.coverage
cover/
updates_key.pem
-*.egg-info
\ No newline at end of file
+*.egg-info
+*.srt
+*.sbv
+*.vtt
+*.flv
+*.mp4
+*.part
only)
## Subtitle Options:
- --write-sub write subtitle file (currently youtube only)
- --write-auto-sub write automatic subtitle file (currently youtube
- only)
- --only-sub [deprecated] alias of --skip-download
+ --write-sub write subtitle file
+ --write-auto-sub write automatic subtitle file (youtube only)
--all-subs downloads all the available subtitles of the
video
--list-subs lists all available subtitles for the video
import json
import sys
import hashlib
-import urllib.request
+import os.path
+
if len(sys.argv) <= 1:
print('Specify the version number as parameter')
'tar': 'youtube-dl-%s.tar.gz' % version}
build_dir = os.path.join('..', '..', 'build', version)
for key, filename in filenames.items():
+ url = 'https://yt-dl.org/downloads/%s/%s' % (version, filename)
fn = os.path.join(build_dir, filename)
with open(fn, 'rb') as f:
data = f.read()
template = tmplf.read()
ie_htmls = []
- for ie in sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME):
+ for ie in sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower()):
ie_html = '<b>{}</b>'.format(ie.IE_NAME)
try:
ie_html += ': {}'.format(ie.IE_DESC)
# 86 - vfluy6kdb 2013/09/06
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[|};?/>.<",
"yuioplkjhgfdsazxcvbnm12345678q0QWrRTYUIOELKJHGFD-AZXCVBNM!@#$%^&*()_<+={[|};?/>.S"),
- # 85
+ # 85 - vflkuzxcs 2013/09/11
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?/>.<",
- ".>/?;}[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWQ0q876543r1mnbvcx9asdfghjklpoiuyt2"),
+ "T>/?;}[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOvUY.REWQ0987654321mnbqcxzasdfghjklpoiuytr"),
# 84 - vflg0g8PQ 2013/08/29 (sporadic)
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?>.<",
">?;}[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWq0987654321mnbvcxzasdfghjklpoiuytr"),
# 83
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!#$%^&*()_+={[};?/>.<",
".>/?;}[{=+_)(*&^%<#!MNBVCXZASPFGHJKLwOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuytreq"),
- # 82 - vflZK4ZYR 2013/08/23
+ # 82 - vflGNjMhJ 2013/09/12
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.<",
- "wertyuioplkjhgfdsaqxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&z(-+={[};?/>.<"),
+ ".>/?;}[<=+-(*&^%$#@!MNBVCXeASDFGHKLPOqUYTREWQ0987654321mnbvcxzasdfghjklpoiuytrIwZ"),
# 81 - vflLC8JvQ 2013/07/25
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.",
"C>/?;}[{=+-(*&^%$#@!MNBVYXZASDFGHKLPOIU.TREWQ0q87659321mnbvcxzasdfghjkl4oiuytrewp"),
"writedescription": false,
"writeinfojson": true,
"writesubtitles": false,
- "onlysubtitles": false,
"allsubtitles": false,
"listssubtitles": false
}
self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/tsm_theoddone/c/2349361"))
def test_youtube_extract(self):
- 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')
+ assertExtractId = lambda url, id: self.assertEqual(YoutubeIE()._extract_id(url), id)
+ assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
+ assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
+ assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
+ assertExtractId('https://www.youtube.com/watch_popup?v=BaW_jenozKc', 'BaW_jenozKc')
+ assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
+ assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
def test_no_duplicates(self):
ies = gen_extractors()
--- /dev/null
+#!/usr/bin/env python
+
+import sys
+import unittest
+import json
+import io
+import hashlib
+
+# Allow direct execution
+import os
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.extractor import DailymotionIE
+from youtube_dl.utils import *
+from helper import FakeYDL
+
+md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
+
+class TestDailymotionSubtitles(unittest.TestCase):
+ def setUp(self):
+ self.DL = FakeYDL()
+ self.url = 'http://www.dailymotion.com/video/xczg00'
+ def getInfoDict(self):
+ IE = DailymotionIE(self.DL)
+ info_dict = IE.extract(self.url)
+ return info_dict
+ def getSubtitles(self):
+ info_dict = self.getInfoDict()
+ return info_dict[0]['subtitles']
+ def test_no_writesubtitles(self):
+ subtitles = self.getSubtitles()
+ self.assertEqual(subtitles, None)
+ def test_subtitles(self):
+ self.DL.params['writesubtitles'] = True
+ subtitles = self.getSubtitles()
+ self.assertEqual(md5(subtitles['en']), '976553874490cba125086bbfea3ff76f')
