[nitter] Minor fixes and update instance list (#3099)

Authored by: foghawk
This commit is contained in:
foghawk 2022-03-18 16:08:38 -05:00 committed by GitHub
parent f4ad919298
commit 510809f1aa
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23

View file

@ -5,7 +5,6 @@ from .common import InfoExtractor
from ..compat import compat_urlparse from ..compat import compat_urlparse
from ..utils import ( from ..utils import (
parse_count, parse_count,
unified_strdate,
unified_timestamp, unified_timestamp,
remove_end, remove_end,
determine_ext, determine_ext,
@ -25,6 +24,16 @@ class NitterIE(InfoExtractor):
'nitter.v6vgyqpa7yefkorazmg5d5fimstmvm2vtbirt6676mt7qmllrcnwycqd.onion', 'nitter.v6vgyqpa7yefkorazmg5d5fimstmvm2vtbirt6676mt7qmllrcnwycqd.onion',
'i23nv6w3juvzlw32xzoxcqzktegd4i4fu3nmnc2ewv4ggiu4ledwklad.onion', 'i23nv6w3juvzlw32xzoxcqzktegd4i4fu3nmnc2ewv4ggiu4ledwklad.onion',
'26oq3gioiwcmfojub37nz5gzbkdiqp7fue5kvye7d4txv4ny6fb4wwid.onion', '26oq3gioiwcmfojub37nz5gzbkdiqp7fue5kvye7d4txv4ny6fb4wwid.onion',
'vfaomgh4jxphpbdfizkm5gbtjahmei234giqj4facbwhrfjtcldauqad.onion',
'iwgu3cv7ywf3gssed5iqtavmrlszgsxazkmwwnt4h2kdait75thdyrqd.onion',
'erpnncl5nhyji3c32dcfmztujtl3xaddqb457jsbkulq24zqq7ifdgad.onion',
'ckzuw5misyahmg7j5t5xwwuj3bwy62jfolxyux4brfflramzsvvd3syd.onion',
'jebqj47jgxleaiosfcxfibx2xdahjettuydlxbg64azd4khsxv6kawid.onion',
'nttr2iupbb6fazdpr2rgbooon2tzbbsvvkagkgkwohhodjzj43stxhad.onion',
'nitraeju2mipeziu2wtcrqsxg7h62v5y4eqgwi75uprynkj74gevvuqd.onion',
'nitter.lqs5fjmajyp7rvp4qvyubwofzi6d4imua7vs237rkc4m5qogitqwrgyd.onion',
'ibsboeui2im5o7dxnik3s5yghufumgy5abevtij5nbizequfpu4qi4ad.onion',
'ec5nvbycpfa5k6ro77blxgkyrzbkv7uy6r5cngcbkadtjj2733nm3uyd.onion',
'nitter.i2p', 'nitter.i2p',
'u6ikd6zndl3c4dsdq4mmujpntgeevdk5qzkfb57r4tnfeccrn2qa.b32.i2p', 'u6ikd6zndl3c4dsdq4mmujpntgeevdk5qzkfb57r4tnfeccrn2qa.b32.i2p',
@ -36,28 +45,55 @@ class NitterIE(InfoExtractor):
'nitter.42l.fr', 'nitter.42l.fr',
'nitter.pussthecat.org', 'nitter.pussthecat.org',
'nitter.nixnet.services', 'nitter.nixnet.services',
'nitter.mastodont.cat',
'nitter.tedomum.net',
'nitter.fdn.fr', 'nitter.fdn.fr',
'nitter.1d4.us', 'nitter.1d4.us',
'nitter.kavin.rocks', 'nitter.kavin.rocks',
'tweet.lambda.dance',
'nitter.cc',
'nitter.vxempire.xyz',
'nitter.unixfox.eu', 'nitter.unixfox.eu',
'nitter.domain.glass', 'nitter.domain.glass',
'nitter.himiko.cloud',
'nitter.eu', 'nitter.eu',
'nitter.namazso.eu', 'nitter.namazso.eu',
'nitter.mailstation.de',
'nitter.actionsack.com', 'nitter.actionsack.com',
'nitter.cattube.org',
'nitter.dark.fail',
'birdsite.xanny.family', 'birdsite.xanny.family',
'nitter.40two.app', 'nitter.hu',
'nitter.skrep.in', 'twitr.gq',
'nitter.moomoo.me',
'nittereu.moomoo.me',
'bird.from.tf',
'nitter.it',
'twitter.censors.us',
'twitter.grimneko.de',
'nitter.alefvanoon.xyz',
'n.hyperborea.cloud',
'nitter.ca',
'twitter.076.ne.jp',
'twitter.mstdn.social',
'nitter.fly.dev',
'notabird.site',
'nitter.weiler.rocks',
'nitter.silkky.cloud',
'nitter.sethforprivacy.com',
'nttr.stream',
'nitter.cutelab.space',
'nitter.nl',
'nitter.mint.lgbt',
'nitter.bus-hit.me',
'fuckthesacklers.network',
'nitter.govt.land',
'nitter.datatunnel.xyz',
'nitter.esmailelbob.xyz',
'tw.artemislena.eu',
'de.nttr.stream',
'nitter.winscloud.net',
'nitter.tiekoetter.com',
'nitter.spaceint.fr',
'twtr.bch.bar',
'nitter.exonip.de',
'nitter.mastodon.pro',
'nitter.notraxx.ch',
# not in the list anymore # not in the list anymore
'nitter.skrep.in',
'nitter.snopyta.org', 'nitter.snopyta.org',
) )
@ -68,96 +104,121 @@ class NitterIE(InfoExtractor):
# official, rate limited # official, rate limited
'nitter.net', 'nitter.net',
# offline # offline
'is-nitter.resolv.ee',
'lu-nitter.resolv.ee',
'nitter.13ad.de', 'nitter.13ad.de',
