mirror of https://github.com/yt-dlp/yt-dlp
Update to ytdl-commit-2dd6c6e
[YouTube] Avoid crash if uploader_id extraction fails
2dd6c6edd8
Except:
* 295736c9cba714fb5de7d1c3dd31d86e50091cf8 [jsinterp] Improve parsing
* 384f632e8a9b61e864a26678d85b2b39933b9bae [ITV] Overhaul ITV extractor
* 33db85c571304bbd6863e3407ad8d08764c9e53b [feat]: Add support to external downloader aria2p
pull/5822/head^2
pukkandan
2 years ago
parent
a538772969
commit
45b2ee6f4f
@ -0,0 +1,167 @@
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import strip_or_none, traverse_obj
|
||||
|
||||
|
||||
class BlerpIE(InfoExtractor):
|
||||
IE_NAME = 'blerp'
|
||||
_VALID_URL = r'https?://(?:www\.)?blerp\.com/soundbites/(?P<id>[0-9a-zA-Z]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://blerp.com/soundbites/6320fe8745636cb4dd677a5a',
|
||||
'info_dict': {
|
||||
'id': '6320fe8745636cb4dd677a5a',
|
||||
'title': 'Samsung Galaxy S8 Over the Horizon Ringtone 2016',
|
||||
'uploader': 'luminousaj',
|
||||
'uploader_id': '5fb81e51aa66ae000c395478',
|
||||
'ext': 'mp3',
|
||||
'tags': ['samsung', 'galaxy', 's8', 'over the horizon', '2016', 'ringtone'],
|
||||
}
|
||||
}, {
|
||||
'url': 'https://blerp.com/soundbites/5bc94ef4796001000498429f',
|
||||
'info_dict': {
|
||||
'id': '5bc94ef4796001000498429f',
|
||||
'title': 'Yee',
|
||||
'uploader': '179617322678353920',
|
||||
'uploader_id': '5ba99cf71386730004552c42',
|
||||
'ext': 'mp3',
|
||||
'tags': ['YEE', 'YEET', 'wo ha haah catchy tune yee', 'yee']
|
||||
}
|
||||
}]
|
||||
|
||||
_GRAPHQL_OPERATIONNAME = "webBitePageGetBite"
|
||||
_GRAPHQL_QUERY = (
|
||||
'''query webBitePageGetBite($_id: MongoID!) {
|
||||
web {
|
||||
biteById(_id: $_id) {
|
||||
...bitePageFrag
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
}
|
||||
|
||||
fragment bitePageFrag on Bite {
|
||||
_id
|
||||
title
|
||||
userKeywords
|
||||
keywords
|
||||
color
|
||||
visibility
|
||||
isPremium
|
||||
owned
|
||||
price
|
||||
extraReview
|
||||
isAudioExists
|
||||
image {
|
||||
filename
|
||||
original {
|
||||
url
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
userReactions {
|
||||
_id
|
||||
reactions
|
||||
createdAt
|
||||
__typename
|
||||
}
|
||||
topReactions
|
||||
totalSaveCount
|
||||
saved
|
||||
blerpLibraryType
|
||||
license
|
||||
licenseMetaData
|
||||
playCount
|
||||
totalShareCount
|
||||
totalFavoriteCount
|
||||
totalAddedToBoardCount
|
||||
userCategory
|
||||
userAudioQuality
|
||||
audioCreationState
|
||||
transcription
|
||||
userTranscription
|
||||
description
|
||||
createdAt
|
||||
updatedAt
|
||||
author
|
||||
listingType
|
||||
ownerObject {
|
||||
_id
|
||||
username
|
||||
profileImage {
|
||||
filename
|
||||
original {
|
||||
url
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
transcription
|
||||
favorited
|
||||
visibility
|
||||
isCurated
|
||||
sourceUrl
|
||||
audienceRating
|
||||
strictAudienceRating
|
||||
ownerId
|
||||
reportObject {
|
||||
reportedContentStatus
|
||||
__typename
|
||||
}
|
||||
giphy {
|
||||
mp4
|
||||
gif
|
||||
__typename
|
||||
}
|
||||
audio {
|
||||
filename
|
||||
original {
|
||||
url
|
||||
__typename
|
||||
}
|
||||
mp3 {
|
||||
url
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
|
||||
''')
|
||||
|
||||
def _real_extract(self, url):
|
||||
audio_id = self._match_id(url)
|
||||
|
||||
data = {
|
||||
'operationName': self._GRAPHQL_OPERATIONNAME,
|
||||
'query': self._GRAPHQL_QUERY,
|
||||
'variables': {
|
||||
'_id': audio_id
|
||||
}
|
||||
}
|
||||
|
||||
headers = {
|
||||
'Content-Type': 'application/json'
|
||||
}
|
||||
|
||||
json_result = self._download_json('https://api.blerp.com/graphql',
|
||||
audio_id, data=json.dumps(data).encode('utf-8'), headers=headers)
|
||||