+ def test_subtitles_lang(self):
+ self.DL.params['writesubtitles'] = True
+ self.DL.params['subtitleslangs'] = ['fr']
+ subtitles = self.getSubtitles()
+ self.assertEqual(md5(subtitles['fr']), '594564ec7d588942e384e920e5341792')
+ def test_allsubtitles(self):
+ self.DL.params['allsubtitles'] = True
+ subtitles = self.getSubtitles()
+ self.assertEqual(len(subtitles.keys()), 5)
+ def test_list_subtitles(self):
+ self.DL.params['listsubtitles'] = True
+ info_dict = self.getInfoDict()
+ self.assertEqual(info_dict, None)
+ def test_automatic_captions(self):
+ self.DL.params['writeautomaticsub'] = True
+ self.DL.params['subtitleslang'] = ['en']
+ subtitles = self.getSubtitles()
+ self.assertTrue(len(subtitles.keys()) == 0)
+ def test_nosubtitles(self):
+ self.url = 'http://www.dailymotion.com/video/x12u166_le-zapping-tele-star-du-08-aout-2013_tv'
+ self.DL.params['allsubtitles'] = True
+ subtitles = self.getSubtitles()
+ self.assertEqual(len(subtitles), 0)
+ def test_multiple_langs(self):
+ self.DL.params['writesubtitles'] = True
+ langs = ['es', 'fr', 'de']
+ self.DL.params['subtitleslangs'] = langs
+ subtitles = self.getSubtitles()
+ for lang in langs:
+ self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
+
+if __name__ == '__main__':
+ unittest.main()
class TestYoutubeSubtitles(unittest.TestCase):
def setUp(self):
- DL = FakeYDL()
- DL.params['allsubtitles'] = False
- DL.params['writesubtitles'] = False
- DL.params['subtitlesformat'] = 'srt'
- DL.params['listsubtitles'] = False
- def test_youtube_no_subtitles(self):
- DL = FakeYDL()
- DL.params['writesubtitles'] = False
- IE = YoutubeIE(DL)
- info_dict = IE.extract('QRS8MkLhQmM')
- subtitles = info_dict[0]['subtitles']
+ self.DL = FakeYDL()
+ self.url = 'QRS8MkLhQmM'
+ def getInfoDict(self):
+ IE = YoutubeIE(self.DL)
+ info_dict = IE.extract(self.url)
+ return info_dict
+ def getSubtitles(self):
+ info_dict = self.getInfoDict()
+ return info_dict[0]['subtitles']
+ def test_youtube_no_writesubtitles(self):
+ self.DL.params['writesubtitles'] = False
+ subtitles = self.getSubtitles()
self.assertEqual(subtitles, None)
def test_youtube_subtitles(self):
- DL = FakeYDL()
- DL.params['writesubtitles'] = True
- IE = YoutubeIE(DL)
- info_dict = IE.extract('QRS8MkLhQmM')
- sub = info_dict[0]['subtitles']['en']
- self.assertEqual(md5(sub), '4cd9278a35ba2305f47354ee13472260')
- def test_youtube_subtitles_it(self):
- DL = FakeYDL()
- DL.params['writesubtitles'] = True
- DL.params['subtitleslangs'] = ['it']
- IE = YoutubeIE(DL)
- info_dict = IE.extract('QRS8MkLhQmM')
- sub = info_dict[0]['subtitles']['it']
- self.assertEqual(md5(sub), '164a51f16f260476a05b50fe4c2f161d')
- def test_youtube_onlysubtitles(self):
- DL = FakeYDL()
- DL.params['writesubtitles'] = True
- DL.params['onlysubtitles'] = True
- IE = YoutubeIE(DL)
- info_dict = IE.extract('QRS8MkLhQmM')
- sub = info_dict[0]['subtitles']['en']
- self.assertEqual(md5(sub), '4cd9278a35ba2305f47354ee13472260')
+ self.DL.params['writesubtitles'] = True
+ subtitles = self.getSubtitles()
+ self.assertEqual(md5(subtitles['en']), '4cd9278a35ba2305f47354ee13472260')
+ def test_youtube_subtitles_lang(self):
+ self.DL.params['writesubtitles'] = True
+ self.DL.params['subtitleslangs'] = ['it']
+ subtitles = self.getSubtitles()
+ self.assertEqual(md5(subtitles['it']), '164a51f16f260476a05b50fe4c2f161d')
def test_youtube_allsubtitles(self):
- DL = FakeYDL()
- DL.params['allsubtitles'] = True
- IE = YoutubeIE(DL)
- info_dict = IE.extract('QRS8MkLhQmM')
- subtitles = info_dict[0]['subtitles']
+ self.DL.params['allsubtitles'] = True
+ subtitles = self.getSubtitles()
self.assertEqual(len(subtitles.keys()), 13)
def test_youtube_subtitles_sbv_format(self):
- DL = FakeYDL()
- DL.params['writesubtitles'] = True
- DL.params['subtitlesformat'] = 'sbv'
- IE = YoutubeIE(DL)
- info_dict = IE.extract('QRS8MkLhQmM')
- sub = info_dict[0]['subtitles']['en']
- self.assertEqual(md5(sub), '13aeaa0c245a8bed9a451cb643e3ad8b')
+ self.DL.params['writesubtitles'] = True
+ self.DL.params['subtitlesformat'] = 'sbv'
+ subtitles = self.getSubtitles()
+ self.assertEqual(md5(subtitles['en']), '13aeaa0c245a8bed9a451cb643e3ad8b')
def test_youtube_subtitles_vtt_format(self):
- DL = FakeYDL()
- DL.params['writesubtitles'] = True
- DL.params['subtitlesformat'] = 'vtt'
- IE = YoutubeIE(DL)
- info_dict = IE.extract('QRS8MkLhQmM')
- sub = info_dict[0]['subtitles']['en']
- self.assertEqual(md5(sub), '356cdc577fde0c6783b9b822e7206ff7')
