from youtube_dl.extractor import (
- YoutubeUserIE,
YoutubePlaylistIE,
YoutubeIE,
YoutubeChannelIE,
self.assertEqual(len(entries), 25)
self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0')
- def test_youtube_channel(self):
- dl = FakeYDL()
- ie = YoutubeChannelIE(dl)
- #test paginated channel
- result = ie.extract('https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w')
- self.assertTrue(len(result['entries']) > 90)
- #test autogenerated channel
- result = ie.extract('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
- self.assertTrue(len(result['entries']) >= 18)
-
- def test_youtube_user(self):
- dl = FakeYDL()
- ie = YoutubeUserIE(dl)
- result = ie.extract('https://www.youtube.com/user/TheLinuxFoundation')
- self.assertTrue(len(result['entries']) >= 320)
-
- def test_youtube_show(self):
- dl = FakeYDL()
- ie = YoutubeShowIE(dl)
- result = ie.extract('http://www.youtube.com/show/airdisasters')
- self.assertTrue(len(result) >= 3)
-
def test_youtube_mix(self):
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
entries = result['entries']
self.assertEqual(len(entries), 100)
- def test_youtube_toplist(self):
- dl = FakeYDL()
- ie = YoutubeTopListIE(dl)
- result = ie.extract('yttoplist:music:Trending')
- entries = result['entries']
- self.assertTrue(len(entries) >= 5)
-
- def test_youtube_search_url(self):
- dl = FakeYDL()
- ie = YoutubeSearchURLIE(dl)
- result = ie.extract('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video')
- entries = result['entries']
- self.assertIsPlaylist(result)
- self.assertEqual(result['title'], 'youtube-dl test video')
- self.assertTrue(len(entries) >= 5)
-
if __name__ == '__main__':
unittest.main()
# urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991)
# To work around aforementioned issue we will replace request's original URL with
# percent-encoded one
- url = req if isinstance(req, compat_str) else req.get_full_url()
+ req_is_string = isinstance(req, basestring if sys.version_info < (3, 0) else compat_str)
+ url = req if req_is_string else req.get_full_url()
url_escaped = escape_url(url)
# Substitute URL if any change after escaping
if url != url_escaped:
- if isinstance(req, compat_str):
+ if req_is_string:
req = url_escaped
else:
req = compat_urllib_request.Request(
'Hari Padmanaban',
'Carlos Ramos',
'5moufl',
+ 'lenaten',
)
__license__ = 'Public Domain'
from .common import FileDownloader
from .hls import HlsFD
+from .hls import NativeHlsFD
from .http import HttpFD
from .mplayer import MplayerFD
from .rtmp import RtmpFD
if url.startswith('rtmp'):
return RtmpFD
+ if protocol == 'm3u8_native':
+ return NativeHlsFD
if (protocol == 'm3u8') or (protocol is None and determine_ext(url) == 'm3u8'):
return HlsFD
if url.startswith('mms') or url.startswith('rtsp'):
Subclasses of this one must re-define the real_download method.
"""
+ _TEST_FILE_SIZE = 10241
params = None
def __init__(self, ydl, params):
+from __future__ import unicode_literals
+
import os
+import re
import subprocess
from .common import FileDownloader
from ..utils import (
+ compat_urlparse,
+ compat_urllib_request,
check_executable,
encodeFilename,
)
self.to_stderr(u"\n")
self.report_error(u'%s exited with code %d' % (program, retval))
return False
+
+
+class NativeHlsFD(FileDownloader):
+ """ A more limited implementation that does not require ffmpeg """
+
+ def real_download(self, filename, info_dict):
+ url = info_dict['url']
+ self.report_destination(filename)
+ tmpfilename = self.temp_name(filename)
+
+ self.to_screen(
+ '[hlsnative] %s: Downloading m3u8 manifest' % info_dict['id'])
+ data = self.ydl.urlopen(url).read()
+ s = data.decode('utf-8', 'ignore')
+ segment_urls = []
+ for line in s.splitlines():
+ line = line.strip()
+ if line and not line.startswith('#'):
+ segment_url = (
+ line
+ if re.match(r'^https?://', line)
+ else compat_urlparse.urljoin(url, line))
+ segment_urls.append(segment_url)
+
+ is_test = self.params.get('test', False)
+ remaining_bytes = self._TEST_FILE_SIZE if is_test else None
+ byte_counter = 0
+ with open(tmpfilename, 'wb') as outf:
+ for i, segurl in enumerate(segment_urls):
+ self.to_screen(
+ '[hlsnative] %s: Downloading segment %d / %d' %
+ (info_dict['id'], i + 1, len(segment_urls)))
+ seg_req = compat_urllib_request.Request(segurl)
+ if remaining_bytes is not None:
+ seg_req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1))
+
+ segment = self.ydl.urlopen(seg_req).read()
+ if remaining_bytes is not None:
+ segment = segment[:remaining_bytes]
+ remaining_bytes -= len(segment)
+ outf.write(segment)
+ byte_counter += len(segment)
+ if remaining_bytes is not None and remaining_bytes <= 0:
+ break
+
+ self._hook_progress({
+ 'downloaded_bytes': byte_counter,
+ 'total_bytes': byte_counter,
+ 'filename': filename,
+ 'status': 'finished',
+ })
+ self.try_rename(tmpfilename, filename)
+ return True
+
class HttpFD(FileDownloader):
- _TEST_FILE_SIZE = 10241
-
def real_download(self, filename, info_dict):
url = info_dict['url']
tmpfilename = self.temp_name(filename)
from .ntv import NTVIE
from .nytimes import NYTimesIE
from .nuvid import NuvidIE
+from .oktoberfesttv import OktoberfestTVIE
from .ooyala import OoyalaIE
from .orf import (
ORFTVthekIE,
from .spiegel import SpiegelIE, SpiegelArticleIE
from .spiegeltv import SpiegeltvIE
from .spike import SpikeIE
+from .sport5 import Sport5IE
from .sportdeutschland import SportDeutschlandIE
from .stanfordoc import StanfordOpenClassroomIE
from .steam import SteamIE
YahooNewsIE,
YahooSearchIE,
)
+from .ynet import YnetIE
from .youjizz import YouJizzIE
from .youku import YoukuIE
from .youporn import YouPornIE
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
urls_info_json = self._search_regex(
title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
description = self._html_search_regex(
- r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
+ r'<div class="description"[^>]*>([^<]+)</div>', webpage, 'description', fatal=False)
thumbnail = self._html_search_regex(
r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False)
r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage)
duration = parse_duration(self._search_regex(
- r'<b>Duration:</b> (\d+:\d+)', webpage, 'duration', fatal=False))
+ r'<b>Duration:</b> (?:<q itemprop="duration">)?(\d+:\d+)', webpage, 'duration', fatal=False))
view_count = int_or_none(self._html_search_regex(
r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False))
from __future__ import unicode_literals
import base64
+import datetime
import hashlib
import json
import netrc
compat_http_client,
compat_urllib_error,
compat_urllib_parse_urlparse,
+ compat_urlparse,
compat_str,
clean_html,
cls._VALID_URL_RE = re.compile(cls._VALID_URL)
return cls._VALID_URL_RE.match(url) is not None
+ @classmethod
+ def _match_id(cls, url):
+ if '_VALID_URL_RE' not in cls.__dict__:
+ cls._VALID_URL_RE = re.compile(cls._VALID_URL)
+ m = cls._VALID_URL_RE.match(url)
+ assert m
+ return m.group('id')
+
@classmethod
def working(cls):
"""Getter method for _WORKING."""
