世外桃源
GitHub
commit
82c23467f7
6
.github/ISSUE_TEMPLATE.md
vendored
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 *2016.10.19*. 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 Issues with outdated version will be rejected.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 **2016.10.19**
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.10.21.1*. 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 Issues with outdated version will be rejected.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 **2016.10.21.1**
|
||||
|
||||
### Before submitting an *issue* make sure you have:
|
||||
- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
|
||||
@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
|
||||
[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 2016.10.19
|
||||
[debug] youtube-dl version 2016.10.21.1
|
||||
[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: {}
|
||||
|
||||
22
ChangeLog
22
ChangeLog
@ -1,7 +1,29 @@
|
||||
version <unreleased>
|
||||
|
||||
Core
|
||||
* Running youtube-dl in the background is fixed (#10996, #10706, #955)
|
||||
|
||||
Extractors
|
||||
+ [dotsub] Support Vimeo embed (#10964)
|
||||
* [litv] Fix extraction
|
||||
|
||||
|
||||
version 2016.10.21.1
|
||||
|
||||
Extractors
|
||||
+ [pluralsight] Process all clip URLs (#10984)
|
||||
|
||||
|
||||
version 2016.10.21
|
||||
|
||||
Core
|
||||
- Disable thumbnails embedding in mkv
|
||||
+ Add support for Comcast multiple-system operator (#10819)
|
||||
|
||||
Extractors
|
||||
* [pluralsight] Adapt to new API (#10972)
|
||||
* [openload] Fix extraction (#10408, #10971)
|
||||
+ [natgeo] Extract m3u8 formats (#10959)
|
||||
|
||||
|
||||
version 2016.10.19
|
||||
|
||||
@ -1376,19 +1376,23 @@ class AdobePassIE(InfoExtractor):
|
||||
provider_redirect_page, urlh = provider_redirect_page_res
|
||||
# Check for Comcast auto login
|
||||
if 'automatically signing you in' in provider_redirect_page:
|
||||
oauth_redirect_url = self._html_search_regex(r'window\.location\s*=\s*[\'"]([^\'"]+)',
|
||||
oauth_redirect_url = self._html_search_regex(
|
||||
r'window\.location\s*=\s*[\'"]([^\'"]+)',
|
||||
provider_redirect_page, 'oauth redirect')
|
||||
# Just need to process the request. No useful data comes back
|
||||
self._download_webpage(oauth_redirect_url, video_id, 'Confirming auto login')
|
||||
self._download_webpage(
|
||||
oauth_redirect_url, video_id, 'Confirming auto login')
|
||||
else:
|
||||
if '<form name="signin"' in provider_redirect_page:
|
||||
# already have the form, just fill it
|
||||
provider_login_page_res = provider_redirect_page_res
|
||||
elif 'http-equiv="refresh"' in provider_redirect_page:
|
||||
# redirects to the login page
|
||||
oauth_redirect_url = self._html_search_regex(r'content="0;\s*url=([^\'"]+)',
|
||||
oauth_redirect_url = self._html_search_regex(
|
||||
r'content="0;\s*url=([^\'"]+)',
|
||||
provider_redirect_page, 'meta refresh redirect')
|
||||
provider_login_page_res = self._download_webpage_handle(oauth_redirect_url,
|
||||
provider_login_page_res = self._download_webpage_handle(
|
||||
oauth_redirect_url,
|
||||
video_id, 'Downloading Provider Login Page')
|
||||
else:
|
||||
provider_login_page_res = post_form(
|
||||
|
||||
@ -9,7 +9,7 @@ from ..utils import (
|
||||
|
||||
class DotsubIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)'
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'https://dotsub.com/view/9c63db2a-fa95-4838-8e6e-13deafe47f09',
|
||||
'md5': '21c7ff600f545358134fea762a6d42b6',
|
||||
'info_dict': {
|
||||
@ -24,7 +24,24 @@ class DotsubIE(InfoExtractor):
|
||||
'upload_date': '20131130',
|
||||
'view_count': int,
|
||||
}
|
||||
}
|
||||
}, {
|
||||
'url': 'https://dotsub.com/view/747bcf58-bd59-45b7-8c8c-ac312d084ee6',
|
||||
'md5': '2bb4a83896434d5c26be868c609429a3',
|
||||
'info_dict': {
|
||||
'id': '168006778',
|
||||
'ext': 'mp4',
|
||||
'title': 'Apartments and flats in Raipur the white symphony',
|
||||
'description': 'md5:784d0639e6b7d1bc29530878508e38fe',
|
||||
'thumbnail': 're:^https?://dotsub.com/media/747bcf58-bd59-45b7-8c8c-ac312d084ee6/p',
|
||||
'duration': 290,
|
||||
'timestamp': 1476767794.2809999,
|
||||
'upload_date': '20160525',
|
||||
'uploader': 'parthivi001',
|
||||
'uploader_id': 'user52596202',
|
||||
'view_count': int,
|
||||
},
|
||||
'add_ie': ['Vimeo'],
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
@ -37,12 +54,23 @@ class DotsubIE(InfoExtractor):
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
video_url = self._search_regex(
|
||||
[r'<source[^>]+src="([^"]+)"', r'"file"\s*:\s*\'([^\']+)'],
|
||||
webpage, 'video url')
|
||||
webpage, 'video url', default=None)
|
||||
info_dict = {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'ext': 'flv',
|
||||
}
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'ext': 'flv',
|
||||
if not video_url:
|
||||
setup_data = self._parse_json(self._html_search_regex(
|
||||
r'(?s)data-setup=([\'"])(?P<content>(?!\1).+?)\1',
|
||||
webpage, 'setup data', group='content'), video_id)
|
||||
info_dict = {
|
||||
'_type': 'url_transparent',
|
||||
'url': setup_data['src'],
|
||||
}
|
||||
|
||||
info_dict.update({
|
||||
'title': info['title'],
|
||||
'description': info.get('description'),
|
||||
'thumbnail': info.get('screenshotURI'),
|
||||
@ -50,4 +78,6 @@ class DotsubIE(InfoExtractor):
|
||||
'uploader': info.get('user'),
|
||||
'timestamp': float_or_none(info.get('dateCreated'), 1000),
|
||||
'view_count': int_or_none(info.get('numberOfViews')),
|
||||
}
|
||||
})
|
||||
|
||||
return info_dict
|
||||
|
||||
@ -796,7 +796,10 @@ from .sendtonews import SendtoNewsIE
|
||||
from .servingsys import ServingSysIE
|
||||
from .sexu import SexuIE
|
||||
from .shahid import ShahidIE
|
||||
from .shared import SharedIE
|
||||
from .shared import (
|
||||
SharedIE,
|
||||
VivoIE,
|
||||
)
|
||||
from .sharesix import ShareSixIE
|
||||
from .sina import SinaIE
|
||||
from .sixplay import SixPlayIE
|
||||
|
||||
@ -2,7 +2,6 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
@ -52,8 +51,8 @@ class LiTVIE(InfoExtractor):
|
||||
'skip': 'Georestricted to Taiwan',
|
||||
}]
|
||||
|
||||
def _extract_playlist(self, season_list, video_id, vod_data, view_data, prompt=True):
|
||||
episode_title = view_data['title']
|
||||
def _extract_playlist(self, season_list, video_id, program_info, prompt=True):
|
||||
episode_title = program_info['title']
|
||||
content_id = season_list['contentId']
|
||||
|
||||
if prompt:
|
||||
@ -61,7 +60,7 @@ class LiTVIE(InfoExtractor):
|
||||
|
||||
all_episodes = [
|
||||
self.url_result(smuggle_url(