+ self.DL.params['writesubtitles'] = True
+ self.DL.params['subtitlesformat'] = 'vtt'
+ subtitles = self.getSubtitles()
+ self.assertEqual(md5(subtitles['en']), '356cdc577fde0c6783b9b822e7206ff7')
def test_youtube_list_subtitles(self):
- DL = FakeYDL()
- DL.params['listsubtitles'] = True
- IE = YoutubeIE(DL)
- info_dict = IE.extract('QRS8MkLhQmM')
+ self.DL.params['listsubtitles'] = True
+ info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_youtube_automatic_captions(self):
- DL = FakeYDL()
- DL.params['writeautomaticsub'] = True
- DL.params['subtitleslangs'] = ['it']
- IE = YoutubeIE(DL)
- info_dict = IE.extract('8YoUxe5ncPo')
- sub = info_dict[0]['subtitles']['it']
- self.assertTrue(sub is not None)
+ self.url = '8YoUxe5ncPo'
+ self.DL.params['writeautomaticsub'] = True
+ self.DL.params['subtitleslangs'] = ['it']
+ subtitles = self.getSubtitles()
+ self.assertTrue(subtitles['it'] is not None)
+ def test_youtube_nosubtitles(self):
+ self.url = 'sAjKT8FhjI8'
+ self.DL.params['allsubtitles'] = True
+ subtitles = self.getSubtitles()
+ self.assertEqual(len(subtitles), 0)
def test_youtube_multiple_langs(self):
- DL = FakeYDL()
- DL.params['writesubtitles'] = True
+ self.url = 'QRS8MkLhQmM'
+ self.DL.params['writesubtitles'] = True
langs = ['it', 'fr', 'de']
- DL.params['subtitleslangs'] = langs
- IE = YoutubeIE(DL)
- subtitles = IE.extract('QRS8MkLhQmM')[0]['subtitles']
+ self.DL.params['subtitleslangs'] = langs
+ subtitles = self.getSubtitles()
for lang in langs:
self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
@staticmethod
def format_seconds(seconds):
(mins, secs) = divmod(seconds, 60)
- (hours, eta_mins) = divmod(mins, 60)
+ (hours, mins) = divmod(mins, 60)
if hours > 99:
return '--:--:--'
if hours == 0:
self.report_writedescription(descfn)
with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
descfile.write(info_dict['description'])
+ except (KeyError, TypeError):
+ self.report_warning(u'There\'s no description to write.')
except (OSError, IOError):
self.report_error(u'Cannot write description file ' + descfn)
return
'Albert Kim',
'Pierre Rudloff',
'Huarong Huo',
+ 'Ismael Mejía',
)
__license__ = 'Public Domain'
subtitles.add_option('--write-sub', '--write-srt',
action='store_true', dest='writesubtitles',
- help='write subtitle file (currently youtube only)', default=False)
+ help='write subtitle file', default=False)
subtitles.add_option('--write-auto-sub', '--write-automatic-sub',
action='store_true', dest='writeautomaticsub',
- help='write automatic subtitle file (currently youtube only)', default=False)
- subtitles.add_option('--only-sub',
- action='store_true', dest='skip_download',
- help='[deprecated] alias of --skip-download', default=False)
+ help='write automatic subtitle file (youtube only)', default=False)
subtitles.add_option('--all-subs',
action='store_true', dest='allsubtitles',
help='downloads all the available subtitles of the video', default=False)
action='store', dest='subtitlesformat', metavar='FORMAT',
help='subtitle format (default=srt) ([sbv/vtt] youtube only)', default='srt')
subtitles.add_option('--sub-lang', '--sub-langs', '--srt-lang',
- action='callback', dest='subtitleslang', metavar='LANGS', type='str',
+ action='callback', dest='subtitleslangs', metavar='LANGS', type='str',
default=[], callback=_comma_separated_values_options_callback,
help='languages of the subtitles to download (optional) separated by commas, use IETF language tags like \'en,pt\'')
'allsubtitles': opts.allsubtitles,
'listsubtitles': opts.listsubtitles,
'subtitlesformat': opts.subtitlesformat,
- 'subtitleslangs': opts.subtitleslang,
+ 'subtitleslangs': opts.subtitleslangs,
'matchtitle': decodeOption(opts.matchtitle),
'rejecttitle': decodeOption(opts.rejecttitle),
'max_downloads': opts.max_downloads,
from .exfm import ExfmIE
from .facebook import FacebookIE
from .flickr import FlickrIE
+from .francetv import (
+ PluzzIE,
+ FranceTvInfoIE,
+)
from .freesound import FreesoundIE
from .funnyordie import FunnyOrDieIE
from .gamespot import GameSpotIE
from .rtlnow import RTLnowIE
from .sina import SinaIE
from .slashdot import SlashdotIE
+from .slideshare import SlideshareIE
from .sohu import SohuIE
from .soundcloud import SoundcloudIE, SoundcloudSetIE
from .spiegel import SpiegelIE
class Canalc2IE(InfoExtractor):
- _IE_NAME = 'canalc2.tv'
+ IE_NAME = 'canalc2.tv'
_VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?idVideo=(\d+)&voir=oui'