return formats
- def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None):
+ def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
+ entry_protocol='m3u8', preference=None):
+
formats = [{
'format_id': 'm3u8-meta',
'url': m3u8_url,
'format_note': 'Quality selection URL',
}]
+ format_url = lambda u: (
+ u
+ if re.match(r'^https?://', u)
+ else compat_urlparse.urljoin(m3u8_url, u))
+
m3u8_doc = self._download_webpage(m3u8_url, video_id)
last_info = None
kv_rex = re.compile(
continue
else:
if last_info is None:
- formats.append({'url': line})
+ formats.append({'url': format_url(line)})
continue
tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000)
f = {
'format_id': 'm3u8-%d' % (tbr if tbr else len(formats)),
- 'url': line.strip(),
+ 'url': format_url(line.strip()),
'tbr': tbr,
'ext': ext,
+ 'protocol': entry_protocol,
+ 'preference': preference,
}
codecs = last_info.get('CODECS')
if codecs:
self._sort_formats(formats)
return formats
+ def _live_title(self, name):
+ """ Generate the title for a live video """
+ now = datetime.datetime.now()
+ now_str = now.strftime("%Y-%m-%d %H:%M")
+ return name + ' ' + now_str
+
class SearchInfoExtractor(InfoExtractor):
"""
from hashlib import sha1
from math import pow, sqrt, floor
-from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
from ..utils import (
ExtractorError,
compat_urllib_parse,
)
-class CrunchyrollIE(InfoExtractor):
+class CrunchyrollIE(SubtitlesInfoExtractor):
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
_TEST = {
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
else:
subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)
+ if self._downloader.params.get('listsubtitles', False):
+ self._list_available_subtitles(video_id, subtitles)
+ return
+
return {
'id': video_id,
'title': video_title,
# encoding: utf-8
+from __future__ import unicode_literals
+
import re
from .common import InfoExtractor
class EitbIE(InfoExtractor):
- IE_NAME = u'eitb.tv'
+ IE_NAME = 'eitb.tv'
_VALID_URL = r'https?://www\.eitb\.tv/(eu/bideoa|es/video)/[^/]+/(?P<playlist_id>\d+)/(?P<chapter_id>\d+)'
_TEST = {
- u'add_ie': ['Brightcove'],
- u'url': u'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/',
- u'md5': u'edf4436247185adee3ea18ce64c47998',
- u'info_dict': {
- u'id': u'2743577154001',
- u'ext': u'mp4',
- u'title': u'60 minutos (Lasa y Zabala, 30 años)',
+ 'add_ie': ['Brightcove'],
+ 'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/',
+ 'md5': 'edf4436247185adee3ea18ce64c47998',
+ 'info_dict': {
+ 'id': '2743577154001',
+ 'ext': 'mp4',
+ 'title': '60 minutos (Lasa y Zabala, 30 años)',
# All videos from eitb has this description in the brightcove info
- u'description': u'.',
- u'uploader': u'Euskal Telebista',
+ 'description': '.',
+ 'uploader': 'Euskal Telebista',
},
}
webpage = self._download_webpage(url, chapter_id)
bc_url = BrightcoveIE._extract_brightcove_url(webpage)
if bc_url is None:
- raise ExtractorError(u'Could not extract the Brightcove url')
+ raise ExtractorError('Could not extract the Brightcove url')
# The BrightcoveExperience object doesn't contain the video id, we set
# it manually
bc_url += '&%40videoPlayer={0}'.format(chapter_id)
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urllib_parse,
+ str_to_int,
)
'ext': 'mp4',
'title': 'Music Video 14 british euro brit european cumshots swallow',
'uploader': 'unknown',
+ 'view_count': int,
'age_limit': 18,
}
}, {
video_title = self._html_search_regex(
r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
uploader = self._html_search_regex(
- r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, 'uploader',
- fatal=False)
+ r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>',
+ webpage, 'uploader', fatal=False)
+ view_count = str_to_int(self._html_search_regex(
+ r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
+ webpage, 'view count', fatal=False))
+
video_url = compat_urllib_parse.unquote(self._html_search_regex(
r'video_url=(.+?)&', webpage, 'video_url'))
path = compat_urllib_parse_urlparse(video_url).path
'id': video_id,
'title': video_title,
'uploader': uploader,
+ 'view_count': view_count,
'url': video_url,
'format': format,
'format_id': format,
class FlickrIE(InfoExtractor):
- """Information Extractor for Flickr videos"""
- _VALID_URL = r'(?:https?://)?(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
+ _VALID_URL = r'https?://(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
_TEST = {
'url': 'http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/',
- 'file': '5645318632.mp4',
'md5': '6fdc01adbc89d72fc9c4f15b4a4ba87b',
'info_dict': {
+ 'id': '5645318632',
+ 'ext': 'mp4',
"description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.",
"uploader_id": "forestwander-nature-pictures",
"title": "Dark Hollow Waterfalls"
raise ExtractorError('Unable to extract video url')
video_url = mobj.group(1) + unescapeHTML(mobj.group(2))
- return [{
- 'id': video_id,
- 'url': video_url,
- 'ext': 'mp4',
- 'title': self._og_search_title(webpage),
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
- 'thumbnail': self._og_search_thumbnail(webpage),
+ 'thumbnail': self._og_search_thumbnail(webpage),
'uploader_id': video_uploader_id,
- }]
+ }
'thumbnail': 're:^https?://.*\.jpg$',
},
},
+ # Wistia embed
+ {
+ 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
+ 'md5': '8788b683c777a5cf25621eaf286d0c23',
+ 'info_dict': {
+ 'id': '1cfaf6b7ea',
+ 'ext': 'mov',
+ 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
+ 'duration': 643.0,
+ 'filesize': 182808282,
+ 'uploader': 'education-portal.com',
+ },
+ },
]
def report_download_webpage(self, video_id):
# Helper method
def _playlist_from_matches(matches, getter, ie=None):
- urlrs = orderedSet(self.url_result(getter(m), ie) for m in matches)
+ urlrs = orderedSet(
+ self.url_result(self._proto_relative_url(getter(m)), ie)
+ for m in matches)
return self.playlist_result(
urlrs, playlist_id=video_id, playlist_title=video_title)
)
(["\'])
(?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
- (?:embed|v)/.+?)
+ (?:embed|v|p)/.+?)