'nitter.40two.app',
'nitter.cattube.org',
'nitter.cc',
'nitter.dark.fail',
'nitter.himiko.cloud',
'nitter.koyu.space',
'nitter.mailstation.de',
'nitter.mastodont.cat',
'nitter.tedomum.net',
'nitter.tokhmi.xyz',
'nitter.weaponizedhumiliation.com', 'nitter.weaponizedhumiliation.com',
'nitter.vxempire.xyz',
'tweet.lambda.dance',
) )
INSTANCES = NON_HTTP_INSTANCES + HTTP_INSTANCES + DEAD_INSTANCES INSTANCES = NON_HTTP_INSTANCES + HTTP_INSTANCES + DEAD_INSTANCES
_INSTANCES_RE = '(?:' + '|'.join([re.escape(instance) for instance in INSTANCES]) + ')' _INSTANCES_RE = f'(?:{"|".join(map(re.escape, INSTANCES))})'
_VALID_URL = r'https?://%(instance)s/(?P<uploader_id>.+)/status/(?P<id>[0-9]+)(#.)?' % {'instance': _INSTANCES_RE} _VALID_URL = fr'https?://{_INSTANCES_RE}/(?P<uploader_id>.+)/status/(?P<id>[0-9]+)(#.)?'
current_instance = random.choice(HTTP_INSTANCES) current_instance = random.choice(HTTP_INSTANCES)
_TESTS = [ _TESTS = [
{ {
# GIF (wrapped in mp4) # GIF (wrapped in mp4)
'url': 'https://%s/firefox/status/1314279897502629888#m' % current_instance, 'url': f'https://{current_instance}/firefox/status/1314279897502629888#m',
'info_dict': { 'info_dict': {
'id': '1314279897502629888', 'id': '1314279897502629888',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Firefox 🔥 - You know the old saying, if you see something say something. Now you actually can with the YouTube regrets extension. \n\nReport harmful YouTube recommendations so others can avoid watching them. ➡️ https://mzl.la/3iFIiyg\n\n#UnfckTheInternet', 'title': 'md5:7890a9277da4639ab624dd899424c5d8',
'description': 'You know the old saying, if you see something say something. Now you actually can with the YouTube regrets extension. \n\nReport harmful YouTube recommendations so others can avoid watching them. ➡️ https://mzl.la/3iFIiyg\n\n#UnfckTheInternet', 'description': 'md5:5fea96a4d3716c350f8b95b21b3111fe',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Firefox 🔥', 'uploader': 'Firefox 🔥',
'uploader_id': 'firefox', 'uploader_id': 'firefox',
'uploader_url': 'https://%s/firefox' % current_instance, 'uploader_url': f'https://{current_instance}/firefox',
'upload_date': '20201008', 'upload_date': '20201008',
'timestamp': 1602183720, 'timestamp': 1602183720,
'like_count': int,
'repost_count': int,
'comment_count': int,
}, },
}, { # normal video }, { # normal video
'url': 'https://%s/Le___Doc/status/1299715685392756737#m' % current_instance, 'url': f'https://{current_instance}/Le___Doc/status/1299715685392756737#m',
'info_dict': { 'info_dict': {
'id': '1299715685392756737', 'id': '1299715685392756737',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Le Doc - "Je ne prédis jamais rien"\nD Raoult, Août 2020...', 'title': 're:^.* - "Je ne prédis jamais rien"\nD Raoult, Août 2020...',
'description': '"Je ne prédis jamais rien"\nD Raoult, Août 2020...', 'description': '"Je ne prédis jamais rien"\nD Raoult, Août 2020...',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Le Doc', 'uploader': 're:^Le *Doc',
'uploader_id': 'Le___Doc', 'uploader_id': 'Le___Doc',
'uploader_url': 'https://%s/Le___Doc' % current_instance, 'uploader_url': f'https://{current_instance}/Le___Doc',
'upload_date': '20200829', 'upload_date': '20200829',
'timestamp': 1598711341, 'timestamp': 1598711340,
'view_count': int, 'view_count': int,
'like_count': int, 'like_count': int,
'repost_count': int, 'repost_count': int,
'comment_count': int, 'comment_count': int,
}, },
}, { # video embed in a "Streaming Political Ads" box }, { # video embed in a "Streaming Political Ads" box
'url': 'https://%s/mozilla/status/1321147074491092994#m' % current_instance, 'url': f'https://{current_instance}/mozilla/status/1321147074491092994#m',