_TEST = {
+# encoding: utf-8
import re
import xml.etree.ElementTree
from ..utils import unified_strdate
class CanalplusIE(InfoExtractor):
- _VALID_URL = r'https?://(www\.canalplus\.fr/.*?\?vid=|player\.canalplus\.fr/#/)(?P<id>\d+)'
+ _VALID_URL = r'https?://(www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>\d+))'
_VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s'
IE_NAME = u'canalplus.fr'
_TEST = {
- u'url': u'http://www.canalplus.fr/c-divertissement/pid3351-c-le-petit-journal.html?vid=889861',
- u'file': u'889861.flv',
- u'md5': u'590a888158b5f0d6832f84001fbf3e99',
+ u'url': u'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
+ u'file': u'922470.flv',
u'info_dict': {
- u'title': u'Le Petit Journal 20/06/13 - La guerre des drone',
- u'upload_date': u'20130620',
+ u'title': u'Zapping - 26/08/13',
+ u'description': u'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
+ u'upload_date': u'20130826',
+ },
+ u'params': {
+ u'skip_download': True,
},
- u'skip': u'Requires rtmpdump'
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
+ if video_id is None:
+ webpage = self._download_webpage(url, mobj.group('path'))
+ video_id = self._search_regex(r'videoId = "(\d+)";', webpage, u'video id')
info_url = self._VIDEO_INFO_TEMPLATE % video_id
info_page = self._download_webpage(info_url,video_id,
u'Downloading video info')
'ext': 'flv',
'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
'thumbnail': media.find('IMAGES/GRAND').text,
+ 'description': infos.find('DESCRIPTION').text,
+ 'view_count': int(infos.find('NB_VUES').text),
}
import itertools
from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
+
from ..utils import (
compat_urllib_request,
+ compat_str,
get_element_by_attribute,
get_element_by_id,
ExtractorError,
)
-class DailymotionIE(InfoExtractor):
+
+class DailymotionIE(SubtitlesInfoExtractor):
"""Information Extractor for Dailymotion"""
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)'
raise ExtractorError(u'Unable to extract video URL')
video_url = info[max_quality]
+ # subtitles
+ video_subtitles = self.extract_subtitles(video_id)
+ if self._downloader.params.get('listsubtitles', False):
+ self._list_available_subtitles(video_id)
+ return
+
return [{
'id': video_id,
'url': video_url,
'upload_date': video_upload_date,
'title': self._og_search_title(webpage),
'ext': video_extension,
+ 'subtitles': video_subtitles,
'thumbnail': info['thumbnail_url']
}]
+ def _get_available_subtitles(self, video_id):
+ try:
+ sub_list = self._download_webpage(
+ 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
+ video_id, note=False)
+ except ExtractorError as err:
+ self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
+ return {}
+ info = json.loads(sub_list)
+ if (info['total'] > 0):
+ sub_lang_list = dict((l['language'], l['url']) for l in info['list'])
+ return sub_lang_list
+ self._downloader.report_warning(u'video doesn\'t have subtitles')
+ return {}
+
class DailymotionPlaylistIE(InfoExtractor):
_VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
--- /dev/null
+# encoding: utf-8
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urlparse,
+)
+
+
+class FranceTVBaseInfoExtractor(InfoExtractor):
+ def _extract_video(self, video_id):
+ xml_desc = self._download_webpage(
+ 'http://www.francetvinfo.fr/appftv/webservices/video/'
+ 'getInfosOeuvre.php?id-diffusion='
+ + video_id, video_id, 'Downloading XML config')
+ info = xml.etree.ElementTree.fromstring(xml_desc.encode('utf-8'))
+
+ manifest_url = info.find('videos/video/url').text
+ video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8')
+ video_url = video_url.replace('/z/', '/i/')
+ thumbnail_path = info.find('image').text
+
+ return {'id': video_id,
+ 'ext': 'mp4',
+ 'url': video_url,
+ 'title': info.find('titre').text,
+ 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path),
+ 'description': info.find('synopsis').text,
+ }
+
+
+class PluzzIE(FranceTVBaseInfoExtractor):
+ IE_NAME = u'pluzz.francetv.fr'
+ _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
+
+ _TEST = {
+ u'url': u'http://pluzz.francetv.fr/videos/allo_rufo_saison5_,88439064.html',
+ u'file': u'88439064.mp4',
+ u'info_dict': {
+ u'title': u'Allô Rufo',
+ u'description': u'md5:d909f1ebdf963814b65772aea250400e',
+ },
+ u'params': {
+ u'skip_download': True,
+ },
+ }
+
+ def _real_extract(self, url):
+ title = re.match(self._VALID_URL, url).group(1)
+ webpage = self._download_webpage(url, title)