\1''', webpage)
if matches:
return _playlist_from_matches(
- matches, lambda m: unescapeHTML(m[1]), ie='Youtube')
+ matches, lambda m: unescapeHTML(m[1]))
# Look for embedded Dailymotion player
matches = re.findall(
'title': video_title,
'id': video_id,
}
+ match = re.search(r'(?:id=["\']wistia_|data-wistiaid=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
+ if match:
+ return {
+ '_type': 'url_transparent',
+ 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
+ 'ie_key': 'Wistia',
+ 'uploader': video_uploader,
+ 'title': video_title,
+ 'id': match.group('id')
+ }
# Look for embedded blip.tv player
mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
# coding: utf-8
from __future__ import unicode_literals
-import datetime
import json
from .common import InfoExtractor
display_id = 'live'
webpage = self._download_webpage(url, display_id)
- now = datetime.datetime.now()
- now_str = now.strftime("%Y-%m-%d %H:%M")
- title = self._og_search_title(webpage) + ' ' + now_str
+ title = self._live_title(self._og_search_title(webpage))
data_js = self._search_regex(
r'(?s)\nplaylist:\s*(\[.*?}\]),related:',
_PLAYER_CONFIG_URL = 'http://www.nfl.com/static/content/static/config/video/config.json'
_TEST = {
'url': 'http://www.nfl.com/videos/nfl-game-highlights/0ap3000000398478/Week-3-Redskins-vs-Eagles-highlights',
- 'skip_download': True, # md5 sum fluctuates
+ # 'md5': '5eb8c40a727dda106d510e5d6ffa79e5', # md5 checksum fluctuates
'info_dict': {
'id': '0ap3000000398478',
'ext': 'mp4',
--- /dev/null
+# encoding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class OktoberfestTVIE(InfoExtractor):
+ _VALID_URL = r'https?://www\.oktoberfest-tv\.de/[^/]+/[^/]+/video/(?P<id>[^/?#]+)'
+
+ _TEST = {
+ 'url': 'http://www.oktoberfest-tv.de/de/kameras/video/hb-zelt',
+ 'info_dict': {
+ 'id': 'hb-zelt',
+ 'ext': 'mp4',
+ 'title': 're:^Live-Kamera: Hofbräuzelt [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'is_live': True,
+ },
+ 'params': {
+ 'skip_download': True,
+ }
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+
+ title = self._live_title(self._html_search_regex(
+ r'<h1><strong>.*?</strong>(.*?)</h1>', webpage, 'title'))
+
+ clip = self._search_regex(
+ r"clip:\s*\{\s*url:\s*'([^']+)'", webpage, 'clip')
+ ncurl = self._search_regex(
+ r"netConnectionUrl:\s*'([^']+)'", webpage, 'rtmp base')
+ video_url = ncurl + clip
+ thumbnail = self._search_regex(
+ r"canvas:\s*\{\s*backgroundImage:\s*'url\(([^)]+)\)'", webpage,
+ 'thumbnail', fatal=False)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'is_live': True,
+ 'thumbnail': thumbnail,
+ }
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class Sport5IE(InfoExtractor):
+ _VALID_URL = r'http://(?:www|vod)?\.sport5\.co\.il/.*\b(?:Vi|docID)=(?P<id>\d+)'
+ _TESTS = [
+ {
+ 'url': 'http://vod.sport5.co.il/?Vc=147&Vi=176331&Page=1',
+ 'info_dict': {
+ 'id': 's5-Y59xx1-GUh2',
+ 'ext': 'mp4',
+ 'title': 'ולנסיה-קורדובה 0:3',
+ 'description': 'אלקאסר, גאייה ופגולי סידרו לקבוצה של נונו ניצחון על קורדובה ואת המקום הראשון בליגה',
+ 'duration': 228,
+ 'categories': list,
+ },
+ 'skip': 'Blocked outside of Israel',
+ }, {
+ 'url': 'http://www.sport5.co.il/articles.aspx?FolderID=3075&docID=176372&lang=HE',
+ 'info_dict': {
+ 'id': 's5-SiXxx1-hKh2',
+ 'ext': 'mp4',
+ 'title': 'GOALS_CELTIC_270914.mp4',
+ 'description': '',
+ 'duration': 87,
+ 'categories': list,
+ },
+ 'skip': 'Blocked outside of Israel',
+ }
+ ]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ media_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, media_id)
+
+ video_id = self._html_search_regex('clipId=([\w-]+)', webpage, 'video id')
+
+ metadata = self._download_xml(
+ 'http://sport5-metadata-rr-d.nsacdn.com/vod/vod/%s/HDS/metadata.xml' % video_id,
+ video_id)
+
+ error = metadata.find('./Error')
+ if error is not None:
+ raise ExtractorError(
+ '%s returned error: %s - %s' % (
+ self.IE_NAME,
+ error.find('./Name').text,
+ error.find('./Description').text),
+ expected=True)
+
+ title = metadata.find('./Title').text
+ description = metadata.find('./Description').text
+ duration = int(metadata.find('./Duration').text)
+
+ posters_el = metadata.find('./PosterLinks')
+ thumbnails = [{
+ 'url': thumbnail.text,
+ 'width': int(thumbnail.get('width')),
+ 'height': int(thumbnail.get('height')),
+ } for thumbnail in posters_el.findall('./PosterIMG')] if posters_el is not None else []
+
+ categories_el = metadata.find('./Categories')
+ categories = [
+ cat.get('name') for cat in categories_el.findall('./Category')
+ ] if categories_el is not None else []
+
+ formats = [{
+ 'url': fmt.text,
+ 'ext': 'mp4',
+ 'vbr': int(fmt.get('bitrate')),
+ 'width': int(fmt.get('width')),
+ 'height': int(fmt.get('height')),
+ } for fmt in metadata.findall('./PlaybackLinks/FileURL')]
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnails': thumbnails,
+ 'duration': duration,
+ 'categories': categories,
+ 'formats': formats,
+ }
\ No newline at end of file
'md5': '99f65c0c9ef9b682b97313e052734c3f',
'info_dict': {
'id': '249bb972c2',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Смях! Чудо - чист за секунди - Скрита камера',
},
}
return {
'id': video_id,
'url': final_url,
- 'ext': 'flv',
'title': title,
'thumbnail': thumbnail_url,
}
from .common import InfoExtractor
from ..utils import (
compat_HTTPError,
+ compat_urllib_request,
ExtractorError,
)
_TESTS = [{
'url': 'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280',
- "md5": "06bea460acb744eab74a9d7dcb4bfd61",
+ "md5": "95ee28ee45e70130e3ab02b0f579ae23",
'info_dict': {
'id': 'GB1101300280',
'ext': 'mp4',
}, {
'note': 'v3 SMIL format',
'url': 'http://www.vevo.com/watch/cassadee-pope/i-wish-i-could-break-your-heart/USUV71302923',
- 'md5': '893ec0e0d4426a1d96c01de8f2bdff58',
+ 'md5': 'f6ab09b034f8c22969020b042e5ac7fc',
'info_dict': {
'id': 'USUV71302923',
'ext': 'mp4',
}]
_SMIL_BASE_URL = 'http://smil.lvl3.vevo.com/'
+ def _real_initialize(self):
+ req = compat_urllib_request.Request(
+ 'http://www.vevo.com/auth', data=b'')
+ webpage = self._download_webpage(
+ req, None,
+ note='Retrieving oauth token',
+ errnote='Unable to retrieve oauth token',
+ fatal=False)
+ if webpage is False:
+ self._oauth_token = None
+ else:
+ self._oauth_token = self._search_regex(
+ r'access_token":\s*"([^"]+)"',
+ webpage, 'access token', fatal=False)
+
def _formats_from_json(self, video_info):
last_version = {'version': -1}
for version in video_info['videoVersions']:
})
return formats
+ def _download_api_formats(self, video_id):
+ if not self._oauth_token:
+ self._downloader.report_warning(
+ 'No oauth token available, skipping API HLS download')
+ return []
+
+ api_url = 'https://apiv2.vevo.com/video/%s/streams/hls?token=%s' % (
+ video_id, self._oauth_token)
+ api_data = self._download_json(
+ api_url, video_id,
+ note='Downloading HLS formats',
+ errnote='Failed to download HLS format list', fatal=False)
+ if api_data is None:
+ return []
+
+ m3u8_url = api_data[0]['url']
+ return self._extract_m3u8_formats(
+ m3u8_url, video_id, entry_protocol='m3u8_native', ext='mp4',
+ preference=0)
+
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
else:
age_limit = None
- # Download SMIL
- smil_blocks = sorted((
- f for f in video_info['videoVersions']
- if f['sourceType'] == 13),
- key=lambda f: f['version'])
-
- smil_url = '%s/Video/V2/VFILE/%s/%sr.smil' % (
- self._SMIL_BASE_URL, video_id, video_id.lower())
- if smil_blocks:
- smil_url_m = self._search_regex(
- r'url="([^"]+)"', smil_blocks[-1]['data'], 'SMIL URL',
- fatal=False)
- if smil_url_m is not None:
- smil_url = smil_url_m
-
- try:
- smil_xml = self._download_webpage(smil_url, video_id,
- 'Downloading SMIL info')
- formats.extend(self._formats_from_smil(smil_xml))
- except ExtractorError as ee:
- if not isinstance(ee.cause, compat_HTTPError):
- raise
- self._downloader.report_warning(
- 'Cannot download SMIL information, falling back to JSON ..')
