = {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': title,
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
}
return [info]

View File

@ -107,8 +107,13 @@ class GenericIE(InfoExtractor):
return new_url
def _real_extract(self, url):
new_url = self._test_redirect(url)
if new_url: return [self.url_result(new_url)]
try:
new_url = self._test_redirect(url)
if new_url:
return [self.url_result(new_url)]
except compat_urllib_error.HTTPError:
# This may be a stupid server that doesn't like HEAD, our UA, or so
pass
video_id = url.split('/')[-1]
try:
@ -144,6 +149,9 @@ class GenericIE(InfoExtractor):
# We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
if m_video_type is not None:
mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
if mobj is None:
# HTML5 video
mobj = re.search(r'<video[^<]*>.*?<source .*?src="([^"]+)"', webpage, flags=re.DOTALL)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)

View File

@ -1,11 +1,24 @@
# coding: utf-8
import json
import re
import xml.etree.ElementTree
from .common import InfoExtractor
class JeuxVideoIE(InfoExtractor):
_VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
_TEST = {
u'url': u'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
u'file': u'5182.mp4',
u'md5': u'e0fdb0cd3ce98713ef9c1e1e025779d0',
u'info_dict': {
u'title': u'GC 2013 : Tearaway nous présente ses papiers d\'identité',
u'description': u'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
title = re.match(self._VALID_URL, url).group(1)
@ -18,16 +31,18 @@ class JeuxVideoIE(InfoExtractor):
xml_config = self._download_webpage(xml_link, title,
'Downloading XML config')
config = xml.etree.ElementTree.fromstring(xml_config.encode('utf-8'))
info = re.search(r'<format\.json>(.*?)</format\.json>',
xml_config, re.MULTILINE|re.DOTALL).group(1)
info = json.loads(info)['versions'][0]
video_url = 'http://video720.jeuxvideo.com/' + info['file']
track_info = {'id':id,
'title' : title,
'ext' : 'mp4',
'url' : video_url
}
return [track_info]
return {'id': id,
'title' : config.find('titre_video').text,
'ext' : 'mp4',
'url' : video_url,
'description': self._og_search_description(webpage),
'thumbnail': config.find('image').text,
}

View File

@ -0,0 +1,34 @@
import re
import json
from .common import InfoExtractor
class PBSIE(InfoExtractor):
_VALID_URL = r'https?://video.pbs.org/video/(?P<id>\d+)/?'
_TEST = {
u'url': u'http://video.pbs.org/video/2365006249/',
u'file': u'2365006249.mp4',
u'md5': 'ce1888486f0908d555a8093cac9a7362',
u'info_dict': {
u'title': u'A More Perfect Union',
u'description': u'md5:ba0c207295339c8d6eced00b7c363c6a',
u'duration': 3190,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
info_page = self._download_webpage(info_url, video_id)
info =json.loads(info_page)
return {'id': video_id,
'title': info['title'],
'url': info['alternate_encoding']['url'],
'ext': 'mp4',
'description': info['program'].get('description'),
'thumbnail': info.get('image_url'),
'duration': info.get('duration'),
}