|
||||
self._URL_TEMPLATE % (view_data['contentType'], episode['contentId']),
|
||||
self._URL_TEMPLATE % (program_info['contentType'], episode['contentId']),
|
||||
{'force_noplaylist': True})) # To prevent infinite recursion
|
||||
for episode in season_list['episode']]
|
||||
|
||||
@ -80,19 +79,15 @@ class LiTVIE(InfoExtractor):
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
view_data = dict(map(lambda t: (t[0], t[2]), re.findall(
|
||||
r'viewData\.([a-zA-Z]+)\s*=\s*(["\'])([^"\']+)\2',
|
||||
webpage)))
|
||||
|
||||
vod_data = self._parse_json(self._search_regex(
|
||||
'var\s+vod\s*=\s*([^;]+)', webpage, 'VOD data', default='{}'),
|
||||
program_info = self._parse_json(self._search_regex(
|
||||
'var\s+programInfo\s*=\s*([^;]+)', webpage, 'VOD data', default='{}'),
|
||||
video_id)
|
||||
|
||||
season_list = list(vod_data.get('seasonList', {}).values())
|
||||
season_list = list(program_info.get('seasonList', {}).values())
|
||||
if season_list:
|
||||
if not noplaylist:
|
||||
return self._extract_playlist(
|
||||
season_list[0], video_id, vod_data, view_data,
|
||||
season_list[0], video_id, program_info,
|
||||
prompt=noplaylist_prompt)
|
||||
|
||||
if noplaylist_prompt:
|
||||
@ -102,8 +97,8 @@ class LiTVIE(InfoExtractor):
|
||||
# endpoint gives the same result as the data embedded in the webpage.
|
||||
# If georestricted, there are no embedded data, so an extra request is
|
||||
# necessary to get the error code
|
||||
if 'assetId' not in view_data:
|
||||
view_data = self._download_json(
|
||||
if 'assetId' not in program_info:
|
||||
program_info = self._download_json(
|
||||
'https://www.litv.tv/vod/ajax/getProgramInfo', video_id,
|
||||
query={'contentId': video_id},
|
||||
headers={'Accept': 'application/json'})
|
||||
@ -112,9 +107,9 @@ class LiTVIE(InfoExtractor):
|
||||
webpage, 'video data', default='{}'), video_id)
|
||||
if not video_data:
|
||||
payload = {
|
||||
'assetId': view_data['assetId'],
|
||||
'watchDevices': view_data['watchDevices'],
|
||||
'contentType': view_data['contentType'],
|
||||
'assetId': program_info['assetId'],
|
||||
'watchDevices': program_info['watchDevices'],
|
||||
'contentType': program_info['contentType'],
|
||||
}
|
||||
video_data = self._download_json(
|
||||
'https://www.litv.tv/vod/getMainUrl', video_id,
|
||||
@ -136,11 +131,11 @@ class LiTVIE(InfoExtractor):
|
||||
# LiTV HLS segments doesn't like compressions
|
||||
a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = True
|
||||
|
||||
title = view_data['title'] + view_data.get('secondaryMark', '')
|
||||
description = view_data.get('description')
|
||||
thumbnail = view_data.get('imageFile')
|
||||
categories = [item['name'] for item in vod_data.get('category', [])]
|
||||
episode = int_or_none(view_data.get('episode'))
|
||||
title = program_info['title'] + program_info.get('secondaryMark', '')
|
||||
description = program_info.get('description')
|
||||
thumbnail = program_info.get('imageFile')
|
||||
categories = [item['name'] for item in program_info.get('category', [])]
|
||||
episode = int_or_none(program_info.get('episode'))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
|
||||
@ -4,7 +4,6 @@ import collections
|
||||
import json
|
||||
import os
|
||||
import random