+ # Download via HLS API
+ formats.extend(self._download_api_formats(video_id))
self._sort_formats(formats)
timestamp_ms = int(self._search_regex(
from ..utils import (
int_or_none,
compat_str,
+ ExtractorError,
)
_TESTS = [
{
+ 'url': 'http://vube.com/trending/William+Wei/Y8NUZ69Tf7?t=s',
+ 'md5': 'e7aabe1f8f1aa826b9e4735e1f9cee42',
+ 'info_dict': {
+ 'id': 'Y8NUZ69Tf7',
+ 'ext': 'mp4',
+ 'title': 'Best Drummer Ever [HD]',
+ 'description': 'md5:2d63c4b277b85c2277761c2cf7337d71',
+ 'thumbnail': 're:^https?://.*\.jpg',
+ 'uploader': 'William',
+ 'timestamp': 1406876915,
+ 'upload_date': '20140801',
+ 'duration': 258.051,
+ 'like_count': int,
+ 'dislike_count': int,
+ 'comment_count': int,
+ 'categories': ['amazing', 'hd', 'best drummer ever', 'william wei', 'bucket drumming', 'street drummer', 'epic street drumming'],
+ },
+ }, {
'url': 'http://vube.com/Chiara+Grispo+Video+Channel/YL2qNPkqon',
'md5': 'db7aba89d4603dadd627e9d1973946fe',
'info_dict': {
'dislike_count': int,
'comment_count': int,
'categories': ['pop', 'music', 'cover', 'singing', 'jessie j', 'price tag', 'chiara grispo'],
- }
+ },
+ 'skip': 'Removed due to DMCA',
},
{
'url': 'http://vube.com/SerainaMusic/my-7-year-old-sister-and-i-singing-alive-by-krewella/UeBhTudbfS?t=s&n=1',
'dislike_count': int,
'comment_count': int,
'categories': ['seraina', 'jessica', 'krewella', 'alive'],
- }
+ },
+ 'skip': 'Removed due to DMCA',
}, {
'url': 'http://vube.com/vote/Siren+Gene/0nmsMY5vEq?n=2&t=s',
'md5': '0584fc13b50f887127d9d1007589d27f',
'dislike_count': int,
'comment_count': int,
'categories': ['let it go', 'cover', 'idina menzel', 'frozen', 'singing', 'disney', 'siren gene'],
- }
+ },
+ 'skip': 'Removed due to DMCA',
}
]
self._sort_formats(formats)
+ if not formats and video.get('vst') == 'dmca':
+ raise ExtractorError(
+ 'This video has been removed in response to a complaint received under the US Digital Millennium Copyright Act.',
+ expected=True)
+
title = video['title']
description = video.get('description')
thumbnail = self._proto_relative_url(video.get('thumbnail_src'), scheme='http:')
'upload_date': '20140816',
'duration': 2910,
},
+ 'skip': "Ce contenu n'est pas disponible pour l'instant.",
},
]
from __future__ import unicode_literals
-import json
import re
from .common import InfoExtractor
+from ..utils import ExtractorError, compat_urllib_request
class WistiaIE(InfoExtractor):
_VALID_URL = r'https?://(?:fast\.)?wistia\.net/embed/iframe/(?P<id>[a-z0-9]+)'
+ _API_URL = 'http://fast.wistia.com/embed/medias/{0:}.json'
_TEST = {
'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt',
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
- webpage = self._download_webpage(url, video_id)
- data_json = self._html_search_regex(
- r'Wistia\.iframeInit\((.*?), {}\);', webpage, 'video data')
-
- data = json.loads(data_json)
+ request = compat_urllib_request.Request(self._API_URL.format(video_id))
+ request.add_header('Referer', url) # Some videos require this.
+ data_json = self._download_json(request, video_id)
+ if data_json.get('error'):
+ raise ExtractorError('Error while getting the playlist',
+ expected=True)
+ data = data_json['media']
formats = []
thumbnails = []
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import compat_urllib_parse
+
+
+class YnetIE(InfoExtractor):
+ _VALID_URL = r'http://(?:.+?\.)?ynet\.co\.il/(?:.+?/)?0,7340,(?P<id>L(?:-[0-9]+)+),00\.html'
+ _TESTS = [
+ {
+ 'url': 'http://hot.ynet.co.il/home/0,7340,L-11659-99244,00.html',
+ 'md5': '002b44ee2f33d50363a1c153bed524cf',
+ 'info_dict': {
+ 'id': 'L-11659-99244',
+ 'ext': 'flv',
+ 'title': 'איש לא יודע מאיפה באנו',
+ 'thumbnail': 're:^https?://.*\.jpg',
+ }
+ }, {
+ 'url': 'http://hot.ynet.co.il/home/0,7340,L-8859-84418,00.html',
+ 'md5': '6455046ae1b48cf7e2b7cae285e53a16',
+ 'info_dict': {
+ 'id': 'L-8859-84418',
+ 'ext': 'flv',
+ 'title': "צפו: הנשיקה הלוהטת של תורגי' ויוליה פלוטקין",
+ '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)
+
+ content = compat_urllib_parse.unquote_plus(self._og_search_video_url(webpage))
+ config = json.loads(self._search_regex(r'config=({.+?})$', content, 'video config'))
+ f4m_url = config['clip']['url']
+ title = self._og_search_title(webpage)
+ m = re.search(r'ynet - HOT -- (["\']+)(?P<title>.+?)\1', title)
+ if m:
+ title = m.group('title')
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'formats': self._extract_f4m_formats(f4m_url, video_id),
+ 'thumbnail': self._og_search_thumbnail(webpage),
+ }
\ No newline at end of file
# coding: utf-8
+from __future__ import unicode_literals
+
import json
import math
import random
class YoukuIE(InfoExtractor):
- _VALID_URL = r'(?:(?:http://)?(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|youku:)(?P<ID>[A-Za-z0-9]+)(?:\.html|/v\.swf|)'
- _TEST = {
- u"url": u"http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html",
- u"file": u"XNDgyMDQ2NTQw_part00.flv",
- u"md5": u"ffe3f2e435663dc2d1eea34faeff5b5b",
- u"params": {u"test": False},
- u"info_dict": {
- u"title": u"youtube-dl test video \"'/\\ä↭𝕐"
+ _VALID_URL = r'''(?x)
+ (?:
+ http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
+ youku:)
+ (?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
+ '''
+ _TEST = {
+ 'url': 'http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html',
+ 'md5': 'ffe3f2e435663dc2d1eea34faeff5b5b',
+ 'params': {
+ 'test': False
+ },
+ 'info_dict': {
+ 'id': 'XNDgyMDQ2NTQw_part00',
+ 'ext': 'flv',
+ 'title': 'youtube-dl test video "\'/\\ä↭𝕐'
}
}
-
def _gen_sid(self):
nowTime = int(time.time() * 1000)
random1 = random.randint(1000,1998)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
- video_id = mobj.group('ID')
+ video_id = mobj.group('id')
info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
- jsondata = self._download_webpage(info_url, video_id)
-
- self.report_extraction(video_id)
- try:
- config = json.loads(jsondata)
- error_code = config['data'][0].get('error_code')
- if error_code:
- # -8 means blocked outside China.