View File

@ -0,0 +1,113 @@
# encoding: utf-8
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
ExtractorError,
)
class RTLnowIE(InfoExtractor):
"""Information Extractor for RTLnow, RTL2now and VOXnow"""
_VALID_URL = r'(?:http://)?(?P<url>(?P<base_url>rtl(?:(?P<is_rtl2>2)|-)now\.rtl(?(is_rtl2)2|)\.de/|(?:www\.)?voxnow\.de/)[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)'
_TESTS = [{
u'url': u'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1',
u'file': u'90419.flv',
u'info_dict': {
u'upload_date': u'20070416',
u'title': u'Ahornallee - Folge 1 - Der Einzug',
u'description': u'Folge 1 - Der Einzug',
},
u'params': {
u'skip_download': True,
},
u'skip': u'Only works from Germany',
},
{
u'url': u'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5',
u'file': u'69756.flv',
u'info_dict': {
u'upload_date': u'20120519',
u'title': u'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit...',
u'description': u'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.',
u'thumbnail': u'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg',
},
u'params': {
u'skip_download': True,
},
u'skip': u'Only works from Germany',
},
{
u'url': u'www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17',
u'file': u'13883.flv',
u'info_dict': {
u'upload_date': u'20090627',
u'title': u'Voxtours - Südafrika-Reporter II',
u'description': u'Südafrika-Reporter II',
},
u'params': {
u'skip_download': True,
},
}]
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)
webpage_url = u'http://' + mobj.group('url')
video_page_url = u'http://' + mobj.group('base_url')
video_id = mobj.group(u'video_id')
webpage = self._download_webpage(webpage_url, video_id)
note_m = re.search(r'''(?sx)
<div[ ]style="margin-left:[ ]20px;[ ]font-size:[ ]13px;">(.*?)
<div[ ]id="playerteaser">''', webpage)
if note_m:
msg = clean_html(note_m.group(1))
raise ExtractorError(msg)
video_title = self._html_search_regex(r'<title>(?P<title>[^<]+)</title>',
webpage, u'title')
playerdata_url = self._html_search_regex(r'\'playerdata\': \'(?P<playerdata_url>[^\']+)\'',
webpage, u'playerdata_url')
playerdata = self._download_webpage(playerdata_url, video_id)
mobj = re.search(r'<title><!\[CDATA\[(?P<description>.+?)\s+- (?:Sendung )?vom (?P<upload_date_d>[0-9]{2})\.(?P<upload_date_m>[0-9]{2})\.(?:(?P<upload_date_Y>[0-9]{4})|(?P<upload_date_y>[0-9]{2})) [0-9]{2}:[0-9]{2} Uhr\]\]></title>', playerdata)
if mobj:
video_description = mobj.group(u'description')
if mobj.group('upload_date_Y'):
video_upload_date = mobj.group('upload_date_Y')
else:
video_upload_date = u'20' + mobj.group('upload_date_y')
video_upload_date += mobj.group('upload_date_m')+mobj.group('upload_date_d')
else:
video_description = None
video_upload_date = None
self._downloader.report_warning(u'Unable to extract description and upload date')
# Thumbnail: not every video has an thumbnail
mobj = re.search(r'<meta property="og:image" content="(?P<thumbnail>[^"]+)">', webpage)
if mobj:
video_thumbnail = mobj.group(u'thumbnail')
else:
video_thumbnail = None
mobj = re.search(r'<filename [^>]+><!\[CDATA\[(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>[^\]]+)\]\]></filename>', playerdata)
if mobj is None:
raise ExtractorError(u'Unable to extract media URL')
video_url = mobj.group(u'url')
video_play_path = u'mp4:' + mobj.group(u'play_path')
video_player_url = video_page_url + u'includes/vodplayer.swf'
return [{
'id': video_id,
'url': video_url,
'play_path': video_play_path,
'page_url': video_page_url,
'player_url': video_player_url,
'ext': 'flv',
'title': video_title,
'description': video_description,
'upload_date': video_upload_date,
'thumbnail': video_thumbnail,
}]

View File

@ -0,0 +1,23 @@
import re
from .common import InfoExtractor
class SlashdotIE(InfoExtractor):
_VALID_URL = r'https?://tv.slashdot.org/video/\?embed=(?P<id>.*?)(&|$)'
_TEST = {
u'url': u'http://tv.slashdot.org/video/?embed=JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz',
u'file': u'JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz.mp4',
u'md5': u'd2222e7a4a4c1541b3e0cf732fb26735',
u'info_dict': {
u'title': u' Meet the Stampede Supercomputing Cluster\'s Administrator',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
ooyala_url = self._search_regex(r'<script src="(.*?)"', webpage, 'ooyala url')
return self.url_result(ooyala_url, 'Ooyala')

View File

@ -4,6 +4,7 @@ import re
from .common import InfoExtractor
from ..utils import (
compat_str,
compat_urlparse,
ExtractorError,
unified_strdate,
@ -22,6 +23,7 @@ class SoundcloudIE(InfoExtractor):
_VALID_URL = r'''^(?:https?://)?
(?:(?:(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)/?(?:[?].*)?$)
|(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+))
|(?P<widget>w.soundcloud.com/player/?.*?url=.*)
)
'''
IE_NAME = u'soundcloud'
@ -79,6 +81,9 @@ class SoundcloudIE(InfoExtractor):
if track_id is not None:
info_json_url = 'http://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID
full_title = track_id
elif mobj.group('widget'):
query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
return self.url_result(query['url'][0], ie='Soundcloud')
else:
# extract uploader (which is in the url)
uploader = mobj.group(1)