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
@ -12,6 +11,7 @@ from ..compat import (
|
||||
compat_urlparse,
|
||||
)
|
||||
from ..utils import (
|
||||
dict_get,
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
@ -23,7 +23,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class PluralsightBaseIE(InfoExtractor):
|
||||
_API_BASE = 'http://app.pluralsight.com'
|
||||
_API_BASE = 'https://app.pluralsight.com'
|
||||
|
||||
|
||||
class PluralsightIE(PluralsightBaseIE):
|
||||
@ -102,7 +102,7 @@ class PluralsightIE(PluralsightBaseIE):
|
||||
'm': name,
|
||||
}
|
||||
captions = self._download_json(
|
||||
'%s/training/Player/Captions' % self._API_BASE, video_id,
|
||||
'%s/player/retrieve-captions' % self._API_BASE, video_id,
|
||||
'Downloading captions JSON', 'Unable to download captions JSON',
|
||||
fatal=False, data=json.dumps(captions_post).encode('utf-8'),
|
||||
headers={'Content-Type': 'application/json;charset=utf-8'})
|
||||
@ -120,14 +120,17 @@ class PluralsightIE(PluralsightBaseIE):
|
||||
@staticmethod
|
||||
def _convert_subtitles(duration, subs):
|
||||
srt = ''
|
||||
TIME_OFFSET_KEYS = ('displayTimeOffset', 'DisplayTimeOffset')
|
||||
TEXT_KEYS = ('text', 'Text')
|
||||
for num, current in enumerate(subs):
|
||||
current = subs[num]
|
||||
start, text = float_or_none(
|
||||
current.get('DisplayTimeOffset')), current.get('Text')
|
||||
start, text = (
|
||||
float_or_none(dict_get(current, TIME_OFFSET_KEYS)),
|
||||
dict_get(current, TEXT_KEYS))
|
||||
if start is None or text is None:
|
||||
continue
|
||||
end = duration if num == len(subs) - 1 else float_or_none(
|
||||
subs[num + 1].get('DisplayTimeOffset'))
|
||||
dict_get(subs[num + 1], TIME_OFFSET_KEYS))
|
||||
if end is None:
|
||||
continue
|
||||
srt += os.linesep.join(
|
||||
@ -147,28 +150,22 @@ class PluralsightIE(PluralsightBaseIE):
|
||||
author = qs.get('author', [None])[0]
|
||||
name = qs.get('name', [None])[0]
|
||||
clip_id = qs.get('clip', [None])[0]
|
||||
course = qs.get('course', [None])[0]
|
||||
course_name = qs.get('course', [None])[0]
|
||||
|
||||
if any(not f for f in (author, name, clip_id, course,)):
|
||||
if any(not f for f in (author, name, clip_id, course_name,)):
|
||||
raise ExtractorError('Invalid URL', expected=True)
|
||||
|
||||
display_id = '%s-%s' % (name, clip_id)
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
parsed_url = compat_urlparse.urlparse(url)
|
||||
|
||||
modules = self._search_regex(
|
||||
r'moduleCollection\s*:\s*new\s+ModuleCollection\((\[.+?\])\s*,\s*\$rootScope\)',
|
||||
webpage, 'modules', default=None)
|
||||
payload_url = compat_urlparse.urlunparse(parsed_url._replace(
|
||||
netloc='app.pluralsight.com', path='player/api/v1/payload'))
|
||||
|
||||
if modules:
|
||||
collection = self._parse_json(modules, display_id)
|
||||
else:
|
||||
# Webpage may be served in different layout (see
|
||||
# https://github.com/rg3/youtube-dl/issues/7607)
|
||||
collection = self._parse_json(
|
||||
self._search_regex(
|
||||
r'var\s+initialState\s*=\s*({.+?});\n', webpage, 'initial state'),
|
||||
display_id)['course']['modules']
|
||||
course = self._download_json(
|
||||
payload_url, display_id, headers={'Referer': url})['payload']['course']
|
||||
|
||||
collection = course['modules']
|
||||
|
||||
module, clip = None, None
