mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-06-26 00:27:57 +00:00
Compare commits
11 Commits
88ea61c877
...
bf086048a8
Author | SHA1 | Date | |
---|---|---|---|
![]() |
bf086048a8 | ||
![]() |
0153b387e5 | ||
![]() |
a48fe7491d | ||
![]() |
e20ca543f0 | ||
![]() |
e39466051f | ||
![]() |
d95c0d203f | ||
![]() |
3bde6a5752 | ||
![]() |
50f6c5668a | ||
![]() |
b4ff08bd2d | ||
![]() |
88bd8b9f87 | ||
![]() |
5966b43092 |
|
@ -5,9 +5,9 @@ import hashlib
|
|||
import json
|
||||
import os.path
|
||||
import re
|
||||
import types
|
||||
import ssl
|
||||
import sys
|
||||
import types
|
||||
import unittest
|
||||
|
||||
import youtube_dl.extractor
|
||||
|
@ -181,18 +181,18 @@ def expect_value(self, got, expected, field):
|
|||
op, _, expected_num = expected.partition(':')
|
||||
expected_num = int(expected_num)
|
||||
if op == 'mincount':
|
||||
assert_func = assertGreaterEqual
|
||||
assert_func = self.assertGreaterEqual
|
||||
msg_tmpl = 'Expected %d items in field %s, but only got %d'
|
||||
elif op == 'maxcount':
|
||||
assert_func = assertLessEqual
|
||||
assert_func = self.assertLessEqual
|
||||
msg_tmpl = 'Expected maximum %d items in field %s, but got %d'
|
||||
elif op == 'count':
|
||||
assert_func = assertEqual
|
||||
assert_func = self.assertEqual
|
||||
msg_tmpl = 'Expected exactly %d items in field %s, but got %d'
|
||||
else:
|
||||
assert False
|
||||
assert_func(
|
||||
self, len(got), expected_num,
|
||||
len(got), expected_num,
|
||||
msg_tmpl % (expected_num, field, len(got)))
|
||||
return
|
||||
self.assertEqual(
|
||||
|
@ -262,27 +262,6 @@ def assertRegexpMatches(self, text, regexp, msg=None):
|
|||
self.assertTrue(m, msg)
|
||||
|
||||
|
||||
def assertGreaterEqual(self, got, expected, msg=None):
|
||||
if not (got >= expected):
|
||||
if msg is None:
|
||||
msg = '%r not greater than or equal to %r' % (got, expected)
|
||||
self.assertTrue(got >= expected, msg)
|
||||
|
||||
|
||||
def assertLessEqual(self, got, expected, msg=None):
|
||||
if not (got <= expected):
|
||||
if msg is None:
|
||||
msg = '%r not less than or equal to %r' % (got, expected)
|
||||
self.assertTrue(got <= expected, msg)
|
||||
|
||||
|
||||
def assertEqual(self, got, expected, msg=None):
|
||||
if not (got == expected):
|
||||
if msg is None:
|
||||
msg = '%r not equal to %r' % (got, expected)
|
||||
self.assertTrue(got == expected, msg)
|
||||
|
||||
|
||||
def expect_warnings(ydl, warnings_re):
|
||||
real_warning = ydl.report_warning
|
||||
|
||||
|
|
|
@ -9,8 +9,6 @@ import unittest
|
|||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from test.helper import (
|
||||
assertGreaterEqual,
|
||||
assertLessEqual,
|
||||
expect_warnings,
|
||||
get_params,
|
||||
gettestcases,
|
||||
|
@ -36,12 +34,20 @@ from youtube_dl.utils import (
|
|||
ExtractorError,
|
||||
error_to_compat_str,
|
||||
format_bytes,
|
||||
IDENTITY,
|
||||
preferredencoding,
|
||||
UnavailableVideoError,
|
||||
)
|
||||
from youtube_dl.extractor import get_info_extractor
|
||||
|
||||
RETRIES = 3
|
||||
|
||||
# Some unittest APIs require actual str
|
||||
if not isinstance('TEST', str):
|
||||
_encode_str = lambda s: s.encode(preferredencoding())
|
||||
else:
|
||||
_encode_str = IDENTITY
|
||||
|
||||
|
||||
class YoutubeDL(youtube_dl.YoutubeDL):
|
||||
def __init__(self, *args, **kwargs):
|
||||
|
@ -102,7 +108,7 @@ def generator(test_case, tname):
|
|||
|
||||
def print_skipping(reason):
|
||||
print('Skipping %s: %s' % (test_case['name'], reason))
|
||||
self.skipTest(reason)
|
||||
self.skipTest(_encode_str(reason))
|
||||
|
||||
if not ie.working():
|
||||
print_skipping('IE marked as not _WORKING')
|
||||
|
@ -187,16 +193,14 @@ def generator(test_case, tname):
|
|||
expect_info_dict(self, res_dict, test_case.get('info_dict', {}))
|
||||
|
||||
if 'playlist_mincount' in test_case:
|
||||
assertGreaterEqual(
|
||||
self,
|
||||
self.assertGreaterEqual(
|
||||
len(res_dict['entries']),
|
||||
test_case['playlist_mincount'],
|
||||
'Expected at least %d in playlist %s, but got only %d' % (
|
||||
test_case['playlist_mincount'], test_case['url'],
|
||||
len(res_dict['entries'])))
|
||||
if 'playlist_maxcount' in test_case:
|
||||
assertLessEqual(
|
||||
self,
|
||||
self.assertLessEqual(
|
||||
len(res_dict['entries']),
|
||||
test_case['playlist_maxcount'],
|