|
||||
bite_json = json_result['data']['web']['biteById']
|
||||
|
||||
info_dict = {
|
||||
'id': bite_json['_id'],
|
||||
'url': bite_json['audio']['mp3']['url'],
|
||||
'title': bite_json['title'],
|
||||
'uploader': traverse_obj(bite_json, ('ownerObject', 'username'), expected_type=strip_or_none),
|
||||
'uploader_id': traverse_obj(bite_json, ('ownerObject', '_id'), expected_type=strip_or_none),
|
||||
'ext': 'mp3',
|
||||
'tags': list(filter(None, map(strip_or_none, (traverse_obj(bite_json, 'userKeywords', expected_type=list) or []))) or None)
|
||||
}
|
||||
|
||||
return info_dict
|
||||
@ -0,0 +1,31 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import update_url
|
||||
|
||||
|
||||
class KommunetvIE(InfoExtractor):
|
||||
_VALID_URL = r'https://(\w+).kommunetv.no/archive/(?P<id>\w+)'
|
||||
_TEST = {
|
||||
'url': 'https://oslo.kommunetv.no/archive/921',
|
||||
'md5': '5f102be308ee759be1e12b63d5da4bbc',
|
||||
'info_dict': {
|
||||
'id': '921',
|
||||
'title': 'Bystyremøte',
|
||||
'ext': 'mp4'
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
headers = {
|
||||
'Accept': 'application/json'
|
||||
}
|
||||
data = self._download_json('https://oslo.kommunetv.no/api/streams?streamType=1&id=%s' % video_id, video_id, headers=headers)
|
||||
title = data['stream']['title']
|
||||
file = data['playlist'][0]['playlist'][0]['file']
|
||||
url = update_url(file, query=None, fragment=None)
|
||||
formats = self._extract_m3u8_formats(url, video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'title': title
|
||||
}
|
||||
@ -0,0 +1,97 @@
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import merge_dicts
|
||||
|
||||
|
||||
class Pr0grammStaticIE(InfoExtractor):
|
||||
# Possible urls:
|
||||
# https://pr0gramm.com/static/5466437
|
||||
_VALID_URL = r'https?://pr0gramm\.com/static/(?P<id>[0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'https://pr0gramm.com/static/5466437',
|
||||
'md5': '52fa540d70d3edc286846f8ca85938aa',
|
||||
'info_dict': {
|
||||
'id': '5466437',
|
||||
'ext': 'mp4',
|
||||
'title': 'pr0gramm-5466437 by g11st',
|
||||
'uploader': 'g11st',
|
||||
'upload_date': '20221221',
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
# Fetch media sources
|
||||
entries = self._parse_html5_media_entries(url, webpage, video_id)
|
||||
media_info = entries[0]
|
||||
|
||||
# Fetch author
|
||||
uploader = self._html_search_regex(r'by\W+([\w-]+)\W+', webpage, 'uploader')
|
||||
|
||||
# Fetch approx upload timestamp from filename
|
||||
# Have None-defaults in case the extraction fails
|
||||
uploadDay = None
|
||||
uploadMon = None
|
||||
uploadYear = None
|
||||
uploadTimestr = None
|
||||
# (//img.pr0gramm.com/2022/12/21/62ae8aa5e2da0ebf.mp4)
|
||||
m = re.search(r'//img\.pr0gramm\.com/(?P<year>[\d]+)/(?P<mon>[\d]+)/(?P<day>[\d]+)/\w+\.\w{,4}', webpage)
|
||||
|
||||
if (m):
|
||||
# Up to a day of accuracy should suffice...
|
||||
uploadDay = m.groupdict().get('day')
|
||||
uploadMon = m.groupdict().get('mon')
|
||||
uploadYear = m.groupdict().get('year')
|
||||
uploadTimestr = uploadYear + uploadMon + uploadDay
|
||||
|
||||
return merge_dicts({
|
||||
'id': video_id,
|
||||
'title': 'pr0gramm-%s%s' % (video_id, (' by ' + uploader) if uploader else ''),
|
||||
'uploader': uploader,
|
||||
'upload_date': uploadTimestr
|
||||
}, media_info)
|
||||
|
||||
|
||||
# This extractor is for the primary url (used for sharing, and appears in the
|
||||
# location bar) Since this page loads the DOM via JS, yt-dl can't find any
|
||||
# video information here. So let's redirect to a compatibility version of
|
||||
# the site, which does contain the <video>-element by itself, without requiring
|
||||
# js to be ran.
|
||||
class Pr0grammIE(InfoExtractor):