|
||||
|
||||
@ -209,8 +206,7 @@ class PluralsightIE(PluralsightBaseIE):
|
||||
|
||||
# Some courses also offer widescreen resolution for high quality (see
|
||||
# https://github.com/rg3/youtube-dl/issues/7766)
|
||||
widescreen = True if re.search(
|
||||
r'courseSupportsWidescreenVideoFormats\s*:\s*true', webpage) else False
|
||||
widescreen = course.get('supportsWideScreenVideoFormats') is True
|
||||
best_quality = 'high-widescreen' if widescreen else 'high'
|
||||
if widescreen:
|
||||
for allowed_quality in ALLOWED_QUALITIES:
|
||||
@ -239,19 +235,19 @@ class PluralsightIE(PluralsightBaseIE):
|
||||
for quality in qualities_:
|
||||
f = QUALITIES[quality].copy()
|
||||
clip_post = {
|
||||
'a': author,
|
||||
'cap': 'false',
|
||||
'cn': clip_id,
|
||||
'course': course,
|
||||
'lc': 'en',
|
||||
'm': name,
|
||||
'mt': ext,
|
||||
'q': '%dx%d' % (f['width'], f['height']),
|
||||
'author': author,
|
||||
'includeCaptions': False,
|
||||
'clipIndex': int(clip_id),
|
||||
'courseName': course_name,
|
||||
'locale': 'en',
|
||||
'moduleName': name,
|
||||
'mediaType': ext,
|
||||
'quality': '%dx%d' % (f['width'], f['height']),
|
||||
}
|
||||
format_id = '%s-%s' % (ext, quality)
|
||||
clip_url = self._download_webpage(
|
||||
'%s/training/Player/ViewClip' % self._API_BASE, display_id,
|
||||
'Downloading %s URL' % format_id, fatal=False,
|
||||
viewclip = self._download_json(
|
||||
'%s/video/clips/viewclip' % self._API_BASE, display_id,
|
||||
'Downloading %s viewclip JSON' % format_id, fatal=False,
|
||||
data=json.dumps(clip_post).encode('utf-8'),
|
||||
headers={'Content-Type': 'application/json;charset=utf-8'})
|
||||
|
||||
@ -265,15 +261,28 @@ class PluralsightIE(PluralsightBaseIE):
|
||||
random.randint(2, 5), display_id,
|
||||
'%(video_id)s: Waiting for %(timeout)s seconds to avoid throttling')
|
||||
|
||||
if not clip_url:
|
||||
if not viewclip:
|
||||
continue
|
||||
f.update({
|
||||
'url': clip_url,
|
||||
'ext': ext,
|
||||
'format_id': format_id,
|
||||
'quality': quality_key(quality),
|
||||
})
|
||||
formats.append(f)
|
||||
|
||||
clip_urls = viewclip.get('urls')
|
||||
if not isinstance(clip_urls, list):
|
||||
continue
|
||||
|
||||
for clip_url_data in clip_urls:
|
||||
clip_url = clip_url_data.get('url')
|
||||
if not clip_url:
|
||||
continue
|
||||
cdn = clip_url_data.get('cdn')
|
||||
clip_f = f.copy()
|
||||
clip_f.update({
|
||||
'url': clip_url,
|
||||
'ext': ext,
|
||||
'format_id': '%s-%s' % (format_id, cdn) if cdn else format_id,
|
||||
'quality': quality_key(quality),
|
||||
'source_preference': int_or_none(clip_url_data.get('rank')),
|
||||
})
|
||||
formats.append(clip_f)
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
duration = int_or_none(
|
||||
|
||||
@ -10,11 +10,38 @@ from ..utils import (
|
||||
)
|
||||
|
||||
|
||||
class SharedIE(InfoExtractor):
|
||||
IE_DESC = 'shared.sx and vivo.sx'
|
||||
_VALID_URL = r'https?://(?:shared|vivo)\.sx/(?P<id>[\da-z]{10})'
|
||||
class SharedBaseIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
_TESTS = [{
|
||||
webpage, urlh = self._download_webpage_handle(url, video_id)
|
||||
|
||||
if self._FILE_NOT_FOUND in webpage:
|
||||
raise ExtractorError(
|
||||
'Video %s does not exist' % video_id, expected=True)
|
||||
|
||||
