Robin de Rooij
Ryan Schmidt
Leslie P. Polzer
+Duncan Keall
dislike_count <? 50 & description" .
--no-playlist If the URL refers to a video and a
playlist, download only the video.
+ --yes-playlist If the URL refers to a video and a
+ playlist, download the playlist.
--age-limit YEARS download only videos suitable for the given
age
--download-archive FILE Download only videos not listed in the
self.assertEqual(parse_duration('2.5 hours'), 9000)
self.assertEqual(parse_duration('02:03:04'), 7384)
self.assertEqual(parse_duration('01:02:03:04'), 93784)
+ self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
def test_fix_xml_ampersands(self):
self.assertEqual(
from .adultswim import AdultSwimIE
from .aftenposten import AftenpostenIE
from .aftonbladet import AftonbladetIE
+from .airmozilla import AirMozillaIE
from .aljazeera import AlJazeeraIE
from .alphaporno import AlphaPornoIE
from .anitube import AnitubeIE
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ int_or_none,
+ parse_duration,
+ parse_iso8601,
+)
+
+
+class AirMozillaIE(InfoExtractor):
+ _VALID_URL = r'https?://air\.mozilla\.org/(?P<id>[0-9a-z-]+)/?'
+ _TEST = {
+ 'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/',
+ 'md5': '2e3e7486ba5d180e829d453875b9b8bf',
+ 'info_dict': {
+ 'id': '6x4q2w',
+ 'ext': 'mp4',
+ 'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',
+ 'thumbnail': 're:https://\w+\.cloudfront\.net/6x4q2w/poster\.jpg\?t=\d+',
+ 'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...',
+ 'timestamp': 1422487800,
+ 'upload_date': '20150128',
+ 'location': 'SFO Commons',
+ 'duration': 3780,
+ 'view_count': int,
+ 'categories': ['Main'],
+ }
+ }
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+ webpage = self._download_webpage(url, display_id)
+ video_id = self._html_search_regex(r'//vid.ly/(.*?)/embed', webpage, 'id')
+
+ embed_script = self._download_webpage('https://vid.ly/{0}/embed'.format(video_id), video_id)
+ jwconfig = self._search_regex(r'\svar jwconfig = (\{.*?\});\s', embed_script, 'metadata')
+ metadata = self._parse_json(jwconfig, video_id)
+
+ formats = [{
+ 'url': source['file'],
+ 'ext': source['type'],
+ 'format_id': self._search_regex(r'&format=(.*)$', source['file'], 'video format'),
+ 'format': source['label'],
+ 'height': int(source['label'].rstrip('p')),
+ } for source in metadata['playlist'][0]['sources']]
+ self._sort_formats(formats)
+
+ view_count = int_or_none(self._html_search_regex(
+ r'Views since archived: ([0-9]+)',
+ webpage, 'view count', fatal=False))
+ timestamp = parse_iso8601(self._html_search_regex(
+ r'<time datetime="(.*?)"', webpage, 'timestamp', fatal=False))
+ duration = parse_duration(self._search_regex(
+ r'Duration:\s*(\d+\s*hours?\s*\d+\s*minutes?)',
+ webpage, 'duration', fatal=False))
+
+ return {
+ 'id': video_id,
+ 'title': self._og_search_title(webpage),
+ 'formats': formats,
+ 'url': self._og_search_url(webpage),
+ 'display_id': display_id,
+ 'thumbnail': metadata['playlist'][0].get('image'),
+ 'description': self._og_search_description(webpage),
+ 'timestamp': timestamp,
+ 'location': self._html_search_regex(r'Location: (.*)', webpage, 'location', default=None),
+ 'duration': duration,
+ 'view_count': view_count,
+ 'categories': re.findall(r'<a href=".*?" class="channel">(.*?)</a>', webpage),
+ }
title = self._html_search_regex(
r'<title>(.*?) - EPORNER', webpage, 'title')
- redirect_code = self._html_search_regex(
- r'<script type="text/javascript" src="/config5/%s/([a-f\d]+)/">' % video_id,
- webpage, 'redirect_code')
- redirect_url = 'http://www.eporner.com/config5/%s/%s' % (video_id, redirect_code)
+ redirect_url = 'http://www.eporner.com/config5/%s' % video_id
player_code = self._download_webpage(
redirect_url, display_id, note='Downloading player config')
'duration': duration,
'view_count': view_count,
'formats': formats,
- 'age_limit': self._rta_search(webpage),
+ 'age_limit': 18,
}
config_url = compat_urllib_parse.unquote(self._html_search_regex(
r'''(?x)
(?:
- <param\s+name="flashvars"\s+value="config=|
+ <param\s+name="flashvars".*?\s+value="config=|
flashvars="config=
)
- ([^"&]+)
+ (https?://[^"&]+)
''',
webpage, 'config URL'))
formats = []
+ ad_formats = []
def _add_format(name, cfgurl, quality):
config = self._download_json(
transform_source=js_to_json)
playlist = config['playlist']
- video_url = next(
- p['url'] for p in playlist
- if p.get('eventCategory') == 'Video')
- formats.append({
- 'url': video_url,
- 'format_id': name,
- 'quality': quality,
- })
+ for p in playlist:
+ if p.get('eventCategory') == 'Video':
+ ar = formats
+ elif p.get('eventCategory') == 'Video Postroll':
+ ar = ad_formats
+ else:
+ continue
+
+ ar.append({
+ 'url': p['url'],
+ 'format_id': name,
+ 'quality': quality,
+ })