+ video_id = self._search_regex(
+ r'data-diffusion="(\d+)"', webpage, 'ID')
+ return self._extract_video(video_id)
+
+
+class FranceTvInfoIE(FranceTVBaseInfoExtractor):
+ IE_NAME = u'francetvinfo.fr'
+ _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+).html'
+
+ _TEST = {
+ u'url': u'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
+ u'file': u'84981923.mp4',
+ u'info_dict': {
+ u'title': u'Soir 3',
+ },
+ u'params': {
+ u'skip_download': True,
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ page_title = mobj.group('title')
+ webpage = self._download_webpage(url, page_title)
+ video_id = self._search_regex(r'id-video=(\d+?)"', webpage, u'video id')
+ return self._extract_video(video_id)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
- video_url = self._search_regex(r'type: "video/mp4", src: "(.*?)"',
+ video_url = self._search_regex(r'type="video/mp4" src="(.*?)"',
webpage, u'video URL', flags=re.DOTALL)
info = {
u"file": u"6410818.mp4",
u"md5": u"b2a30deaa8654fcccd43713a6b6a4825",
u"info_dict": {
- u"title": u"Arma III - Community Guide: SITREP I",
+ u"title": u"Arma 3 - Community Guide: SITREP I",
u"upload_date": u"20130627",
}
}
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
- webpage_url = 'http://www.howcast.com/videos/' + video_id
- webpage = self._download_webpage(webpage_url, video_id)
+ webpage = self._download_webpage(url, video_id)
self.report_extraction(video_id)
class KickStarterIE(InfoExtractor):
- _VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>.*)/.*\?'
+ _VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>\d*)/.*'
_TEST = {
- "url": "https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant?ref=home_location",
- "file": "1404461844.mp4",
- "md5": "c81addca81327ffa66c642b5d8b08cab",
- "info_dict": {
- "title": u"Intersection: The Story of Josh Grant by Kyle Cowling \u2014 Kickstarter"
- }
+ u"url": u"https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant?ref=home_location",
+ u"file": u"1404461844.mp4",
+ u"md5": u"c81addca81327ffa66c642b5d8b08cab",
+ u"info_dict": {
+ u"title": u"Intersection: The Story of Josh Grant by Kyle Cowling",
+ },
}
-
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('id')
-
webpage_src = self._download_webpage(url, video_id)
video_url = self._search_regex(r'data-video="(.*?)">',
webpage_src, u'video URL')
-
if 'mp4' in video_url:
ext = 'mp4'
else:
ext = 'flv'
-
- video_title = self._html_search_regex(r"<title>(.*)</title>?",
- webpage_src, u'title')
-
+ video_title = self._html_search_regex(r"<title>(.*?)</title>",
+ webpage_src, u'title').rpartition(u'\u2014 Kickstarter')[0].strip()
results = [{
'id': video_id,
- 'url' : video_url,
- 'title' : video_title,
- 'ext' : ext,
+ 'url': video_url,
+ 'title': video_title,
+ 'ext': ext,
}]
-
- return results
\ No newline at end of file
+ return results
--- /dev/null
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urlparse,
+ ExtractorError,
+)
+
+
+class SlideshareIE(InfoExtractor):
+ _VALID_URL = r'https?://www\.slideshare\.net/[^/]+?/(?P<title>.+?)($|\?)'
+
+ _TEST = {
+ u'url': u'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity',
+ u'file': u'25665706.mp4',
+ u'info_dict': {
+ u'title': u'Managing Scale and Complexity',
+ u'description': u'This was a keynote presentation at the NoSQL Now! 2013 Conference & Expo (http://www.nosqlnow.com). This presentation was given by Adrian Cockcroft from Netflix',
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ page_title = mobj.group('title')
+ webpage = self._download_webpage(url, page_title)
+ slideshare_obj = self._search_regex(
+ r'var slideshare_object = ({.*?}); var user_info =',
+ webpage, u'slideshare object')
+ info = json.loads(slideshare_obj)
+ if info['slideshow']['type'] != u'video':
+ raise ExtractorError(u'Webpage type is "%s": only video extraction is supported for Slideshare' % info['slideshow']['type'], expected=True)
+
+ doc = info['doc']
+ bucket = info['jsplayer']['video_bucket']
+ ext = info['jsplayer']['video_extension']
+ video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext)
+
+ return {
+ '_type': 'video',
+ 'id': info['slideshow']['id'],
+ 'title': info['slideshow']['title'],
+ 'ext': ext,
+ 'url': video_url,
+ 'thumbnail': info['slideshow']['pin_image_url'],
+ 'description': self._og_search_description(webpage),
+ }
class SohuIE(InfoExtractor):
- _VALID_URL = r'https?://tv\.sohu\.com/\d+?/n(?P<id>\d+)\.shtml.*?'