video_url = self._extract_video_url(webpage, video_id, url)
|
||||
|
||||
title = base64.b64decode(self._html_search_meta(
|
||||
'full:title', webpage, 'title').encode('utf-8')).decode('utf-8')
|
||||
filesize = int_or_none(self._html_search_meta(
|
||||
'full:size', webpage, 'file size', fatal=False))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'ext': 'mp4',
|
||||
'filesize': filesize,
|
||||
'title': title,
|
||||
}
|
||||
|
||||
|
||||
class SharedIE(SharedBaseIE):
|
||||
IE_DESC = 'shared.sx'
|
||||
_VALID_URL = r'https?://shared\.sx/(?P<id>[\da-z]{10})'
|
||||
_FILE_NOT_FOUND = '>File does not exist<'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://shared.sx/0060718775',
|
||||
'md5': '106fefed92a8a2adb8c98e6a0652f49b',
|
||||
'info_dict': {
|
||||
@ -23,7 +50,32 @@ class SharedIE(InfoExtractor):
|
||||
'title': 'Bmp4',
|
||||
'filesize': 1720110,
|
||||
},
|
||||
}, {
|
||||
}
|
||||
|
||||
def _extract_video_url(self, webpage, video_id, url):
|
||||
download_form = self._hidden_inputs(webpage)
|
||||
|
||||
video_page = self._download_webpage(
|
||||
url, video_id, 'Downloading video page',
|
||||
data=urlencode_postdata(download_form),
|
||||
headers={
|
||||
'Content-Type': 'application/x-www-form-urlencoded',
|
||||
'Referer': url,
|
||||
})
|
||||
|
||||
video_url = self._html_search_regex(
|
||||
r'data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
|
||||
video_page, 'video URL', group='url')
|
||||
|
||||
return video_url
|
||||
|
||||
|
||||
class VivoIE(SharedBaseIE):
|
||||
IE_DESC = 'vivo.sx'
|
||||
_VALID_URL = r'https?://vivo\.sx/(?P<id>[\da-z]{10})'
|
||||
_FILE_NOT_FOUND = '>The file you have requested does not exists or has been removed'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://vivo.sx/d7ddda0e78',
|
||||
'md5': '15b3af41be0b4fe01f4df075c2678b2c',
|
||||
'info_dict': {
|
||||
@ -32,43 +84,13 @@ class SharedIE(InfoExtractor):
|
||||
'title': 'Chicken',
|
||||
'filesize': 528031,
|
||||
},
|
||||
}]
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage, urlh = self._download_webpage_handle(url, video_id)
|
||||
|
||||
if '>File does not exist<' in webpage:
|
||||
raise ExtractorError(
|
||||
'Video %s does not exist' % video_id, expected=True)
|
||||
|
||||
download_form = self._hidden_inputs(webpage)
|
||||
|
||||
video_page = self._download_webpage(
|
||||
urlh.geturl(), video_id, 'Downloading video page',
|
||||
data=urlencode_postdata(download_form),
|
||||
headers={
|
||||
'Content-Type': 'application/x-www-form-urlencoded',
|
||||
'Referer': urlh.geturl(),
|
||||
})
|
||||
|
||||
video_url = self._html_search_regex(
|
||||
r'data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
|
||||
video_page, 'video URL', group='url')
|
||||
title = base64.b64decode(self._html_search_meta(
|
||||
'full:title', webpage, 'title').encode('utf-8')).decode('utf-8')
|
||||
filesize = int_or_none(self._html_search_meta(
|
||||
'full:size', webpage, 'file size', fatal=False))
|
||||
thumbnail = self._html_search_regex(
|
||||
r'data-poster=(["\'])(?P<url>(?:(?!\1).)+)\1',
|
||||
video_page, 'thumbnail', default=None, group='url')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'ext': 'mp4',
|
||||
'filesize': filesize,
|
||||
'title': title,
|
||||
'thumbnail': thumbnail,
|
||||
}
|
||||