'info_dict': { 'info_dict': {
'id': '1321147074491092994', 'id': '1321147074491092994',
'ext': 'mp4', 'ext': 'mp4',
'title': "Mozilla - Are you being targeted with weird, ominous or just plain annoying political ads while streaming your favorite shows?\n\nThis isn't a real political ad, but if you're watching streaming TV in the U.S., chances are you've seen quite a few. \n\nLearn more ➡️ https://mzl.la/StreamingAds", 'title': 'md5:8290664aabb43b9189145c008386bf12',
'description': "Are you being targeted with weird, ominous or just plain annoying political ads while streaming your favorite shows?\n\nThis isn't a real political ad, but if you're watching streaming TV in the U.S., chances are you've seen quite a few. \n\nLearn more ➡️ https://mzl.la/StreamingAds", 'description': 'md5:9cf2762d49674bc416a191a689fb2aaa',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Mozilla', 'uploader': 'Mozilla',
'uploader_id': 'mozilla', 'uploader_id': 'mozilla',
'uploader_url': 'https://%s/mozilla' % current_instance, 'uploader_url': f'https://{current_instance}/mozilla',
'upload_date': '20201027', 'upload_date': '20201027',
'timestamp': 1603820982 'timestamp': 1603820940,
'view_count': int,
'like_count': int,
'repost_count': int,
'comment_count': int,
}, },
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
}, { # not the first tweet but main-tweet }, { # not the first tweet but main-tweet
'url': 'https://%s/TheNaturalNu/status/1379050895539724290#m' % current_instance, 'url': f'https://{current_instance}/firefox/status/1354848277481414657#m',
'info_dict': { 'info_dict': {
'id': '1379050895539724290', 'id': '1354848277481414657',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Dorothy Zbornak - This had me hollering!!', 'title': 'md5:bef647f03bd1c6b15b687ea70dfc9700',
'description': 'This had me hollering!!', 'description': 'md5:5efba25e2f9dac85ebcd21160cb4341f',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Dorothy Zbornak', 'uploader': 'Firefox 🔥',
'uploader_id': 'TheNaturalNu', 'uploader_id': 'firefox',
'uploader_url': 'https://%s/TheNaturalNu' % current_instance, 'uploader_url': f'https://{current_instance}/firefox',
'timestamp': 1617626329, 'upload_date': '20210128',
'upload_date': '20210405' 'timestamp': 1611855960,
'view_count': int,
'like_count': int,
'repost_count': int,
'comment_count': int,
} }
} }
] ]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id, uploader_id = self._match_valid_url(url).group('id', 'uploader_id')
parsed_url = compat_urlparse.urlparse(url) parsed_url = compat_urlparse.urlparse(url)
base_url = '%s://%s' % (parsed_url.scheme, parsed_url.netloc) base_url = f'{parsed_url.scheme}://{parsed_url.netloc}'
self._set_cookie(parsed_url.netloc, 'hlsPlayback', 'on') self._set_cookie(parsed_url.netloc, 'hlsPlayback', 'on')
full_webpage = self._download_webpage(url, video_id) full_webpage = webpage = self._download_webpage(url, video_id)
main_tweet_start = full_webpage.find('class="main-tweet"') main_tweet_start = full_webpage.find('class="main-tweet"')
if main_tweet_start > 0: if main_tweet_start > 0:
webpage = full_webpage[main_tweet_start:] webpage = full_webpage[main_tweet_start:]
if not webpage:
webpage = full_webpage
video_url = '%s%s' % (base_url, self._html_search_regex(r'(?:<video[^>]+data-url|<source[^>]+src)="([^"]+)"', webpage, 'video url')) video_url = '%s%s' % (base_url, self._html_search_regex(
r'(?:<video[^>]+data-url|<source[^>]+src)="([^"]+)"', webpage, 'video url'))
ext = determine_ext(video_url) ext = determine_ext(video_url)
if ext == 'unknown_video': if ext == 'unknown_video':
@ -168,61 +229,49 @@ class NitterIE(InfoExtractor):
'ext': ext 'ext': ext
}] }]