+ _VALID_URL = r'https?://(?P<mytv>my\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P<id>\d+)\.shtml.*?'
_TEST = {
u'url': u'http://tv.sohu.com/20130724/n382479172.shtml#super',
def _real_extract(self, url):
- def _fetch_data(vid_id):
- base_data_url = u'http://hot.vrs.sohu.com/vrs_flash.action?vid='
+ def _fetch_data(vid_id, mytv=False):
+ if mytv:
+ base_data_url = 'http://my.tv.sohu.com/play/videonew.do?vid='
+ else:
+ base_data_url = u'http://hot.vrs.sohu.com/vrs_flash.action?vid='
data_url = base_data_url + str(vid_id)
data_json = self._download_webpage(
data_url, video_id,
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
+ mytv = mobj.group('mytv') is not None
webpage = self._download_webpage(url, video_id)
raw_title = self._html_search_regex(r'(?s)<title>(.+?)</title>',
webpage, u'video title')
title = raw_title.partition('-')[0].strip()
- vid = self._html_search_regex(r'var vid="(\d+)"', webpage,
+ vid = self._html_search_regex(r'var vid ?= ?["\'](\d+)["\']', webpage,
u'video path')
- data = _fetch_data(vid)
+ data = _fetch_data(vid, mytv)
QUALITIES = ('ori', 'super', 'high', 'nor')
vid_ids = [data['data'][q + 'Vid']
# For now, we just pick the highest available quality
vid_id = vid_ids[-1]
- format_data = data if vid == vid_id else _fetch_data(vid_id)
+ format_data = data if vid == vid_id else _fetch_data(vid_id, mytv)
part_count = format_data['data']['totalBlocks']
allot = format_data['allot']
prot = format_data['prot']
--- /dev/null
+from .common import InfoExtractor
+
+from ..utils import (
+ compat_str,
+ ExtractorError,
+)
+
+
+class SubtitlesInfoExtractor(InfoExtractor):
+ @property
+ def _have_to_download_any_subtitles(self):
+ return any([self._downloader.params.get('writesubtitles', False),
+ self._downloader.params.get('writeautomaticsub'),
+ self._downloader.params.get('allsubtitles', False)])
+
+ def _list_available_subtitles(self, video_id, webpage=None):
+ """ outputs the available subtitles for the video """
+ sub_lang_list = self._get_available_subtitles(video_id)
+ auto_captions_list = self._get_available_automatic_caption(video_id, webpage)
+ sub_lang = ",".join(list(sub_lang_list.keys()))
+ self.to_screen(u'%s: Available subtitles for video: %s' %
+ (video_id, sub_lang))
+ auto_lang = ",".join(auto_captions_list.keys())
+ self.to_screen(u'%s: Available automatic captions for video: %s' %
+ (video_id, auto_lang))
+
+ def extract_subtitles(self, video_id, video_webpage=None):
+ """
+ returns {sub_lang: sub} ,{} if subtitles not found or None if the
+ subtitles aren't requested.