|
||||
# Possible urls:
|
||||
# https://pr0gramm.com/new/546637
|
||||
# https://pr0gramm.com/new/video/546637
|
||||
# https://pr0gramm.com/top/546637
|
||||
# https://pr0gramm.com/top/video/546637
|
||||
# https://pr0gramm.com/user/g11st/uploads/5466437
|
||||
# https://pr0gramm.com/user/froschler/dafur-ist-man-hier/5091290
|
||||
# https://pr0gramm.com/user/froschler/reinziehen-1elf/5232030
|
||||
# https://pr0gramm.com/user/froschler/1elf/5232030
|
||||
# https://pr0gramm.com/new/5495710:comment62621020 <- this is not the id!
|
||||
# https://pr0gramm.com/top/fruher war alles damals/5498175
|
||||
|
||||
_VALID_URL = r'https?:\/\/pr0gramm\.com\/(?!static/\d+).+?\/(?P<id>[\d]+)(:|$)'
|
||||
_TEST = {
|
||||
'url': 'https://pr0gramm.com/new/video/5466437',
|
||||
'info_dict': {
|
||||
'id': '5466437',
|
||||
'ext': 'mp4',
|
||||
'title': 'pr0gramm-5466437 by g11st',
|
||||
'uploader': 'g11st',
|
||||
'upload_date': '20221221',
|
||||
}
|
||||
}
|
||||
|
||||
def _generic_title():
|
||||
return "oof"
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
return self.url_result(
|
||||
'https://pr0gramm.com/static/' + video_id,
|
||||
video_id=video_id,
|
||||
ie=Pr0grammStaticIE.ie_key())
|
||||
@ -0,0 +1,93 @@
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class RbgTumIE(InfoExtractor):
|
||||
_VALID_URL = r'https://live\.rbg\.tum\.de/w/(?P<id>.+)'
|
||||
_TESTS = [{
|
||||
# Combined view
|
||||
'url': 'https://live.rbg.tum.de/w/cpp/22128',
|
||||
'md5': '53a5e7b3e07128e33bbf36687fe1c08f',
|
||||
'info_dict': {
|
||||
'id': 'cpp/22128',
|
||||
'ext': 'mp4',
|
||||
'title': 'Lecture: October 18. 2022',
|
||||
'series': 'Concepts of C++ programming (IN2377)',
|
||||
}
|
||||
}, {
|
||||
# Presentation only
|
||||
'url': 'https://live.rbg.tum.de/w/I2DL/12349/PRES',
|
||||
'md5': '36c584272179f3e56b0db5d880639cba',
|
||||
'info_dict': {
|
||||
'id': 'I2DL/12349/PRES',
|
||||
'ext': 'mp4',
|
||||
'title': 'Lecture 3: Introduction to Neural Networks',
|
||||
'series': 'Introduction to Deep Learning (IN2346)',
|
||||
}
|
||||
}, {
|
||||
# Camera only
|
||||
'url': 'https://live.rbg.tum.de/w/fvv-info/16130/CAM',
|
||||
'md5': 'e04189d92ff2f56aedf5cede65d37aad',
|
||||
'info_dict': {
|
||||
'id': 'fvv-info/16130/CAM',
|
||||
'ext': 'mp4',
|
||||
'title': 'Fachschaftsvollversammlung',
|
||||
'series': 'Fachschaftsvollversammlung Informatik',
|
||||
}
|
||||
}, ]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
m3u8 = self._html_search_regex(r'(https://.+?\.m3u8)', webpage, 'm3u8')
|
||||
lecture_title = self._html_search_regex(r'(?si)<h1.*?>(.*)</h1>', webpage, 'title')
|
||||
lecture_series_title = self._html_search_regex(
|
||||
r'(?s)<title\b[^>]*>\s*(?:TUM-Live\s\|\s?)?([^:]+):?.*?</title>', webpage, 'series')
|
||||
|
||||
formats = self._extract_m3u8_formats(m3u8, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': lecture_title,
|
||||
'series': lecture_series_title,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
|
||||
class RbgTumCourseIE(InfoExtractor):
|
||||
_VALID_URL = r'https://live\.rbg\.tum\.de/course/(?P<id>.+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://live.rbg.tum.de/course/2022/S/fpv',
|
||||
'info_dict': {
|
||||
'title': 'Funktionale Programmierung und Verifikation (IN0003)',
|
||||
'id': '2022/S/fpv',
|
||||
},
|
||||
'params': {
|
||||
'noplaylist': False,
|
||||
},
|
||||
'playlist_count': 13,
|
||||
}, {
|
||||
'url': 'https://live.rbg.tum.de/course/2022/W/set',
|
||||
'info_dict': {
|
||||
'title': 'SET FSMPIC',
|
||||
'id': '2022/W/set',
|
||||
},
|
||||
'params': {
|
||||
'noplaylist': False,
|
||||
},
|
||||
'playlist_count': 6,
|
||||
}, ]
|
||||
|
||||
def _real_extract(self, url):
|
||||
course_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, course_id)
|
||||
|
||||
lecture_series_title = self._html_search_regex(r'(?si)<h1.*?>(.*)</h1>', webpage, 'title')
|
||||
|
||||
lecture_urls = []
|
||||
for lecture_url in re.findall(r'(?i)href="/w/(.+)(?<!/cam)(?<!/pres)(?<!/chat)"', webpage):
|
||||
lecture_urls.append(self.url_result('https://live.rbg.tum.de/w/' + lecture_url, ie=RbgTumIE.ie_key()))
|
||||
|
||||
return self.playlist_result(lecture_urls, course_id, lecture_series_title)
|
||||
Loading…
Reference in New Issue