Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-22 05:47:15 +08:00
Code Issues Releases Wiki Activity

Merge branch 'master' into Vimeo-issue-16717

Browse Source
This commit is contained in:
Parmjit Virk 2018-07-21 15:53:28 -05:00
commit 1b4d8e8573
58 changed files with 295 additions and 155 deletions

6
.github/ISSUE_TEMPLATE.md vendored

@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.07.10*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.07.10**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.07.21*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.07.21**
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2018.07.10
[debug] youtube-dl version 2018.07.21
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

23
ChangeLog

@ -1,3 +1,26 @@
version 2018.07.21
Core
+ [utils] Introduce url_or_none
* [utils] Allow JSONP without function name (#17028)
+ [extractor/common] Extract DASH and MSS formats from SMIL manifests
Extractors
+ [bbc] Add support for BBC Radio Play pages (#17022)
* [iwara] Fix download URLs (#17026)
* [vrtnu] Relax title extraction and extract JSON-LD (#17018)
+ [viu] Pass Referer and Origin headers and area id (#16992)
+ [vimeo] Add another config regular expression (#17013)
+ [facebook] Extract view count (#16942)
* [dailymotion] Improve description extraction (#16984)
* [slutload] Fix and improve extraction (#17001)
* [mediaset] Fix extraction (#16977)
+ [theplatform] Add support for theplatform TLD customization (#16977)
* [imgur] Relax URL regular expression (#16987)
* [pornhub] Improve extraction and extract all formats (#12166, #15891, #16262,
#16959)
version 2018.07.10
Core

15
test/test_utils.py

@ -78,6 +78,7 @@ from youtube_dl.utils import (
uppercase_escape,
lowercase_escape,
url_basename,
url_or_none,
base_url,
urljoin,
urlencode_postdata,
@ -507,6 +508,16 @@ class TestUtil(unittest.TestCase):
self.assertEqual(urljoin('http://foo.de/', ['foobar']), None)
self.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt')
def test_url_or_none(self):
self.assertEqual(url_or_none(None), None)
self.assertEqual(url_or_none(''), None)
self.assertEqual(url_or_none('foo'), None)
self.assertEqual(url_or_none('http://foo.de'), 'http://foo.de')
self.assertEqual(url_or_none('https://foo.de'), 'https://foo.de')
self.assertEqual(url_or_none('http$://foo.de'), None)
self.assertEqual(url_or_none('http://foo.de'), 'http://foo.de')
self.assertEqual(url_or_none('//foo.de'), '//foo.de')
def test_parse_age_limit(self):
self.assertEqual(parse_age_limit(None), None)
self.assertEqual(parse_age_limit(False), None)
@ -717,6 +728,10 @@ class TestUtil(unittest.TestCase):
d = json.loads(stripped)
self.assertEqual(d, {'status': 'success'})
stripped = strip_jsonp('({"status": "success"});')
d = json.loads(stripped)
self.assertEqual(d, {'status': 'success'})
def test_uppercase_escape(self):
self.assertEqual(uppercase_escape('aä'), 'aä')
self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')

3
youtube_dl/extractor/adultswim.py

@ -7,6 +7,7 @@ from .turner import TurnerBaseIE
from ..utils import (
int_or_none,
strip_or_none,
url_or_none,
)
@ -98,7 +99,7 @@ class AdultSwimIE(TurnerBaseIE):
if not video_id:
entries = []
for episode in video_data.get('archiveEpisodes', []):
episode_url = episode.get('url')
episode_url = url_or_none(episode.get('url'))
if not episode_url:
continue
entries.append(self.url_result(

3
youtube_dl/extractor/afreecatv.py

@ -9,6 +9,7 @@ from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
url_or_none,
urlencode_postdata,
xpath_text,
)
@ -304,7 +305,7 @@ class AfreecaTVIE(InfoExtractor):
file_elements = video_element.findall(compat_xpath('./file'))
one = len(file_elements) == 1
for file_num, file_element in enumerate(file_elements, start=1):
file_url = file_element.text
file_url = url_or_none(file_element.text)
if not file_url:
continue
key = file_element.get('key', '')

15
youtube_dl/extractor/amp.py

@ -3,11 +3,12 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_iso8601,
mimetype2ext,
determine_ext,
ExtractorError,
int_or_none,
mimetype2ext,
parse_iso8601,
url_or_none,
)
@ -35,7 +36,7 @@ class AMPIE(InfoExtractor):
media_thumbnail = [media_thumbnail]
for thumbnail_data in media_thumbnail:
thumbnail = thumbnail_data.get('@attributes', {})
thumbnail_url = thumbnail.get('url')
thumbnail_url = url_or_none(thumbnail.get('url'))
if not thumbnail_url:
continue
thumbnails.append({
@ -51,7 +52,7 @@ class AMPIE(InfoExtractor):
media_subtitle = [media_subtitle]
for subtitle_data in media_subtitle:
subtitle = subtitle_data.get('@attributes', {})
subtitle_href = subtitle.get('href')
subtitle_href = url_or_none(subtitle.get('href'))
if not subtitle_href:
continue
subtitles.setdefault(subtitle.get('lang') or 'en', []).append({
@ -65,7 +66,7 @@ class AMPIE(InfoExtractor):
media_content = [media_content]
for media_data in media_content:
media = media_data.get('@attributes', {})
media_url = media.get('url')
media_url = url_or_none(media.get('url'))
if not media_url:
continue
ext = mimetype2ext(media.get('type')) or determine_ext(media_url)
@ -79,7 +80,7 @@ class AMPIE(InfoExtractor):
else:
formats.append({
'format_id': media_data.get('media-category', {}).get('@attributes', {}).get('label'),
'url': media['url'],
'url': media_url,
'tbr': int_or_none(media.get('bitrate')),
'filesize': int_or_none(media.get('fileSize')),
'ext': ext,