+ """
+ if not self._have_to_download_any_subtitles:
+ return None
+ available_subs_list = {}
+ if self._downloader.params.get('writeautomaticsub', False):
+ available_subs_list.update(self._get_available_automatic_caption(video_id, video_webpage))
+ if self._downloader.params.get('writesubtitles', False) or self._downloader.params.get('allsubtitles', False):
+ available_subs_list.update(self._get_available_subtitles(video_id))
+
+ if not available_subs_list: # error, it didn't get the available subtitles
+ return {}
+ if self._downloader.params.get('allsubtitles', False):
+ sub_lang_list = available_subs_list
+ else:
+ if self._downloader.params.get('subtitleslangs', False):
+ requested_langs = self._downloader.params.get('subtitleslangs')
+ elif 'en' in available_subs_list:
+ requested_langs = ['en']
+ else:
+ requested_langs = [list(available_subs_list.keys())[0]]
+
+ sub_lang_list = {}
+ for sub_lang in requested_langs:
+ if not sub_lang in available_subs_list:
+ self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang)
+ continue
+ sub_lang_list[sub_lang] = available_subs_list[sub_lang]
+
+ subtitles = {}
+ for sub_lang, url in sub_lang_list.items():
+ subtitle = self._request_subtitle_url(sub_lang, url)
+ if subtitle:
+ subtitles[sub_lang] = subtitle
+ return subtitles
+
+ def _request_subtitle_url(self, sub_lang, url):
+ """ makes the http request for the subtitle """
+ try:
+ sub = self._download_webpage(url, None, note=False)
+ except ExtractorError as err:
+ self._downloader.report_warning(u'unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err)))
+ return
+ if not sub:
+ self._downloader.report_warning(u'Did not fetch video subtitles')
+ return
+ return sub
+
+ def _get_available_subtitles(self, video_id):
+ """
+ returns {sub_lang: url} or {} if not available
+ Must be redefined by the subclasses
+ """
+ pass
+
+ def _get_available_automatic_caption(self, video_id, webpage):
+ """
+ returns {sub_lang: url} or {} if not available
+ Must be redefined by the subclasses that support automatic captions,
+ otherwise it will return {}
+ """
+ self._downloader.report_warning(u'Automatic Captions not supported by this server')
+ return {}
import re
import socket
import itertools
+import xml.etree.ElementTree
from .common import InfoExtractor, SearchInfoExtractor
+from .subtitles import SubtitlesInfoExtractor
from ..utils import (
compat_http_client,
compat_parse_qs,
return
self._confirm_age()
-class YoutubeIE(YoutubeBaseInfoExtractor):
+
+class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
IE_DESC = u'YouTube.com'
_VALID_URL = r"""^
(
|youtu\.be/ # just youtu.be/xxxx
)
)? # all until now is optional -> you can pass the naked ID
- ([0-9A-Za-z_-]+) # here is it! the YouTube video ID
+ ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
(?(1).+)? # if we found the ID, everything can follow
$"""
_NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
"""Report attempt to download video info webpage."""
self.to_screen(u'%s: Downloading video info webpage' % video_id)
- def report_video_subtitles_download(self, video_id):
- """Report attempt to download video info webpage."""
- self.to_screen(u'%s: Checking available subtitles' % video_id)
-
- def report_video_subtitles_request(self, video_id, sub_lang, format):
- """Report attempt to download video info webpage."""
- self.to_screen(u'%s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format))
-
- def report_video_subtitles_available(self, video_id, sub_lang_list):
- """Report available subtitles."""
- sub_lang = ",".join(list(sub_lang_list.keys()))
- self.to_screen(u'%s: Available subtitles for video: %s' % (video_id, sub_lang))
-
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
self.to_screen(u'%s: Extracting video information' % video_id)
elif len(s) == 86:
return s[5:34] + s[0] + s[35:38] + s[3] + s[39:45] + s[38] + s[46:53] + s[73] + s[54:73] + s[85] + s[74:85] + s[53]
elif len(s) == 85:
- return s[83:34:-1] + s[0] + s[33:27:-1] + s[3] + s[26:19:-1] + s[34] + s[18:3:-1] + s[27]
+ return s[40] + s[82:43:-1] + s[22] + s[42:40:-1] + s[83] + s[39:22:-1] + s[0] + s[21:2:-1]
elif len(s) == 84:
return s[81:36:-1] + s[0] + s[35:2:-1]
elif len(s) == 83:
return s[81:64:-1] + s[82] + s[63:52:-1] + s[45] + s[51:45:-1] + s[1] + s[44:1:-1] + s[0]
elif len(s) == 82:
- return s[1:19] + s[0] + s[20:68] + s[19] + s[69:82]
+ return s[80:73:-1] + s[81] + s[72:54:-1] + s[2] + s[53:43:-1] + s[0] + s[42:2:-1] + s[43] + s[1] + s[54]
elif len(s) == 81:
return s[56] + s[79:56:-1] + s[41] + s[55:41:-1] + s[80] + s[40:34:-1] + s[0] + s[33:29:-1] + s[34] + s[28:9:-1] + s[29] + s[8:0:-1] + s[9]
elif len(s) == 80:
# Fallback to the other algortihms
return self._decrypt_signature(s)
-
def _get_available_subtitles(self, video_id):
- self.report_video_subtitles_download(video_id)
- request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
try:
- sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ sub_list = self._download_webpage(
+ 'http://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))
return {}
- sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)
- sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list)
+ lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)
+
+ sub_lang_list = {}
+ for l in lang_list:
+ lang = l[1]
+ params = compat_urllib_parse.urlencode({
+ 'lang': lang,
+ 'v': video_id,
+ 'fmt': self._downloader.params.get('subtitlesformat'),
+ })
+ url = u'http://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')
return {}
return sub_lang_list
- def _list_available_subtitles(self, video_id):
- sub_lang_list = self._get_available_subtitles(video_id)
- self.report_video_subtitles_available(video_id, sub_lang_list)
-
- def _request_subtitle(self, sub_lang, sub_name, video_id, format):
- """
- Return the subtitle as a string or None if they are not found
- """
- self.report_video_subtitles_request(video_id, sub_lang, format)
- params = compat_urllib_parse.urlencode({
- 'lang': sub_lang,
- 'name': sub_name,
- 'v': video_id,
- 'fmt': format,
- })
- url = 'http://www.youtube.com/api/timedtext?' + params
- try:
- sub = compat_urllib_request.urlopen(url).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_warning(u'unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err)))
- return
- if not sub:
- self._downloader.report_warning(u'Did not fetch video subtitles')
- return
- return sub
-
- def _request_automatic_caption(self, video_id, webpage):
+ def _get_available_automatic_caption(self, video_id, webpage):
"""We need the webpage for getting the captions url, pass it as an
argument to speed up the process."""