- error = config['data'][0].get('error') # Chinese and English, separated by newline.
- raise ExtractorError(error or u'Server reported error %i' % error_code,
- expected=True)
-
- video_title = config['data'][0]['title']
- seed = config['data'][0]['seed']
-
- format = self._downloader.params.get('format', None)
- supported_format = list(config['data'][0]['streamfileids'].keys())
-
- if format is None or format == 'best':
- if 'hd2' in supported_format:
- format = 'hd2'
- else:
- format = 'flv'
- ext = u'flv'
- elif format == 'worst':
- format = 'mp4'
- ext = u'mp4'
- else:
- format = 'flv'
- ext = u'flv'
+ config = self._download_json(info_url, video_id)
+
+ error_code = config['data'][0].get('error_code')
+ if error_code:
+ # -8 means blocked outside China.
+ error = config['data'][0].get('error') # Chinese and English, separated by newline.
+ raise ExtractorError(error or 'Server reported error %i' % error_code,
+ expected=True)
+ video_title = config['data'][0]['title']
+ seed = config['data'][0]['seed']
- fileid = config['data'][0]['streamfileids'][format]
- keys = [s['k'] for s in config['data'][0]['segs'][format]]
- # segs is usually a dictionary, but an empty *list* if an error occured.
- except (UnicodeDecodeError, ValueError, KeyError):
- raise ExtractorError(u'Unable to extract info section')
+ format = self._downloader.params.get('format', None)
+ supported_format = list(config['data'][0]['streamfileids'].keys())
+
+ # TODO proper format selection
+ if format is None or format == 'best':
+ if 'hd2' in supported_format:
+ format = 'hd2'
+ else:
+ format = 'flv'
+ ext = 'flv'
+ elif format == 'worst':
+ format = 'mp4'
+ ext = 'mp4'
+ else:
+ format = 'flv'
+ ext = 'flv'
+
+ fileid = config['data'][0]['streamfileids'][format]
+ keys = [s['k'] for s in config['data'][0]['segs'][format]]
+ # segs is usually a dictionary, but an empty *list* if an error occured.
files_info=[]
sid = self._gen_sid()
#column 8,9 of fileid represent the segment number
#fileid[7:9] should be changed
for index, key in enumerate(keys):
-
temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:])
- download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
+ download_url = 'http://k.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
info = {
'id': '%s_part%02d' % (video_id, index),
def _set_language(self):
return bool(self._download_webpage(
self._LANG_URL, None,
- note=u'Setting language', errnote='unable to set language',
+ note='Setting language', errnote='unable to set language',
fatal=False))
def _login(self):
# No authentication to be performed
if username is None:
if self._LOGIN_REQUIRED:
- raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True)
+ raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
return True
login_page = self._download_webpage(
self._LOGIN_URL, None,
- note=u'Downloading login page',
- errnote=u'unable to fetch login page', fatal=False)
+ note='Downloading login page',
+ errnote='unable to fetch login page', fatal=False)
if login_page is False:
return
req = compat_urllib_request.Request(self._LOGIN_URL, login_data)
login_results = self._download_webpage(
req, None,
- note=u'Logging in', errnote=u'unable to log in', fatal=False)
+ note='Logging in', errnote='unable to log in', fatal=False)
if login_results is False:
return False
if re.search(r'id="errormsg_0_Passwd"', login_results) is not None:
- raise ExtractorError(u'Please use your account password and a two-factor code instead of an application-specific password.', expected=True)
+ raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True)
# Two-Factor
# TODO add SMS and phone call support - these require making a request and then prompting the user
tfa_code = self._get_tfa_info()
if tfa_code is None:
- self._downloader.report_warning(u'Two-factor authentication required. Provide it with --twofactor <code>')
- self._downloader.report_warning(u'(Note that only TOTP (Google Authenticator App) codes work at this time.)')
+ self._downloader.report_warning('Two-factor authentication required. Provide it with --twofactor <code>')
+ self._downloader.report_warning('(Note that only TOTP (Google Authenticator App) codes work at this time.)')
return False
# Unlike the first login form, secTok and timeStmp are both required for the TFA form
match = re.search(r'id="secTok"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U)
if match is None:
- self._downloader.report_warning(u'Failed to get secTok - did the page structure change?')
+ self._downloader.report_warning('Failed to get secTok - did the page structure change?')
secTok = match.group(1)
match = re.search(r'id="timeStmp"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U)
if match is None:
- self._downloader.report_warning(u'Failed to get timeStmp - did the page structure change?')
+ self._downloader.report_warning('Failed to get timeStmp - did the page structure change?')
timeStmp = match.group(1)
tfa_form_strs = {
tfa_req = compat_urllib_request.Request(self._TWOFACTOR_URL, tfa_data)
tfa_results = self._download_webpage(
tfa_req, None,
- note=u'Submitting TFA code', errnote=u'unable to submit tfa', fatal=False)
+ note='Submitting TFA code', errnote='unable to submit tfa', fatal=False)
if tfa_results is False:
return False
if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', tfa_results) is not None:
- self._downloader.report_warning(u'Two-factor code expired. Please try again, or use a one-use backup code instead.')
+ self._downloader.report_warning('Two-factor code expired. Please try again, or use a one-use backup code instead.')
return False
if re.search(r'(?i)<form[^>]* id="gaia_loginform"', tfa_results) is not None:
- self._downloader.report_warning(u'unable to log in - did the page structure change?')
+ self._downloader.report_warning('unable to log in - did the page structure change?')
return False
if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None:
- self._downloader.report_warning(u'Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.')
+ self._downloader.report_warning('Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.')
return False
if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None:
- self._downloader.report_warning(u'unable to log in: bad username or password')
+ self._downloader.report_warning('unable to log in: bad username or password')
return False
return True
self._download_webpage(
req, None,
- note=u'Confirming age', errnote=u'Unable to confirm age')
+ note='Confirming age', errnote='Unable to confirm age')
return True
def _real_initialize(self):
youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
(?:.*?\#/)? # handle anchor (#/) redirect urls
(?: # the various things that can precede the ID:
- (?:(?:v|embed|e)/) # v/ or embed/ or e/
+ (?:(?:v|embed|e)/(?!videoseries)) # 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)
(?:\?|\#!?) # the params delimiter ? or # or #!