title = self._og_search_description(full_webpage) title = description = self._og_search_description(full_webpage) or self._html_search_regex(
if not title: r'<div class="tweet-content[^>]+>([^<]+)</div>', webpage, 'title', fatal=False)
title = self._html_search_regex(r'<div class="tweet-content[^>]+>([^<]+)</div>', webpage, 'title')
description = title
mobj = self._match_valid_url(url) uploader_id = self._html_search_regex(
uploader_id = ( r'<a class="username"[^>]+title="@([^"]+)"', webpage, 'uploader id', fatal=False) or uploader_id
mobj.group('uploader_id')
or self._html_search_regex(r'<a class="fullname"[^>]+title="([^"]+)"', webpage, 'uploader name', fatal=False)
)
if uploader_id:
uploader_url = '%s/%s' % (base_url, uploader_id)
uploader = self._html_search_regex(r'<a class="fullname"[^>]+title="([^"]+)"', webpage, 'uploader name', fatal=False)
uploader = self._html_search_regex(
r'<a class="fullname"[^>]+title="([^"]+)"', webpage, 'uploader name', fatal=False)
if uploader: if uploader:
title = '%s - %s' % (uploader, title) title = f'{uploader} - {title}'
view_count = parse_count(self._html_search_regex(r'<span[^>]+class="icon-play[^>]*></span>\s([^<]+)</div>', webpage, 'view count', fatal=False)) counts = {
like_count = parse_count(self._html_search_regex(r'<span[^>]+class="icon-heart[^>]*></span>\s([^<]+)</div>', webpage, 'like count', fatal=False)) f'{x[0]}_count': self._html_search_regex(
repost_count = parse_count(self._html_search_regex(r'<span[^>]+class="icon-retweet[^>]*></span>\s([^<]+)</div>', webpage, 'repost count', fatal=False)) fr'<span[^>]+class="icon-{x[1]}[^>]*></span>([^<]*)</div>',
comment_count = parse_count(self._html_search_regex(r'<span[^>]+class="icon-comment[^>]*></span>\s([^<]+)</div>', webpage, 'repost count', fatal=False)) webpage, f'{x[0]} count', fatal=False)
for x in (('view', 'play'), ('like', 'heart'), ('repost', 'retweet'), ('comment', 'comment'))
}
counts = {field: 0 if count == '' else parse_count(count) for field, count in counts.items()}
thumbnail = self._html_search_meta('og:image', full_webpage, 'thumbnail url') thumbnail = (
if not thumbnail: self._html_search_meta('og:image', full_webpage, 'thumbnail url')
thumbnail = '%s%s' % (base_url, self._html_search_regex(r'<video[^>]+poster="([^"]+)"', webpage, 'thumbnail url', fatal=False)) or remove_end('%s%s' % (base_url, self._html_search_regex(
thumbnail = remove_end(thumbnail, '%3Asmall') r'<video[^>]+poster="([^"]+)"', webpage, 'thumbnail url', fatal=False)), '%3Asmall'))
thumbnails = [] thumbnails = [
thumbnail_ids = ('thumb', 'small', 'large', 'medium', 'orig') {'id': id, 'url': f'{thumbnail}%3A{id}'}
for id in thumbnail_ids: for id in ('thumb', 'small', 'large', 'medium', 'orig')
thumbnails.append({ ]
'id': id,
'url': thumbnail + '%3A' + id,
})
date = self._html_search_regex(r'<span[^>]+class="tweet-date"[^>]*><a[^>]+title="([^"]+)"', webpage, 'upload date', fatal=False) date = self._html_search_regex(
upload_date = unified_strdate(date) r'<span[^>]+class="tweet-date"[^>]*><a[^>]+title="([^"]+)"',
timestamp = unified_timestamp(date) webpage, 'upload date', default='').replace('·', '')
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'description': description, 'description': description,
'uploader': uploader, 'uploader': uploader,
'timestamp': timestamp, 'timestamp': unified_timestamp(date),
'uploader_id': uploader_id, 'uploader_id': uploader_id,
'uploader_url': uploader_url, 'uploader_url': f'{base_url}/{uploader_id}',
'view_count': view_count,
'like_count': like_count,
'repost_count': repost_count,
'comment_count': comment_count,
'formats': formats, 'formats': formats,
'thumbnails': thumbnails, 'thumbnails': thumbnails,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'upload_date': upload_date, **counts,
} }