3
youtube_dl/extractor/animeondemand.py

@ -8,6 +8,7 @@ from ..utils import (
determine_ext,
extract_attributes,
ExtractorError,
url_or_none,
urlencode_postdata,
urljoin,
)
@ -165,7 +166,7 @@ class AnimeOnDemandIE(InfoExtractor):
}, fatal=False)
if not playlist:
continue
stream_url = playlist.get('streamurl')
stream_url = url_or_none(playlist.get('streamurl'))
if stream_url:
rtmp = re.search(
r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+/))(?P<playpath>mp[34]:.+)',

3
youtube_dl/extractor/aol.py

@ -7,6 +7,7 @@ from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
url_or_none,
)
@ -77,7 +78,7 @@ class AolIE(InfoExtractor):
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
for rendition in video_data.get('renditions', []):
video_url = rendition.get('url')
video_url = url_or_none(rendition.get('url'))
if not video_url:
continue
ext = rendition.get('format')

6
youtube_dl/extractor/apa.py

@ -4,10 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
js_to_json,
url_or_none,
)
@ -68,8 +68,8 @@ class APAIE(InfoExtractor):
for source in sources:
if not isinstance(source, dict):
continue
source_url = source.get('file')
if not source_url or not isinstance(source_url, compat_str):
source_url = url_or_none(source.get('file'))
if not source_url:
continue
ext = determine_ext(source_url)
if ext == 'm3u8':

3
youtube_dl/extractor/aparat.py

@ -5,6 +5,7 @@ from .common import InfoExtractor
from ..utils import (
int_or_none,
mimetype2ext,
url_or_none,
)
@ -43,7 +44,7 @@ class AparatIE(InfoExtractor):
formats = []
for item in file_list[0]:
file_url = item.get('file')
file_url = url_or_none(item.get('file'))
if not file_url:
continue
ext = mimetype2ext(item.get('type'))

4
youtube_dl/extractor/ard.py

@ -5,7 +5,6 @@ import re
from .common import InfoExtractor
from .generic import GenericIE
from ..compat import compat_str
from ..utils import (
determine_ext,
ExtractorError,
@ -15,6 +14,7 @@ from ..utils import (
unified_strdate,
xpath_text,
update_url_query,
url_or_none,
)
from ..compat import compat_etree_fromstring
@ -100,7 +100,7 @@ class ARDMediathekIE(InfoExtractor):
quality = stream.get('_quality')
server = stream.get('_server')
for stream_url in stream_urls:
if not isinstance(stream_url, compat_str) or '//' not in stream_url:
if not url_or_none(stream_url):
continue
ext = determine_ext(stream_url)
if quality != 'auto' and ext in ('f4m', 'm3u8'):

7
youtube_dl/extractor/bandcamp.py

@ -19,6 +19,7 @@ from ..utils import (
unescapeHTML,
update_url_query,
unified_strdate,
url_or_none,
)
@ -131,8 +132,8 @@ class BandcampIE(InfoExtractor):
fatal=False)
if not stat:
continue
retry_url = stat.get('retry_url')
if not isinstance(retry_url, compat_str):
retry_url = url_or_none(stat.get('retry_url'))
if not retry_url:
continue
formats.append({
'url': self._proto_relative_url(retry_url, 'http:'),
@ -306,7 +307,7 @@ class BandcampWeeklyIE(InfoExtractor):
formats = []
for format_id, format_url in show['audio_stream'].items():
if not isinstance(format_url, compat_str):
if not url_or_none(format_url):
continue
for known_ext in KNOWN_EXTENSIONS:
if known_ext in format_id:

41
youtube_dl/extractor/bbc.py

@ -778,6 +778,17 @@ class BBCIE(BBCCoUkIE):
'params': {
'skip_download': True,
}
}, {
# window.__PRELOADED_STATE__
'url': 'https://www.bbc.co.uk/radio/play/b0b9z4yl',
'info_dict': {
'id': 'b0b9z4vz',
'ext': 'mp4',
'title': 'Prom 6: An American in Paris and Turangalila',
'description': 'md5:51cf7d6f5c8553f197e58203bc78dff8',
'uploader': 'Radio 3',
'uploader_id': 'bbc_radio_three',
},
}]
@classmethod
@ -1000,6 +1011,36 @@ class BBCIE(BBCCoUkIE):
'subtitles': subtitles,
}
preload_state = self._parse_json(self._search_regex(
r'window\.__PRELOADED_STATE__\s*=\s*({.+?});', webpage,
'preload state', default='{}'), playlist_id, fatal=False)
if preload_state:
current_programme = preload_state.get('programmes', {}).get('current') or {}
programme_id = current_programme.get('id')
if current_programme and programme_id and current_programme.get('type') == 'playable_item':
title = current_programme.get('titles', {}).get('tertiary') or playlist_title
formats, subtitles = self._download_media_selector(programme_id)
self._sort_formats(formats)
synopses = current_programme.get('synopses') or {}
network = current_programme.get('network') or {}
duration = int_or_none(
current_programme.get('duration', {}).get('value'))
thumbnail = None
image_url = current_programme.get('image_url')
if image_url:
thumbnail = image_url.replace('{recipe}', '1920x1920')
return {
'id': programme_id,
'title': title,
'description': dict_get(synopses, ('long', 'medium', 'short')),
'thumbnail': thumbnail,
'duration': duration,
'uploader': network.get('short_title'),
'uploader_id': network.get('id'),
'formats': formats,
'subtitles': subtitles,
}
bbc3_config = self._parse_json(
self._search_regex(
r'(?s)bbcthreeConfig\s*=\s*({.+?})\s*;\s*<', webpage,