IE_NAME = 'youtube'
_TESTS = [
{
- u"url": u"http://www.youtube.com/watch?v=BaW_jenozKc",
- u"file": u"BaW_jenozKc.mp4",
- u"info_dict": {
- u"title": u"youtube-dl test video \"'/\\ä↭𝕐",
- u"uploader": u"Philipp Hagemeister",
- u"uploader_id": u"phihag",
- u"upload_date": u"20121002",
- u"description": u"test chars: \"'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .",
- u"categories": [u'Science & Technology'],
+ 'url': 'http://www.youtube.com/watch?v=BaW_jenozKc',
+ 'info_dict': {
+ 'id': 'BaW_jenozKc',
+ 'ext': 'mp4',
+ 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
+ 'uploader': 'Philipp Hagemeister',
+ 'uploader_id': 'phihag',
+ 'upload_date': '20121002',
+ 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
+ 'categories': ['Science & Technology'],
'like_count': int,
'dislike_count': int,
}
},
{
- u"url": u"http://www.youtube.com/watch?v=UxxajLWwzqY",
- u"file": u"UxxajLWwzqY.mp4",
- u"note": u"Test generic use_cipher_signature video (#897)",
- u"info_dict": {
- u"upload_date": u"20120506",
- u"title": u"Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]",
- u"description": u"md5:fea86fda2d5a5784273df5c7cc994d9f",
- u"uploader": u"Icona Pop",
- u"uploader_id": u"IconaPop"
+ 'url': 'http://www.youtube.com/watch?v=UxxajLWwzqY',
+ 'note': 'Test generic use_cipher_signature video (#897)',
+ 'info_dict': {
+ 'id': 'UxxajLWwzqY',
+ 'ext': 'mp4',
+ 'upload_date': '20120506',
+ 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
+ 'description': 'md5:fea86fda2d5a5784273df5c7cc994d9f',
+ 'uploader': 'Icona Pop',
+ 'uploader_id': 'IconaPop',
}
},
{
- u"url": u"https://www.youtube.com/watch?v=07FYdnEawAQ",
- u"file": u"07FYdnEawAQ.mp4",
- u"note": u"Test VEVO video with age protection (#956)",
- u"info_dict": {
- u"upload_date": u"20130703",
- u"title": u"Justin Timberlake - Tunnel Vision (Explicit)",
- u"description": u"md5:64249768eec3bc4276236606ea996373",
- u"uploader": u"justintimberlakeVEVO",
- u"uploader_id": u"justintimberlakeVEVO"
+ 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
+ 'note': 'Test VEVO video with age protection (#956)',
+ 'info_dict': {
+ 'id': '07FYdnEawAQ',
+ 'ext': 'mp4',
+ 'upload_date': '20130703',
+ 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
+ 'description': 'md5:64249768eec3bc4276236606ea996373',
+ 'uploader': 'justintimberlakeVEVO',
+ 'uploader_id': 'justintimberlakeVEVO',
}
},
{
- u"url": u"//www.YouTube.com/watch?v=yZIXLfi8CZQ",
- u"file": u"yZIXLfi8CZQ.mp4",
- u"note": u"Embed-only video (#1746)",
- u"info_dict": {
- u"upload_date": u"20120608",
- u"title": u"Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012",
- u"description": u"md5:09b78bd971f1e3e289601dfba15ca4f7",
- u"uploader": u"SET India",
- u"uploader_id": u"setindia"
+ 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
+ 'note': 'Embed-only video (#1746)',
+ 'info_dict': {
+ 'id': 'yZIXLfi8CZQ',
+ 'ext': 'mp4',
+ 'upload_date': '20120608',
+ 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
+ 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
+ 'uploader': 'SET India',
+ 'uploader_id': 'setindia'
}
},
{
- u"url": u"http://www.youtube.com/watch?v=a9LDPn-MO4I",
- u"file": u"a9LDPn-MO4I.m4a",
- u"note": u"256k DASH audio (format 141) via DASH manifest",
- u"info_dict": {
- u"upload_date": "20121002",
- u"uploader_id": "8KVIDEO",
- u"description": '',
- u"uploader": "8KVIDEO",
- u"title": "UHDTV TEST 8K VIDEO.mp4"
+ 'url': 'http://www.youtube.com/watch?v=a9LDPn-MO4I',
+ 'note': '256k DASH audio (format 141) via DASH manifest',
+ 'info_dict': {
+ 'id': 'a9LDPn-MO4I',
+ 'ext': 'm4a',
+ 'upload_date': '20121002',
+ 'uploader_id': '8KVIDEO',
+ 'description': '',
+ 'uploader': '8KVIDEO',
+ 'title': 'UHDTV TEST 8K VIDEO.mp4'
},
- u"params": {
- u"youtube_include_dash_manifest": True,
- u"format": "141",
+ 'params': {
+ 'youtube_include_dash_manifest': True,
+ 'format': '141',
},
},
# DASH manifest with encrypted signature
'uploader_id': 'AfrojackVEVO',
'upload_date': '20131011',
},
- u"params": {
+ 'params': {
'youtube_include_dash_manifest': True,
'format': '141',
},
def report_video_info_webpage_download(self, video_id):
"""Report attempt to download video info webpage."""
- self.to_screen(u'%s: Downloading video info webpage' % video_id)
+ self.to_screen('%s: Downloading video info webpage' % video_id)
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
- self.to_screen(u'%s: Extracting video information' % video_id)
+ self.to_screen('%s: Extracting video information' % video_id)
def report_unavailable_format(self, video_id, format):
"""Report extracted video URL."""
- self.to_screen(u'%s: Format %s not available' % (video_id, format))
+ self.to_screen('%s: Format %s not available' % (video_id, format))
def report_rtmp_download(self):
"""Indicate the download will use the RTMP protocol."""
- self.to_screen(u'RTMP download detected')
+ self.to_screen('RTMP download detected')
def _signature_cache_id(self, example_sig):
""" Return a string representation of a signature """
player_type, player_id, self._signature_cache_id(example_sig))
assert os.path.basename(func_id) == func_id
- cache_spec = self._downloader.cache.load(u'youtube-sigfuncs', func_id)
+ cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
if cache_spec is not None:
return lambda s: ''.join(s[i] for i in cache_spec)
if player_type == 'js':
code = self._download_webpage(
player_url, video_id,
- note=u'Downloading %s player %s' % (player_type, player_id),
- errnote=u'Download of %s failed' % player_url)
+ note='Downloading %s player %s' % (player_type, player_id),
+ errnote='Download of %s failed' % player_url)
res = self._parse_sig_js(code)
elif player_type == 'swf':
urlh = self._request_webpage(
player_url, video_id,
- note=u'Downloading %s player %s' % (player_type, player_id),
- errnote=u'Download of %s failed' % player_url)
+ note='Downloading %s player %s' % (player_type, player_id),
+ errnote='Download of %s failed' % player_url)
code = urlh.read()
res = self._parse_sig_swf(code)
else:
cache_res = res(test_string)
cache_spec = [ord(c) for c in cache_res]
- self._downloader.cache.store(u'youtube-sigfuncs', func_id, cache_spec)
+ self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
return res
def _print_sig_code(self, func, example_sig):
def gen_sig_code(idxs):
def _genslice(start, end, step):
starts = '' if start == 0 else str(start)
- ends = (u':%d' % (end+step)) if end + step >= 0 else ':'
- steps = '' if step == 1 else (u':%d' % step)
+ ends = (':%d' % (end+step)) if end + step >= 0 else ':'
+ steps = '' if step == 1 else (':%d' % step)
return 's[%s%s%s]' % (starts, ends, steps)
step = None
expr_code = ' + '.join(gen_sig_code(cache_spec))
signature_id_tuple = '(%s)' % (
', '.join(compat_str(len(p)) for p in example_sig.split('.')))