_add_format('normal', config_url, quality=0)
hq_url = (config_url +
_add_format('hq', hq_url, quality=1)
except ExtractorError:
pass # That's fine, we'll just use normal quality
-
self._sort_formats(formats)
- return {
+ res = {
'id': video_id,
'formats': formats,
'uploader': uploader,
'thumbnail': self._og_search_thumbnail(webpage),
'description': description,
}
+
+ if self._downloader.params.get('include_ads') and ad_formats:
+ self._sort_formats(ad_formats)
+ ad_res = {
+ 'id': '%s-ad' % video_id,
+ 'title': '%s (Postroll)' % title,
+ 'formats': ad_formats,
+ }
+ return {
+ '_type': 'playlist',
+ 'entries': [res, ad_res],
+ 'title': title,
+ 'id': video_id,
+ }
+
+ return res
return entries[0]
else:
for num, e in enumerate(entries, start=1):
- e['title'] = '%s (%d)' % (e['title'], num)
+ # 'url' results don't have a title
+ if e.get('title') is not None:
+ e['title'] = '%s (%d)' % (e['title'], num)
return {
'_type': 'playlist',
'entries': entries,
IE_NAME = 'mitele.es'
_VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
'md5': '6a75fe9d0d3275bead0cb683c616fddb',
'info_dict': {
'display_id': 'programa-144',
'duration': 2913,
},
- }
+ }]
def _real_extract(self, url):
episode = self._match_id(url)
import re
from .common import InfoExtractor
+from ..compat import compat_str
from ..utils import (
ExtractorError,
float_or_none,
def _get_subtitles(self, subtitlesurl, video_id, baseurl):
url = "%s%s" % (baseurl, subtitlesurl)
self._debug_print('%s: Subtitle url: %s' % (video_id, url))
- captions = self._download_xml(url, video_id, 'Downloading subtitles')
+ captions = self._download_xml(
+ url, video_id, 'Downloading subtitles',
+ transform_source=lambda s: s.replace(r'<br />', '\r\n'))
lang = captions.get('lang', 'no')
ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/ns/ttml}'))
srt = ''
duration = parse_duration(p.get('dur'))
starttime = self._seconds2str(begin)
endtime = self._seconds2str(begin + duration)
- text = '\n'.join(p.itertext())
- srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), starttime, endtime, text)
+ srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (compat_str(pos), starttime, endtime, p.text)
return {lang: [
{'ext': 'ttml', 'url': url},
{'ext': 'srt', 'data': srt},
mobj = re.search(r'.*/(?P<hoster>[^/]+)/videos/(?P<play_path>.+)\.f4m', filename.text)
if mobj:
fmt = {
- 'url': 'rtmpe://fmspay-fra2.rtl.de/' + mobj.group('hoster'),
+ 'url': 'rtmpe://fms.rtl.de/' + mobj.group('hoster'),
'play_path': 'mp4:' + mobj.group('play_path'),
'page_url': url,
'player_url': video_page_url + 'includes/vodplayer.swf',
class TelecincoIE(MiTeleIE):
IE_NAME = 'telecinco.es'
- _VALID_URL = r'https?://www\.telecinco\.es/[^/]+/[^/]+/[^/]+/(?P<id>.*?)\.html'
+ _VALID_URL = r'https?://www\.telecinco\.es/[^/]+/[^/]+/(?:[^/]+/)?(?P<id>.*?)\.html'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.telecinco.es/robinfood/temporada-01/t01xp14/Bacalao-cocochas-pil-pil_0_1876350223.html',
'info_dict': {
'id': 'MDSVID20141015_0058',
'title': 'Con MartÃn Berasategui, hacer un bacalao al ...',
'duration': 662,
},
- }
+ }, {
+ 'url': 'http://www.telecinco.es/informativos/nacional/Pablo_Iglesias-Informativos_Telecinco-entrevista-Pedro_Piqueras_2_1945155182.html',
+ 'only_matching': True,
+ }]
'--no-playlist',
action='store_true', dest='noplaylist', default=False,
help='If the URL refers to a video and a playlist, download only the video.')
+ selection.add_option(
+ '--yes-playlist',
+ action='store_false', dest='noplaylist', default=False,
+ help='If the URL refers to a video and a playlist, download the playlist.')
selection.add_option(
'--age-limit',
metavar='YEARS', dest='age_limit', default=None, type=int,
compiled_regex_type = type(re.compile(''))
std_headers = {
- 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0 (Chrome)',
+ 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/20.0 (Chrome)',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate',
(?P<only_mins>[0-9.]+)\s*(?:mins?|minutes?)\s*|
(?P<only_hours>[0-9.]+)\s*(?:hours?)|
+ \s*(?P<hours_reversed>[0-9]+)\s*(?:[:h]|hours?)\s*(?P<mins_reversed>[0-9]+)\s*(?:[:m]|mins?|minutes?)\s*|
(?:
(?:
(?:(?P<days>[0-9]+)\s*(?:[:d]|days?)\s*)?
return float_or_none(m.group('only_hours'), invscale=60 * 60)
if m.group('secs'):
res += int(m.group('secs'))
+ if m.group('mins_reversed'):
+ res += int(m.group('mins_reversed')) * 60
if m.group('mins'):
res += int(m.group('mins')) * 60
if m.group('hours'):
res += int(m.group('hours')) * 60 * 60
+ if m.group('hours_reversed'):
+ res += int(m.group('hours_reversed')) * 60 * 60
if m.group('days'):
res += int(m.group('days')) * 24 * 60 * 60
if m.group('ms'):
from __future__ import unicode_literals
-__version__ = '2015.02.24.2'
+__version__ = '2015.02.26'
projects / youtube-dl.git / commitdiff