10
youtube_dl/extractor/breakcom.py

@ -4,8 +4,10 @@ import re
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..compat import compat_str
from ..utils import int_or_none
from ..utils import (
int_or_none,
url_or_none,
)
class BreakIE(InfoExtractor):
@ -55,8 +57,8 @@ class BreakIE(InfoExtractor):
formats = []
for video in content:
video_url = video.get('url')
if not video_url or not isinstance(video_url, compat_str):
video_url = url_or_none(video.get('url'))
if not video_url:
continue
bitrate = int_or_none(self._search_regex(
r'(\d+)_kbps', video_url, 'tbr', default=None))

6
youtube_dl/extractor/cammodels.py

@ -2,10 +2,10 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
int_or_none,
url_or_none,
)
@ -56,8 +56,8 @@ class CamModelsIE(InfoExtractor):
for media in encodings:
if not isinstance(media, dict):
continue
media_url = media.get('location')
if not media_url or not isinstance(media_url, compat_str):
media_url = url_or_none(media.get('location'))
if not media_url:
continue
format_id_list = [format_id]

13
youtube_dl/extractor/canvas.py

@ -11,6 +11,7 @@ from ..utils import (
strip_or_none,
float_or_none,
int_or_none,
merge_dicts,
parse_iso8601,
)
@ -248,9 +249,13 @@ class VrtNUIE(GigyaBaseIE):
webpage, urlh = self._download_webpage_handle(url, display_id)
title = self._html_search_regex(
info = self._search_json_ld(webpage, display_id, default={})
# title is optional here since it may be extracted by extractor
# that is delegated from here
title = strip_or_none(self._html_search_regex(
r'(?ms)<h1 class="content__heading">(.+?)</h1>',
webpage, 'title').strip()
webpage, 'title', default=None))
description = self._html_search_regex(
r'(?ms)<div class="content__description">(.+?)</div>',
@ -295,7 +300,7 @@ class VrtNUIE(GigyaBaseIE):
# the first one
video_id = list(video.values())[0].get('videoid')
return {
return merge_dicts(info, {
'_type': 'url_transparent',
'url': 'https://mediazone.vrt.be/api/v1/vrtvideo/assets/%s' % video_id,
'ie_key': CanvasIE.ie_key(),
@ -307,4 +312,4 @@ class VrtNUIE(GigyaBaseIE):
'season_number': season_number,
'episode_number': episode_number,
'release_date': release_date,
}
})

6
youtube_dl/extractor/ccma.py

@ -4,13 +4,13 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
clean_html,
int_or_none,
parse_duration,
parse_iso8601,
parse_resolution,
url_or_none,
)
@ -53,8 +53,8 @@ class CCMAIE(InfoExtractor):
media_url = media['media']['url']
if isinstance(media_url, list):
for format_ in media_url:
format_url = format_.get('file')
if not format_url or not isinstance(format_url, compat_str):
format_url = url_or_none(format_.get('file'))
if not format_url:
continue
label = format_.get('label')
f = parse_resolution(label)

14
youtube_dl/extractor/crackle.py

@ -4,16 +4,14 @@ from __future__ import unicode_literals, division
import re
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_HTTPError,
)
from ..compat import compat_HTTPError
from ..utils import (
determine_ext,
float_or_none,
int_or_none,
parse_age_limit,
parse_duration,
url_or_none,
ExtractorError
)
@ -86,8 +84,8 @@ class CrackleIE(InfoExtractor):
for e in media['MediaURLs']:
if e.get('UseDRM') is True:
continue
format_url = e.get('Path')
if not format_url or not isinstance(format_url, compat_str):
format_url = url_or_none(e.get('Path'))
if not format_url:
continue
ext = determine_ext(format_url)
if ext == 'm3u8':
@ -124,8 +122,8 @@ class CrackleIE(InfoExtractor):
for cc_file in cc_files:
if not isinstance(cc_file, dict):
continue
cc_url = cc_file.get('Path')
if not cc_url or not isinstance(cc_url, compat_str):
cc_url = url_or_none(cc_file.get('Path'))
if not cc_url:
continue
lang = cc_file.get('Locale') or 'en'
subtitles.setdefault(lang, []).append({'url': cc_url})

7
youtube_dl/extractor/dctp.py

@ -7,6 +7,7 @@ from ..utils import (
float_or_none,
int_or_none,
unified_timestamp,
url_or_none,
)
@ -69,7 +70,7 @@ class DctpTvIE(InfoExtractor):
endpoint = next(
server['endpoint']
for server in servers
if isinstance(server.get('endpoint'), compat_str) and
if url_or_none(server.get('endpoint')) and
'cloudfront' in server['endpoint'])
else:
endpoint = 'rtmpe://s2pqqn4u96e4j8.cloudfront.net/cfx/st/'
@ -92,8 +93,8 @@ class DctpTvIE(InfoExtractor):
for image in images:
if not isinstance(image, dict):
continue
image_url = image.get('url')
if not image_url or not isinstance(image_url, compat_str):
image_url = url_or_none(image.get('url'))
if not image_url:
continue
thumbnails.append({
'url': image_url,