- code = (u'if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
+ code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
' return %s\n') % (signature_id_tuple, expr_code)
- self.to_screen(u'Extracted signature function:\n' + code)
+ self.to_screen('Extracted signature function:\n' + code)
def _parse_sig_js(self, jscode):
funcname = self._search_regex(
"""Turn the encrypted s field into a working signature"""
if player_url is None:
- raise ExtractorError(u'Cannot decrypt signature without player_url')
+ raise ExtractorError('Cannot decrypt signature without player_url')
- if player_url.startswith(u'//'):
+ if player_url.startswith('//'):
player_url = 'https:' + player_url
try:
player_id = (player_url, self._signature_cache_id(s))
'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
video_id, note=False)
except ExtractorError as err:
- self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
+ self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err))
return {}
lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)
url = 'https://www.youtube.com/api/timedtext?' + params
sub_lang_list[lang] = url
if not sub_lang_list:
- self._downloader.report_warning(u'video doesn\'t have subtitles')
+ self._downloader.report_warning('video doesn\'t have subtitles')
return {}
return sub_lang_list
"""We need the webpage for getting the captions url, pass it as an
argument to speed up the process."""
sub_format = self._downloader.params.get('subtitlesformat', 'srt')
- self.to_screen(u'%s: Looking for automatic captions' % video_id)
+ self.to_screen('%s: Looking for automatic captions' % video_id)
mobj = re.search(r';ytplayer.config = ({.*?});', webpage)
err_msg = 'Couldn\'t find automatic captions for %s' % video_id
if mobj is None:
caption_list = self._download_xml(list_url, video_id)
original_lang_node = caption_list.find('track')
if original_lang_node is None or original_lang_node.attrib.get('kind') != 'asr' :
- self._downloader.report_warning(u'Video doesn\'t have automatic captions')
+ self._downloader.report_warning('Video doesn\'t have automatic captions')
return {}
original_lang = original_lang_node.attrib['lang_code']
def extract_id(cls, url):
mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
+ raise ExtractorError('Invalid URL: %s' % url)
video_id = mobj.group(2)
return video_id
def _extract_annotations(self, video_id):
url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
- return self._download_webpage(url, video_id, note=u'Searching for annotations.', errnote=u'Unable to download video annotations.')
+ return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
def _real_extract(self, url):
proto = (
# Check for "rental" videos
if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
- raise ExtractorError(u'"rental" videos not supported')
+ raise ExtractorError('"rental" videos not supported')
# Start extracting information
self.report_information_extraction(video_id)
# uploader
if 'author' not in video_info:
- raise ExtractorError(u'Unable to extract uploader name')
+ raise ExtractorError('Unable to extract uploader name')
video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0])
# uploader_id
if mobj is not None:
video_uploader_id = mobj.group(1)
else:
- self._downloader.report_warning(u'unable to extract uploader nickname')
+ self._downloader.report_warning('unable to extract uploader nickname')
# title
if 'title' in video_info:
video_title = video_info['title'][0]
else:
- self._downloader.report_warning(u'Unable to extract video title')
+ self._downloader.report_warning('Unable to extract video title')
video_title = '_'
# thumbnail image
if m_thumb is not None:
video_thumbnail = m_thumb.group(1)
elif 'thumbnail_url' not in video_info:
- self._downloader.report_warning(u'unable to extract video thumbnail')
+ self._downloader.report_warning('unable to extract video thumbnail')
video_thumbnail = None
else: # don't panic if we can't find it
video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0])
if count is not None:
return int(count.replace(',', ''))
return None
- like_count = _extract_count(u'like')
- dislike_count = _extract_count(u'dislike')
+ like_count = _extract_count('like')
+ dislike_count = _extract_count('dislike')
# subtitles
video_subtitles = self.extract_subtitles(video_id, video_webpage)
return
if 'length_seconds' not in video_info:
- self._downloader.report_warning(u'unable to extract video duration')
+ self._downloader.report_warning('unable to extract video duration')
video_duration = None
else:
video_duration = int(compat_urllib_parse.unquote_plus(video_info['length_seconds'][0]))
# Easy way to know if the 's' value is in url_encoded_fmt_stream_map
# this signatures are encrypted
if 'url_encoded_fmt_stream_map' not in args:
- raise ValueError(u'No stream_map present') # caught below
+ raise ValueError('No stream_map present') # caught below
re_signature = re.compile(r'[&,]s=')
m_s = re_signature.search(args['url_encoded_fmt_stream_map'])
if m_s is not None:
- self.to_screen(u'%s: Encrypted signatures detected.' % video_id)
+ self.to_screen('%s: Encrypted signatures detected.' % video_id)
video_info['url_encoded_fmt_stream_map'] = [args['url_encoded_fmt_stream_map']]
m_s = re_signature.search(args.get('adaptive_fmts', ''))
if m_s is not None:
player_desc = 'html5 player %s' % player_version
parts_sizes = self._signature_cache_id(encrypted_sig)
- self.to_screen(u'{%s} signature length %s, %s' %
+ self.to_screen('{%s} signature length %s, %s' %
(format_id, parts_sizes, player_desc))
signature = self._decrypt_signature(
url_map = self._extract_from_m3u8(manifest_url, video_id)
formats = _map_to_format_list(url_map)
else:
- raise ExtractorError(u'no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
+ raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
# Look for the DASH manifest
if (self._downloader.params.get('youtube_include_dash_manifest', False)):
dash_manifest_url = re.sub(r'/s/([\w\.]+)', decrypt_sig, dash_manifest_url)
dash_doc = self._download_xml(
dash_manifest_url, video_id,
- note=u'Downloading DASH manifest',
- errnote=u'Could not download DASH manifest')
- for r in dash_doc.findall(u'.//{urn:mpeg:DASH:schema:MPD:2011}Representation'):
+ note='Downloading DASH manifest',
+ errnote='Could not download DASH manifest')
+ for r in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}Representation'):
url_el = r.find('{urn:mpeg:DASH:schema:MPD:2011}BaseURL')
if url_el is None:
continue
existing_format.update(f)
except (ExtractorError, KeyError) as e:
- self.report_warning(u'Skipping DASH manifest: %s' % e, video_id)
+ self.report_warning('Skipping DASH manifest: %s' % e, video_id)
self._sort_formats(formats)
(?:\w+\.)?