View File

@ -5,13 +5,13 @@ from .common import InfoExtractor
class StatigramIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?statigr\.am/p/([^/]+)'
_TEST = {
u'url': u'http://statigr.am/p/484091715184808010_284179915',
u'file': u'484091715184808010_284179915.mp4',
u'md5': u'deda4ff333abe2e118740321e992605b',
u'url': u'http://statigr.am/p/522207370455279102_24101272',
u'file': u'522207370455279102_24101272.mp4',
u'md5': u'6eb93b882a3ded7c378ee1d6884b1814',
u'info_dict': {
u"uploader_id": u"videoseconds",
u"title": u"Instagram photo by @videoseconds"
}
u'uploader_id': u'aguynamedpatrick',
u'title': u'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
},
}
def _real_extract(self, url):

View File

@ -11,7 +11,7 @@ class VevoIE(InfoExtractor):
Accepts urls from vevo.com or in the format 'vevo:{id}'
(currently used by MTVIE)
"""
_VALID_URL = r'((http://www.vevo.com/watch/.*?/.*?/)|(vevo:))(?P<id>.*)$'
_VALID_URL = r'((http://www.vevo.com/watch/.*?/.*?/)|(vevo:))(?P<id>.*?)(\?|$)'
_TEST = {
u'url': u'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280',
u'file': u'GB1101300280.mp4',

View File

@ -20,18 +20,31 @@ class VimeoIE(InfoExtractor):
_VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)(?:[?].*)?$'
_NETRC_MACHINE = 'vimeo'
IE_NAME = u'vimeo'
_TEST = {
u'url': u'http://vimeo.com/56015672',
u'file': u'56015672.mp4',
u'md5': u'8879b6cc097e987f02484baf890129e5',
u'info_dict': {
u"upload_date": u"20121220",
u"description": u"This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
u"uploader_id": u"user7108434",
u"uploader": u"Filippo Valsorda",
u"title": u"youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550"
}
}
_TESTS = [
{
u'url': u'http://vimeo.com/56015672',
u'file': u'56015672.mp4',
u'md5': u'8879b6cc097e987f02484baf890129e5',
u'info_dict': {
u"upload_date": u"20121220",
u"description": u"This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
u"uploader_id": u"user7108434",
u"uploader": u"Filippo Valsorda",
u"title": u"youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
},
},
{
u'url': u'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
u'file': u'68093876.mp4',
u'md5': u'3b5ca6aa22b60dfeeadf50b72e44ed82',
u'note': u'Vimeo Pro video (#1197)',
u'info_dict': {
u'uploader_id': u'openstreetmapus',
u'uploader': u'OpenStreetMap US',
u'title': u'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
},
},
]
def _login(self):
(username, password) = self._get_login_info()
@ -83,7 +96,9 @@ class VimeoIE(InfoExtractor):
video_id = mobj.group('id')
if not mobj.group('proto'):
url = 'https://' + url
if mobj.group('direct_link') or mobj.group('pro'):
elif mobj.group('pro'):
url = 'http://player.vimeo.com/video/' + video_id
elif mobj.group('direct_link'):
url = 'https://vimeo.com/' + video_id
# Retrieve video webpage to extract further information

View File

@ -141,7 +141,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
(?: # the various things that can precede the ID:
(?:(?:v|embed|e)/) # v/ or embed/ or e/
|(?: # or the v= param in all its forms
(?:watch|movie(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
(?:(?:watch|movie)(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
(?:\?|\#!?) # the params delimiter ? or # or #!
(?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx)
v=
@ -255,7 +255,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
u"upload_date": u"20120506",
u"title": u"Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]",
u"description": u"md5:b085c9804f5ab69f4adea963a2dceb3c",
u"uploader": u"IconaPop",
u"uploader": u"Icona Pop",
u"uploader_id": u"IconaPop"
}
},

View File

@ -1,2 +1,2 @@
__version__ = '2013.08.17'
__version__ = '2013.08.21'