7
youtube_dl/extractor/discoverygo.py

@ -3,7 +3,6 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
extract_attributes,
@ -12,6 +11,7 @@ from ..utils import (
parse_age_limit,
remove_end,
unescapeHTML,
url_or_none,
)
@ -69,9 +69,8 @@ class DiscoveryGoBaseIE(InfoExtractor):
captions = stream.get('captions')
if isinstance(captions, list):
for caption in captions:
subtitle_url = caption.get('fileUrl')
if (not subtitle_url or not isinstance(subtitle_url, compat_str) or
not subtitle_url.startswith('http')):
subtitle_url = url_or_none(caption.get('fileUrl'))
if not subtitle_url or not subtitle_url.startswith('http'):
continue
lang = caption.get('fileLang', 'en')
ext = determine_ext(subtitle_url)

10
youtube_dl/extractor/dramafever.py

@ -7,7 +7,6 @@ import json
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_str,
compat_urlparse,
)
from ..utils import (
@ -17,6 +16,7 @@ from ..utils import (
parse_age_limit,
parse_duration,
unified_timestamp,
url_or_none,
)
@ -139,8 +139,8 @@ class DramaFeverIE(DramaFeverBaseIE):
for sub in subs:
if not isinstance(sub, dict):
continue
sub_url = sub.get('url')
if not sub_url or not isinstance(sub_url, compat_str):
sub_url = url_or_none(sub.get('url'))
if not sub_url:
continue
subtitles.setdefault(
sub.get('code') or sub.get('language') or 'en', []).append({
@ -163,8 +163,8 @@ class DramaFeverIE(DramaFeverBaseIE):
for format_id, format_dict in download_assets.items():
if not isinstance(format_dict, dict):
continue
format_url = format_dict.get('url')
if not format_url or not isinstance(format_url, compat_str):
format_url = url_or_none(format_dict.get('url'))
if not format_url:
continue
formats.append({
'url': format_url,

8
youtube_dl/extractor/eagleplatform.py

@ -4,14 +4,12 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_str,
)
from ..compat import compat_HTTPError
from ..utils import (
ExtractorError,
int_or_none,
unsmuggle_url,
url_or_none,
)
@ -177,7 +175,7 @@ class EaglePlatformIE(InfoExtractor):
video_id, 'Downloading mp4 JSON', fatal=False)
if mp4_data:
for format_id, format_url in mp4_data.get('data', {}).items():
if not isinstance(format_url, compat_str):
if not url_or_none(format_url):
continue
height = int_or_none(format_id)
if height is not None and m3u8_formats_dict.get(height):

8
youtube_dl/extractor/egghead.py

@ -8,6 +8,7 @@ from ..utils import (
int_or_none,
try_get,
unified_timestamp,
url_or_none,
)
@ -34,8 +35,8 @@ class EggheadCourseIE(InfoExtractor):
entries = []
for lesson in lessons:
lesson_url = lesson.get('http_url')
if not lesson_url or not isinstance(lesson_url, compat_str):
lesson_url = url_or_none(lesson.get('http_url'))
if not lesson_url:
continue
lesson_id = lesson.get('id')
if lesson_id:
@ -95,7 +96,8 @@ class EggheadLessonIE(InfoExtractor):
formats = []
for _, format_url in lesson['media_urls'].items():
if not format_url or not isinstance(format_url, compat_str):
format_url = url_or_none(format_url)
if not format_url:
continue
ext = determine_ext(format_url)
if ext == 'm3u8':

5
youtube_dl/extractor/eporner.py

@ -11,6 +11,7 @@ from ..utils import (
int_or_none,
parse_duration,
str_to_int,
url_or_none,
)
@ -82,8 +83,8 @@ class EpornerIE(InfoExtractor):
for format_id, format_dict in formats_dict.items():
if not isinstance(format_dict, dict):
continue
src = format_dict.get('src')
if not isinstance(src, compat_str) or not src.startswith('http'):
src = url_or_none(format_dict.get('src'))
if not src or not src.startswith('http'):
continue
if kind == 'hls':
formats.extend(self._extract_m3u8_formats(

5
youtube_dl/extractor/firsttv.py

@ -10,6 +10,7 @@ from ..utils import (
int_or_none,
qualities,
unified_strdate,
url_or_none,
)
@ -88,8 +89,8 @@ class FirstTVIE(InfoExtractor):
formats = []
path = None
for f in item.get('mbr', []):
src = f.get('src')
if not src or not isinstance(src, compat_str):
src = url_or_none(f.get('src'))
if not src:
continue
tbr = int_or_none(self._search_regex(
r'_(\d{3,})\.mp4', src, 'tbr', default=None))

8
youtube_dl/extractor/francetv.py

@ -16,6 +16,7 @@ from ..utils import (
int_or_none,
parse_duration,
try_get,
url_or_none,
)
from .dailymotion import DailymotionIE
@ -115,14 +116,13 @@ class FranceTVIE(InfoExtractor):
def sign(manifest_url, manifest_id):
for host in ('hdfauthftv-a.akamaihd.net', 'hdfauth.francetv.fr'):
signed_url = self._download_webpage(
signed_url = url_or_none(self._download_webpage(
'https://%s/esi/TA' % host, video_id,
'Downloading signed %s manifest URL' % manifest_id,
fatal=False, query={
'url': manifest_url,
})
if (signed_url and isinstance(signed_url, compat_str) and
re.search(r'^(?:https?:)?//', signed_url)):
}))
if signed_url:
return signed_url
return manifest_url