def _extract_video_url(self, webpage, video_id, *args):
|
||||
return self._parse_json(
|
||||
self._search_regex(
|
||||
r'InitializeStream\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
|
||||
webpage, 'stream', group='url'),
|
||||
video_id,
|
||||
transform_source=lambda x: base64.b64decode(
|
||||
x.encode('ascii')).decode('utf-8'))[0]
|
||||
|
||||
@ -398,7 +398,7 @@ class TwitchStreamIE(TwitchBaseIE):
|
||||
channel_id = self._match_id(url)
|
||||
|
||||
stream = self._call_api(
|
||||
'kraken/streams/%s' % channel_id, channel_id,
|
||||
'kraken/streams/%s?stream_type=all' % channel_id, channel_id,
|
||||
'Downloading stream JSON').get('stream')
|
||||
|
||||
if not stream:
|
||||
@ -417,6 +417,7 @@ class TwitchStreamIE(TwitchBaseIE):
|
||||
query = {
|
||||
'allow_source': 'true',
|
||||
'allow_audio_only': 'true',
|
||||
'allow_spectre': 'true',
|
||||
'p': random.randint(1000000, 10000000),
|
||||
'player': 'twitchweb',
|
||||
'segment_preference': '4',
|
||||
|
||||
@ -322,6 +322,22 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
},
|
||||
'expected_warnings': ['Unable to download JSON metadata'],
|
||||
},
|
||||
{
|
||||
# redirects to ondemand extractor and should be passed throught it
|
||||
# for successful extraction
|
||||
'url': 'https://vimeo.com/73445910',
|
||||
'info_dict': {
|
||||
'id': '73445910',
|
||||
'ext': 'mp4',
|
||||
'title': 'The Reluctant Revolutionary',
|
||||
'uploader': '10Ft Films',
|
||||
'uploader_url': 're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
|
||||
'uploader_id': 'tenfootfilms',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
{
|
||||
'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
|
||||
'only_matching': True,
|
||||
@ -414,7 +430,12 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
# Retrieve video webpage to extract further information
|
||||
request = sanitized_Request(url, headers=headers)
|
||||
try:
|
||||
webpage = self._download_webpage(request, video_id)
|
||||
webpage, urlh = self._download_webpage_handle(request, video_id)
|
||||
# Some URLs redirect to ondemand can't be extracted with
|
||||
# this extractor right away thus should be passed through
|
||||
# ondemand extractor (e.g. https://vimeo.com/73445910)
|
||||
if VimeoOndemandIE.suitable(urlh.geturl()):
|
||||
return self.url_result(urlh.geturl(), VimeoOndemandIE.ie_key())
|
||||
except ExtractorError as ee:
|
||||
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
|
||||
errmsg = ee.cause.read()
|
||||
|
||||
@ -1818,8 +1818,12 @@ def get_exe_version(exe, args=['--version'],
|
||||
""" Returns the version of the specified executable,
|
||||
or False if the executable is not present """
|
||||
try:
|
||||
# STDIN should be redirected too. On UNIX-like systems, ffmpeg triggers
|
||||
# SIGTTOU if youtube-dl is run in the background.
|
||||
# See https://github.com/rg3/youtube-dl/issues/955#issuecomment-209789656
|
||||
out, _ = subprocess.Popen(
|
||||
[encodeArgument(exe)] + args,
|
||||
stdin=subprocess.PIPE,
|
||||
stdout=subprocess.PIPE, stderr=subprocess.STDOUT).communicate()
|
||||
except OSError:
|
||||
return False
|
||||
|
||||
@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2016.10.19'
|
||||
__version__ = '2016.10.21.1'
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user