- sub_lang = (self._downloader.params.get('subtitleslangs') or ['en'])[0]
sub_format = self._downloader.params.get('subtitlesformat')
self.to_screen(u'%s: Looking for automatic captions' % video_id)
mobj = re.search(r';ytplayer.config = ({.*?});', webpage)
- err_msg = u'Couldn\'t find automatic captions for "%s"' % sub_lang
+ err_msg = u'Couldn\'t find automatic captions for %s' % video_id
if mobj is None:
self._downloader.report_warning(err_msg)
return {}
args = player_config[u'args']
caption_url = args[u'ttsurl']
timestamp = args[u'timestamp']
- params = compat_urllib_parse.urlencode({
- 'lang': 'en',
- 'tlang': sub_lang,
- 'fmt': sub_format,
- 'ts': timestamp,
- 'kind': 'asr',
+ # We get the available subtitles
+ list_params = compat_urllib_parse.urlencode({
+ 'type': 'list',
+ 'tlangs': 1,
+ 'asrs': 1,
})
- subtitles_url = caption_url + '&' + params
- sub = self._download_webpage(subtitles_url, video_id, u'Downloading automatic captions')
- return {sub_lang: sub}
+ list_url = caption_url + '&' + list_params
+ list_page = self._download_webpage(list_url, video_id)
+ caption_list = xml.etree.ElementTree.fromstring(list_page.encode('utf-8'))
+ original_lang_node = caption_list.find('track')
+ if original_lang_node.attrib.get('kind') != 'asr' :
+ self._downloader.report_warning(u'Video doesn\'t have automatic captions')
+ return {}
+ original_lang = original_lang_node.attrib['lang_code']
+
+ sub_lang_list = {}
+ for lang_node in caption_list.findall('target'):
+ sub_lang = lang_node.attrib['lang_code']
+ params = compat_urllib_parse.urlencode({
+ 'lang': original_lang,
+ 'tlang': sub_lang,
+ 'fmt': sub_format,
+ 'ts': timestamp,
+ 'kind': 'asr',
+ })
+ sub_lang_list[sub_lang] = caption_url + '&' + params
+ return sub_lang_list
# An extractor error can be raise by the download process if there are
# no automatic captions but there are subtitles
except (KeyError, ExtractorError):
self._downloader.report_warning(err_msg)
return {}
-
- def _extract_subtitles(self, video_id):
- """
- Return a dictionary: {language: subtitles} or {} if the subtitles
- couldn't be found
- """
- available_subs_list = self._get_available_subtitles(video_id)
- sub_format = self._downloader.params.get('subtitlesformat')
- if not available_subs_list: #There was some error, it didn't get the available subtitles
- return {}
- if self._downloader.params.get('allsubtitles', False):
- sub_lang_list = available_subs_list
- else:
- if self._downloader.params.get('subtitleslangs', False):
- reqested_langs = self._downloader.params.get('subtitleslangs')
- elif 'en' in available_subs_list:
- reqested_langs = ['en']
- else:
- reqested_langs = [list(available_subs_list.keys())[0]]
-
- sub_lang_list = {}
- for sub_lang in reqested_langs:
- if not sub_lang in available_subs_list:
- self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang)
- continue
- sub_lang_list[sub_lang] = available_subs_list[sub_lang]
- subtitles = {}
- for sub_lang in sub_lang_list:
- subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
- if subtitle:
- subtitles[sub_lang] = subtitle
- return subtitles
def _print_formats(self, formats):
print('Available formats:')
manifest = self._download_webpage(manifest_url, video_id, u'Downloading formats manifest')
formats_urls = _get_urls(manifest)
for format_url in formats_urls:
- itag = self._search_regex(r'itag%3D(\d+?)/', format_url, 'itag')
+ itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag')
url_map[itag] = format_url
return url_map
video_description = u''
# subtitles
- video_subtitles = None
-
- if self._downloader.params.get('writesubtitles', False) or self._downloader.params.get('allsubtitles', False):
- video_subtitles = self._extract_subtitles(video_id)
- elif self._downloader.params.get('writeautomaticsub', False):
- video_subtitles = self._request_automatic_caption(video_id, video_webpage)
+ video_subtitles = self.extract_subtitles(video_id, video_webpage)
if self._downloader.params.get('listsubtitles', False):
- self._list_available_subtitles(video_id)
+ self._list_available_subtitles(video_id, video_webpage)
return
if 'length_seconds' not in video_info:
-__version__ = '2013.09.06.1'
+__version__ = '2013.09.12'
projects / youtube-dl / commitdiff