3
youtube_dl/extractor/frontendmasters.py

@ -11,6 +11,7 @@ from ..compat import (
from ..utils import (
ExtractorError,
parse_duration,
url_or_none,
urlencode_postdata,
)
@ -80,7 +81,7 @@ class FrontendMastersPageBaseIE(FrontendMastersBaseIE):
chapters = []
lesson_elements = course.get('lessonElements')
if isinstance(lesson_elements, list):
chapters = [e for e in lesson_elements if isinstance(e, compat_str)]
chapters = [url_or_none(e) for e in lesson_elements if url_or_none(e)]
return chapters
@staticmethod

5
youtube_dl/extractor/generic.py

@ -32,6 +32,7 @@ from ..utils import (
unified_strdate,
unsmuggle_url,
UnsupportedError,
url_or_none,
xpath_text,
)
from .commonprotocols import RtmpIE
@ -3130,8 +3131,8 @@ class GenericIE(InfoExtractor):
sources = [sources]
formats = []
for source in sources:
src = source.get('src')
if not src or not isinstance(src, compat_str):
src = url_or_none(source.get('src'))
if not src:
continue
src = compat_urlparse.urljoin(url, src)
src_type = source.get('type')

10
youtube_dl/extractor/hidive.py

@ -8,6 +8,7 @@ from ..compat import compat_str
from ..utils import (
ExtractorError,
int_or_none,
url_or_none,
urlencode_postdata,
)
@ -80,8 +81,8 @@ class HiDiveIE(InfoExtractor):
bitrates = rendition.get('bitrates')
if not isinstance(bitrates, dict):
continue
m3u8_url = bitrates.get('hls')
if not isinstance(m3u8_url, compat_str):
m3u8_url = url_or_none(bitrates.get('hls'))
if not m3u8_url:
continue
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
@ -93,9 +94,8 @@ class HiDiveIE(InfoExtractor):
if not isinstance(cc_file, list) or len(cc_file) < 3:
continue
cc_lang = cc_file[0]
cc_url = cc_file[2]
if not isinstance(cc_lang, compat_str) or not isinstance(
cc_url, compat_str):
cc_url = url_or_none(cc_file[2])
if not isinstance(cc_lang, compat_str) or not cc_url:
continue
subtitles.setdefault(cc_lang, []).append({
'url': cc_url,

6
youtube_dl/extractor/imdb.py

@ -3,12 +3,12 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
mimetype2ext,
parse_duration,
qualities,
url_or_none,
)
@ -61,8 +61,8 @@ class ImdbIE(InfoExtractor):
for encoding in video_metadata.get('encodings', []):
if not encoding or not isinstance(encoding, dict):
continue
video_url = encoding.get('videoUrl')
if not video_url or not isinstance(video_url, compat_str):
video_url = url_or_none(encoding.get('videoUrl'))
if not video_url:
continue
ext = determine_ext(video_url, mimetype2ext(encoding.get('mimeType')))
if ext == 'm3u8':

3
youtube_dl/extractor/instagram.py

@ -17,6 +17,7 @@ from ..utils import (
lowercase_escape,
std_headers,
try_get,
url_or_none,
)
@ -170,7 +171,7 @@ class InstagramIE(InfoExtractor):
node = try_get(edge, lambda x: x['node'], dict)
if not node:
continue
node_video_url = try_get(node, lambda x: x['video_url'], compat_str)
node_video_url = url_or_none(node.get('video_url'))
if not node_video_url:
continue
entries.append({

5
youtube_dl/extractor/itv.py

@ -20,6 +20,7 @@ from ..utils import (
merge_dicts,
parse_duration,
smuggle_url,
url_or_none,
xpath_with_ns,
xpath_element,
xpath_text,
@ -250,8 +251,8 @@ class ITVIE(InfoExtractor):
for sub in subs:
if not isinstance(sub, dict):
continue
href = sub.get('Href')
if isinstance(href, compat_str):
href = url_or_none(sub.get('Href'))
if href:
extract_subtitle(href)
if not info.get('duration'):
info['duration'] = parse_duration(video_data.get('Duration'))

6
youtube_dl/extractor/iwara.py

@ -7,6 +7,7 @@ from ..utils import (
int_or_none,
mimetype2ext,
remove_end,
url_or_none,
)
@ -73,11 +74,14 @@ class IwaraIE(InfoExtractor):
formats = []
for a_format in video_data:
format_uri = url_or_none(a_format.get('uri'))
if not format_uri:
continue
format_id = a_format.get('resolution')
height = int_or_none(self._search_regex(
r'(\d+)p', format_id, 'height', default=None))
formats.append({
'url': a_format['uri'],
'url': self._proto_relative_url(format_uri, 'https:'),
'format_id': format_id,
'ext': mimetype2ext(a_format.get('mime')) or 'mp4',
'height': height,

9
youtube_dl/extractor/keezmovies.py

@ -4,16 +4,14 @@ import re
from .common import InfoExtractor
from ..aes import aes_decrypt_text
from ..compat import (
compat_str,
compat_urllib_parse_unquote,
)
from ..compat import compat_urllib_parse_unquote
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
str_to_int,
strip_or_none,
url_or_none,
)
@ -55,7 +53,8 @@ class KeezMoviesIE(InfoExtractor):
encrypted = False
def extract_format(format_url, height=None):
if not isinstance(format_url, compat_str) or not format_url.startswith(('http', '//')):
format_url = url_or_none(format_url)
if not format_url or not format_url.startswith(('http', '//')):
return
if format_url in format_urls:
return