youtube\.com/
(?:
- (?:course|view_play_list|my_playlists|artist|playlist|watch)
+ (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries)
\? (?:.*?&)*? (?:p|a|list)=
| p/
)
'title': 'YDL_safe_search',
},
'playlist_count': 2,
+ }, {
+ 'note': 'embedded',
+ 'url': 'http://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
+ 'playlist_count': 4,
+ 'info_dict': {
+ 'title': 'JODA15',
+ }
+ }, {
+ 'note': 'Embedded SWF player',
+ 'url': 'http://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
+ 'playlist_count': 4,
+ 'info_dict': {
+ 'title': 'JODA7',
+ }
}]
def _real_initialize(self):
# Extract playlist id
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
+ raise ExtractorError('Invalid URL: %s' % url)
playlist_id = mobj.group(1) or mobj.group(2)
# Check if it's a video-specific URL
if 'v' in query_dict:
video_id = query_dict['v'][0]
if self._downloader.params.get('noplaylist'):
- self.to_screen(u'Downloading just video %s because of --no-playlist' % video_id)
+ self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
return self.url_result(video_id, 'Youtube', video_id=video_id)
else:
- self.to_screen(u'Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
+ self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
if playlist_id.startswith('RD'):
# Mixes require a custom extraction process
return self._extract_mix(playlist_id)
if playlist_id.startswith('TL'):
- raise ExtractorError(u'For downloading YouTube.com top lists, use '
+ raise ExtractorError('For downloading YouTube.com top lists, use '
'the "yttoplist" keyword, for example "youtube-dl \'yttoplist:music:Top Tracks\'"', expected=True)
url = self._TEMPLATE_URL % playlist_id
class YoutubeTopListIE(YoutubePlaylistIE):
IE_NAME = 'youtube:toplist'
- IE_DESC = (u'YouTube.com top lists, "yttoplist:{channel}:{list title}"'
+ IE_DESC = ('YouTube.com top lists, "yttoplist:{channel}:{list title}"'
' (Example: "yttoplist:music:Top Tracks")')
_VALID_URL = r'yttoplist:(?P<chann>.*?):(?P<title>.*?)$'
- _TESTS = []
+ _TESTS = [{
+ 'url': 'yttoplist:music:Trending',
+ 'playlist_mincount': 5,
+ 'skip': 'Only works for logged-in users',
+ }]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
channel = mobj.group('chann')
title = mobj.group('title')
query = compat_urllib_parse.urlencode({'title': title})
- playlist_re = 'href="([^"]+?%s.*?)"' % re.escape(query)
- channel_page = self._download_webpage('https://www.youtube.com/%s' % channel, title)
- link = self._html_search_regex(playlist_re, channel_page, 'list')
+ channel_page = self._download_webpage(
+ 'https://www.youtube.com/%s' % channel, title)
+ link = self._html_search_regex(
+ r'''(?x)
+ <a\s+href="([^"]+)".*?>\s*
+ <span\s+class="branded-page-module-title-text">\s*
+ <span[^>]*>.*?%s.*?</span>''' % re.escape(query),
+ channel_page, 'list')
url = compat_urlparse.urljoin('https://www.youtube.com/', link)
video_re = r'data-index="\d+".*?data-video-id="([0-9A-Za-z_-]{11})"'
_MORE_PAGES_INDICATOR = 'yt-uix-load-more'
_MORE_PAGES_URL = 'https://www.youtube.com/c4_browse_ajax?action_load_more_videos=1&flow=list&paging=%s&view=0&sort=da&channel_id=%s'
IE_NAME = 'youtube:channel'
+ _TESTS = [{
+ 'note': 'paginated channel',
+ 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'playlist_mincount': 91,
+ }]
def extract_videos_from_page(self, page):
ids_in_page = []
# Extract channel id
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
+ raise ExtractorError('Invalid URL: %s' % url)
# Download channel page
channel_id = mobj.group(1)
for pagenum in itertools.count(1):
url = self._MORE_PAGES_URL % (pagenum, channel_id)
page = self._download_json(
- url, channel_id, note=u'Downloading page #%s' % pagenum,
+ url, channel_id, note='Downloading page #%s' % pagenum,
transform_source=uppercase_escape)
ids_in_page = self.extract_videos_from_page(page['content_html'])
if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']:
break
- self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids)))
+ self._downloader.to_screen('[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids)))
url_entries = [self.url_result(video_id, 'Youtube', video_id=video_id)
for video_id in video_ids]
_GDATA_URL = 'https://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d&alt=json'
IE_NAME = 'youtube:user'
+ _TESTS = [{
+ 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
+ 'playlist_mincount': 320,
+ 'info_dict': {
+ 'title': 'TheLinuxFoundation',
+ }
+ }, {
+ 'url': 'ytuser:phihag',
+ 'only_matching': True,
+ }]
+
@classmethod
def suitable(cls, url):
# Don't return True if the url can be extracted with other youtube
# Extract username
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
+ raise ExtractorError('Invalid URL: %s' % url)
username = mobj.group(1)
try:
response = json.loads(page)
except ValueError as err:
- raise ExtractorError(u'Invalid JSON in API response: ' + compat_str(err))
+ raise ExtractorError('Invalid JSON in API response: ' + compat_str(err))
if 'entry' not in response['feed']:
return
compat_urllib_parse.quote_plus(query.encode('utf-8')),
(PAGE_SIZE * pagenum) + 1)
data_json = self._download_webpage(
- result_url, video_id=u'query "%s"' % query,
- note=u'Downloading page %s' % (pagenum + 1),
- errnote=u'Unable to download API page')
+ result_url, video_id='query "%s"' % query,
+ note='Downloading page %s' % (pagenum + 1),
+ errnote='Unable to download API page')
data = json.loads(data_json)
api_response = data['data']
IE_DESC = 'YouTube.com search URLs'
IE_NAME = 'youtube:search_url'
_VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?search_query=(?P<query>[^&]+)(?:[&]|$)'
+ _TESTS = [{
+ 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
+ 'playlist_mincount': 5,
+ 'info_dict': {
+ 'title': 'youtube-dl test video',
+ }
+ }]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
class YoutubeShowIE(InfoExtractor):
IE_DESC = 'YouTube.com (multi-season) shows'
- _VALID_URL = r'https?://www\.youtube\.com/show/(.*)'
+ _VALID_URL = r'https?://www\.youtube\.com/show/(?P<id>[^?#]*)'
IE_NAME = 'youtube:show'
+ _TESTS = [{
+ 'url': 'http://www.youtube.com/show/airdisasters',
+ 'playlist_mincount': 3,
+ 'info_dict': {
+ 'id': 'airdisasters',
+ 'title': 'Air Disasters',
+ }
+ }]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- show_name = mobj.group(1)
- webpage = self._download_webpage(url, show_name, 'Downloading show webpage')
+ playlist_id = mobj.group('id')
+ webpage = self._download_webpage(
+ url, playlist_id, 'Downloading show webpage')
# There's one playlist for each season of the show
m_seasons = list(re.finditer(r'href="(/playlist\?list=.*?)"', webpage))
- self.to_screen(u'%s: Found %s seasons' % (show_name, len(m_seasons)))
- return [self.url_result('https://www.youtube.com' + season.group(1), 'YoutubePlaylist') for season in m_seasons]
+ self.to_screen('%s: Found %s seasons' % (playlist_id, len(m_seasons)))
+ entries = [
+ self.url_result(
+ 'https://www.youtube.com' + season.group(1), 'YoutubePlaylist')
+ for season in m_seasons
+ ]
+ title = self._og_search_title(webpage, fatal=False)
+
+ return {
+ '_type': 'playlist',
+ 'id': playlist_id,
+ 'title': title,
+ 'entries': entries,
+ }
class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
-__version__ = '2014.09.22.1'
+__version__ = '2014.09.28'
projects / youtube-dl / commitdiff