5
youtube_dl/extractor/konserthusetplay.py

@ -2,11 +2,11 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
float_or_none,
int_or_none,
url_or_none,
)
@ -109,7 +109,8 @@ class KonserthusetPlayIE(InfoExtractor):
captions = source.get('captionsAvailableLanguages')
if isinstance(captions, dict):
for lang, subtitle_url in captions.items():
if lang != 'none' and isinstance(subtitle_url, compat_str):
subtitle_url = url_or_none(subtitle_url)
if lang != 'none' and subtitle_url:
subtitles.setdefault(lang, []).append({'url': subtitle_url})
return {

5
youtube_dl/extractor/mediasite.py

@ -15,6 +15,7 @@ from ..utils import (
mimetype2ext,
unescapeHTML,
unsmuggle_url,
url_or_none,
urljoin,
)
@ -156,8 +157,8 @@ class MediasiteIE(InfoExtractor):
stream_formats = []
for unum, VideoUrl in enumerate(video_urls):
video_url = VideoUrl.get('Location')
if not video_url or not isinstance(video_url, compat_str):
video_url = url_or_none(VideoUrl.get('Location'))
if not video_url:
continue
# XXX: if Stream.get('CanChangeScheme', False), switch scheme to HTTP/HTTPS

5
youtube_dl/extractor/peertube.py

@ -10,6 +10,7 @@ from ..utils import (
parse_resolution,
try_get,
unified_timestamp,
url_or_none,
urljoin,
)
@ -200,8 +201,8 @@ class PeerTubeIE(InfoExtractor):
for file_ in video['files']:
if not isinstance(file_, dict):
continue
file_url = file_.get('fileUrl')
if not file_url or not isinstance(file_url, compat_str):
file_url = url_or_none(file_.get('fileUrl'))
if not file_url:
continue
file_size = int_or_none(file_.get('size'))
format_id = try_get(

6
youtube_dl/extractor/redtube.py

@ -3,12 +3,12 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
int_or_none,
str_to_int,
unified_strdate,
url_or_none,
)
@ -71,8 +71,8 @@ class RedTubeIE(InfoExtractor):
video_id, fatal=False)
if medias and isinstance(medias, list):
for media in medias:
format_url = media.get('videoUrl')
if not format_url or not isinstance(format_url, compat_str):
format_url = url_or_none(media.get('videoUrl'))
if not format_url:
continue
format_id = media.get('quality')
formats.append({

5
youtube_dl/extractor/rentv.py

@ -6,6 +6,7 @@ from ..compat import compat_str
from ..utils import (
determine_ext,
int_or_none,
url_or_none,
)
@ -37,8 +38,8 @@ class RENTVIE(InfoExtractor):
title = config['title']
formats = []
for video in config['src']:
src = video.get('src')
if not src or not isinstance(src, compat_str):
src = url_or_none(video.get('src'))
if not src:
continue
ext = determine_ext(src)
if ext == 'm3u8':

5
youtube_dl/extractor/rutube.py

@ -16,6 +16,7 @@ from ..utils import (
int_or_none,
try_get,
unified_timestamp,
url_or_none,
)
@ -176,8 +177,8 @@ class RutubePlaylistBaseIE(RutubeBaseIE):
break
for result in results:
video_url = result.get('video_url')
if not video_url or not isinstance(video_url, compat_str):
video_url = url_or_none(result.get('video_url'))
if not video_url:
continue
entry = self._extract_video(result, require_title=False)
entry.update({

1
youtube_dl/extractor/theplatform.py

@ -33,6 +33,7 @@ _x = lambda p: xpath_with_ns(p, {'smil': default_ns})
class ThePlatformBaseIE(OnceIE):
_TP_TLD = 'com'
def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL data'):
meta = self._download_xml(
smil_url, video_id, note=note, query={'format': 'SMIL'},

5
youtube_dl/extractor/turner.py

@ -15,6 +15,7 @@ from ..utils import (
update_url_query,
ExtractorError,
strip_or_none,
url_or_none,
)
@ -154,8 +155,8 @@ class TurnerBaseIE(AdobePassIE):
subtitles = {}
for source in video_data.findall('closedCaptions/source'):
for track in source.findall('track'):
track_url = track.get('url')
if not isinstance(track_url, compat_str) or track_url.endswith('/big'):
track_url = url_or_none(track.get('url'))
if not track_url or track_url.endswith('/big'):
continue
lang = track.get('lang') or track.get('label') or 'en'
subtitles.setdefault(lang, []).append({

7
youtube_dl/extractor/tvnet.py

@ -4,10 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
unescapeHTML,
url_or_none,
)
@ -106,9 +106,8 @@ class TVNetIE(InfoExtractor):
for stream in self._download_json(data_file, video_id):
if not isinstance(stream, dict):
continue
stream_url = stream.get('url')
if (stream_url in stream_urls or not stream_url or
not isinstance(stream_url, compat_str)):
stream_url = url_or_none(stream.get('url'))
if stream_url in stream_urls or not stream_url:
continue
stream_urls.add(stream_url)
formats.extend(self._extract_m3u8_formats(

4
youtube_dl/extractor/tvplay.py

@ -19,6 +19,7 @@ from ..utils import (
try_get,
unsmuggle_url,
update_url_query,
url_or_none,
)
@ -255,7 +256,8 @@ class TVPlayIE(InfoExtractor):
quality = qualities(['hls', 'medium', 'high'])
formats = []
for format_id, video_url in streams.get('streams', {}).items():
if not video_url or not isinstance(video_url, compat_str):
video_url = url_or_none(video_url)
if not video_url:
continue
ext = determine_ext(video_url)
if ext == 'f4m':

5
youtube_dl/extractor/twitch.py

@ -27,6 +27,7 @@ from ..utils import (
unified_timestamp,
update_url_query,
urlencode_postdata,
url_or_none,
urljoin,
)
@ -663,8 +664,8 @@ class TwitchClipsIE(TwitchBaseIE):
for option in status['quality_options']:
if not isinstance(option, dict):
continue
source = option.get('source')
if not source or not isinstance(source, compat_str):
source = url_or_none(option.get('source'))
if not source:
continue
formats.append({
'url': source,

13
youtube_dl/extractor/udemy.py

@ -20,6 +20,7 @@ from ..utils import (
sanitized_Request,
try_get,
unescapeHTML,
url_or_none,
urlencode_postdata,
)
@ -265,8 +266,8 @@ class UdemyIE(InfoExtractor):
if not isinstance(source_list, list):
return
for source in source_list:
video_url = source.get('file') or source.get('src')
if not video_url or not isinstance(video_url, compat_str):
video_url = url_or_none(source.get('file') or source.get('src'))
if not video_url:
continue
if source.get('type') == 'application/x-mpegURL' or determine_ext(video_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
@ -293,8 +294,8 @@ class UdemyIE(InfoExtractor):
continue
if track.get('kind') != 'captions':
continue
src = track.get('src')
if not src or not isinstance(src, compat_str):
src = url_or_none(track.get('src'))
if not src:
continue
lang = track.get('language') or track.get(
'srclang') or track.get('label')
@ -314,8 +315,8 @@ class UdemyIE(InfoExtractor):
for cc in captions:
if not isinstance(cc, dict):
continue
cc_url = cc.get('url')
if not cc_url or not isinstance(cc_url, compat_str):
cc_url = url_or_none(cc.get('url'))
if not cc_url:
continue
lang = try_get(cc, lambda x: x['locale']['locale'], compat_str)
sub_dict = (automatic_captions if cc.get('source') == 'auto'

10
youtube_dl/extractor/vidme.py

@ -3,15 +3,13 @@ from __future__ import unicode_literals
import itertools
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_str,
)
from ..compat import compat_HTTPError
from ..utils import (
ExtractorError,
int_or_none,
float_or_none,
parse_iso8601,
url_or_none,
)
@ -166,8 +164,8 @@ class VidmeIE(InfoExtractor):
formats = []
for f in video.get('formats', []):
format_url = f.get('uri')
if not format_url or not isinstance(format_url, compat_str):
format_url = url_or_none(f.get('uri'))
if not format_url:
continue
format_type = f.get('type')
if format_type == 'dash':

3
youtube_dl/extractor/vimeo.py

@ -539,9 +539,10 @@ class VimeoIE(VimeoBaseInfoExtractor):
# We try to find out to which variable is assigned the config dic
m_variable_name = re.search(r'(\w)\.video\.id', webpage)
if m_variable_name is not None:
config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
config_re = [r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))]
else:
config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
config_re.append(r'\bvar\s+r\s*=\s*({.+?})\s*;')
config = self._search_regex(config_re, webpage, 'info section',
flags=re.DOTALL)
config = json.loads(config)

26
youtube_dl/extractor/viu.py

@ -195,16 +195,29 @@ class ViuOTTIE(InfoExtractor):
'skip': 'Geo-restricted to Hong Kong',
}]
_AREA_ID = {
'HK': 1,
'SG': 2,
'TH': 4,
'PH': 5,
}
def _real_extract(self, url):
country_code, video_id = re.match(self._VALID_URL, url).groups()
query = {
'r': 'vod/ajax-detail',
'platform_flag_label': 'web',
'product_id': video_id,
}
area_id = self._AREA_ID.get(country_code.upper())
if area_id:
query['area_id'] = area_id
product_data = self._download_json(
'http://www.viu.com/ott/%s/index.php' % country_code, video_id,
'Downloading video info', query={
'r': 'vod/ajax-detail',
'platform_flag_label': 'web',
'product_id': video_id,
})['data']
'Downloading video info', query=query)['data']
video_data = product_data.get('current_product')
if not video_data:
@ -214,6 +227,9 @@ class ViuOTTIE(InfoExtractor):
'https://d1k2us671qcoau.cloudfront.net/distribute_web_%s.php' % country_code,
video_id, 'Downloading stream info', query={
'ccs_product_id': video_data['ccs_product_id'],
}, headers={
'Referer': url,
'Origin': re.search(r'https?://[^/]+', url).group(0),
})['data']['stream']
stream_sizes = stream_data.get('size', {})

4
youtube_dl/extractor/vk.py

@ -20,6 +20,7 @@ from ..utils import (
str_to_int,
unescapeHTML,
unified_timestamp,
url_or_none,
urlencode_postdata,
)
from .dailymotion import DailymotionIE
@ -423,7 +424,8 @@ class VKIE(VKBaseIE):
formats = []
for format_id, format_url in data.items():
if not isinstance(format_url, compat_str) or not format_url.startswith(('http', '//', 'rtmp')):
format_url = url_or_none(format_url)
if not format_url or not format_url.startswith(('http', '//', 'rtmp')):
continue
if (format_id.startswith(('url', 'cache')) or
format_id in ('extra_data', 'live_mp4', 'postlive_mp4')):

7
youtube_dl/extractor/xhamster.py

@ -13,6 +13,7 @@ from ..utils import (
parse_duration,
try_get,
unified_strdate,
url_or_none,
)
@ -137,7 +138,8 @@ class XHamsterIE(InfoExtractor):
else:
format_url = format_item
filesize = None
if not isinstance(format_url, compat_str):
format_url = url_or_none(format_url)
if not format_url:
continue
formats.append({
'format_id': '%s-%s' % (format_id, quality),
@ -198,7 +200,8 @@ class XHamsterIE(InfoExtractor):
default='{}'),
video_id, fatal=False)
for format_id, format_url in sources.items():
if not isinstance(format_url, compat_str):
format_url = url_or_none(format_url)
if not format_url:
continue
if format_url in format_urls:
continue

8
youtube_dl/extractor/yapfiles.py

@ -4,12 +4,12 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
int_or_none,
qualities,
unescapeHTML,
url_or_none,
)
@ -80,9 +80,9 @@ class YapFilesIE(InfoExtractor):
formats = []
for format_id in QUALITIES:
is_hd = format_id == 'hd'
format_url = playlist.get(
'file%s' % ('_hd' if is_hd else ''))
if not format_url or not isinstance(format_url, compat_str):
format_url = url_or_none(playlist.get(
'file%s' % ('_hd' if is_hd else '')))
if not format_url:
continue
formats.append({
'url': format_url,

6
youtube_dl/extractor/youjizz.py

@ -3,11 +3,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
int_or_none,
parse_duration,
url_or_none,
)
@ -50,8 +50,8 @@ class YouJizzIE(InfoExtractor):
for encoding in encodings:
if not isinstance(encoding, dict):
continue
format_url = encoding.get('filename')
if not isinstance(format_url, compat_str):
format_url = url_or_none(encoding.get('filename'))
if not format_url:
continue
if determine_ext(format_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(

6
youtube_dl/extractor/youporn.py

@ -3,13 +3,13 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
sanitized_Request,
str_to_int,
unescapeHTML,
unified_strdate,
url_or_none,
)
from ..aes import aes_decrypt_text
@ -88,8 +88,8 @@ class YouPornIE(InfoExtractor):
for definition in definitions:
if not isinstance(definition, dict):
continue
video_url = definition.get('videoUrl')
if isinstance(video_url, compat_str) and video_url:
video_url = url_or_none(definition.get('videoUrl'))
if video_url:
links.append(video_url)
# Fallback #1, this also contains extra low quality 180p format

5
youtube_dl/extractor/zattoo.py

@ -13,6 +13,7 @@ from ..utils import (
ExtractorError,
int_or_none,
try_get,
url_or_none,
urlencode_postdata,
)
@ -150,8 +151,8 @@ class ZattooBaseIE(InfoExtractor):
for watch in watch_urls:
if not isinstance(watch, dict):
continue
watch_url = watch.get('url')
if not watch_url or not isinstance(watch_url, compat_str):
watch_url = url_or_none(watch.get('url'))
if not watch_url:
continue
format_id_list = [stream_type]
maxrate = watch.get('maxrate')

12
youtube_dl/extractor/zdf.py

@ -15,6 +15,7 @@ from ..utils import (
try_get,
unified_timestamp,
update_url_query,
url_or_none,
urljoin,
)
@ -67,8 +68,8 @@ class ZDFIE(ZDFBaseIE):
def _extract_subtitles(src):
subtitles = {}
for caption in try_get(src, lambda x: x['captions'], list) or []:
subtitle_url = caption.get('uri')
if subtitle_url and isinstance(subtitle_url, compat_str):
subtitle_url = url_or_none(caption.get('uri'))
if subtitle_url:
lang = caption.get('language', 'deu')
subtitles.setdefault(lang, []).append({
'url': subtitle_url,
@ -76,8 +77,8 @@ class ZDFIE(ZDFBaseIE):
return subtitles
def _extract_format(self, video_id, formats, format_urls, meta):
format_url = meta.get('url')
if not format_url or not isinstance(format_url, compat_str):
format_url = url_or_none(meta.get('url'))
if not format_url:
return
if format_url in format_urls:
return
@ -152,7 +153,8 @@ class ZDFIE(ZDFBaseIE):
content, lambda x: x['teaserImageRef']['layouts'], dict)
if layouts:
for layout_key, layout_url in layouts.items():
if not isinstance(layout_url, compat_str):
layout_url = url_or_none(layout_url)
if not layout_url:
continue
thumbnail = {
'url': layout_url,

9
youtube_dl/utils.py

@ -1866,6 +1866,13 @@ def strip_or_none(v):
return None if v is None else v.strip()
def url_or_none(url):
if not url or not isinstance(url, compat_str):
return None
url = url.strip()
return url if re.match(r'^(?:[a-zA-Z][\da-zA-Z.+-]*:)?//', url) else None
def parse_duration(s):
if not isinstance(s, compat_basestring):
return None
@ -2282,7 +2289,7 @@ def parse_age_limit(s):
def strip_jsonp(code):
return re.sub(
r'''(?sx)^
(?:window\.)?(?P<func_name>[a-zA-Z0-9_.$]+)
(?:window\.)?(?P<func_name>[a-zA-Z0-9_.$]*)
(?:\s*&&\s*(?P=func_name))?
\s*\(\s*(?P<callback_data>.*)\);?
\s*?(?://[^\n]*)*$''',

2
youtube_dl/version.py

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2018.07.10'
__version__ = '2018.07.21'