||||
'Expected at most %d in playlist %s, but got %d' % (
|
||||
|
@ -243,8 +247,8 @@ def generator(test_case, tname):
|
|||
if params.get('test'):
|
||||
expected_minsize = max(expected_minsize, 10000)
|
||||
got_fsize = os.path.getsize(tc_filename)
|
||||
assertGreaterEqual(
|
||||
self, got_fsize, expected_minsize,
|
||||
self.assertGreaterEqual(
|
||||
got_fsize, expected_minsize,
|
||||
'Expected %s to be at least %s, but it\'s only %s ' %
|
||||
(tc_filename, format_bytes(expected_minsize),
|
||||
format_bytes(got_fsize)))
|
||||
|
|
|
@ -1039,8 +1039,8 @@ class YoutubeDL(object):
|
|||
elif result_type in ('playlist', 'multi_video'):
|
||||
# Protect from infinite recursion due to recursively nested playlists
|
||||
# (see https://github.com/ytdl-org/youtube-dl/issues/27833)
|
||||
webpage_url = ie_result['webpage_url']
|
||||
if webpage_url in self._playlist_urls:
|
||||
webpage_url = ie_result.get('webpage_url') # not all pl/mv have this
|
||||
if webpage_url and webpage_url in self._playlist_urls:
|
||||
self.to_screen(
|
||||
'[download] Skipping already downloaded playlist: %s'
|
||||
% ie_result.get('title') or ie_result.get('id'))
|
||||
|
@ -1048,6 +1048,10 @@ class YoutubeDL(object):
|
|||
|
||||
self._playlist_level += 1
|
||||
self._playlist_urls.add(webpage_url)
|
||||
new_result = dict((k, v) for k, v in extra_info.items() if k not in ie_result)
|
||||
if new_result:
|
||||
new_result.update(ie_result)
|
||||
ie_result = new_result
|
||||
try:
|
||||
return self.__process_playlist(ie_result, download)
|
||||
finally:
|
||||
|
@ -1593,6 +1597,28 @@ class YoutubeDL(object):
|
|||
self.cookiejar.add_cookie_header(pr)
|
||||
return pr.get_header('Cookie')
|
||||
|
||||
def _fill_common_fields(self, info_dict, final=True):
|
||||
|
||||
for ts_key, date_key in (
|
||||
('timestamp', 'upload_date'),
|
||||
('release_timestamp', 'release_date'),
|
||||
):
|
||||
if info_dict.get(date_key) is None and info_dict.get(ts_key) is not None:
|
||||
# Working around out-of-range timestamp values (e.g. negative ones on Windows,
|
||||
# see http://bugs.python.org/issue1646728)
|
||||
try:
|
||||
upload_date = datetime.datetime.utcfromtimestamp(info_dict[ts_key])
|
||||
info_dict[date_key] = compat_str(upload_date.strftime('%Y%m%d'))
|
||||
except (ValueError, OverflowError, OSError):
|
||||
pass
|
||||
|
||||
# Auto generate title fields corresponding to the *_number fields when missing
|
||||
# in order to always have clean titles. This is very common for TV series.
|
||||
if final:
|
||||
for field in ('chapter', 'season', 'episode'):
|
||||
if info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
|
||||
info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
|
||||
|
||||
def process_video_result(self, info_dict, download=True):
|
||||
assert info_dict.get('_type', 'video') == 'video'
|
||||
|
||||
|
@ -1660,24 +1686,7 @@ class YoutubeDL(object):
|
|||
if 'display_id' not in info_dict and 'id' in info_dict:
|
||||
info_dict['display_id'] = info_dict['id']
|
||||
|
||||
for ts_key, date_key in (
|
||||
('timestamp', 'upload_date'),
|
||||
('release_timestamp', 'release_date'),
|
||||
):
|
||||
if info_dict.get(date_key) is None and info_dict.get(ts_key) is not None:
|
||||
# Working around out-of-range timestamp values (e.g. negative ones on Windows,
|
||||
# see http://bugs.python.org/issue1646728)
|
||||
try:
|
||||
upload_date = datetime.datetime.utcfromtimestamp(info_dict[ts_key])
|
||||
info_dict[date_key] = compat_str(upload_date.strftime('%Y%m%d'))
|
||||
except (ValueError, OverflowError, OSError):
|
||||
pass
|
||||
|
||||
# Auto generate title fields corresponding to the *_number fields when missing
|
||||
# in order to always have clean titles. This is very common for TV series.
|
||||
for field in ('chapter', 'season', 'episode'):
|
||||
if info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
|
||||
info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
|
||||
self._fill_common_fields(info_dict)
|
||||
|
||||
for cc_kind in ('subtitles', 'automatic_captions'):
|
||||
cc = info_dict.get(cc_kind)
|
||||
|
|
|
@ -494,6 +494,11 @@ from .hotstar import (
|
|||
)
|
||||
from .howcast import HowcastIE
|
||||
from .howstuffworks import HowStuffWorksIE
|
||||
from .hqporner import (
|
||||
HQPornerIE,
|
||||
HQPornerListIE,
|
||||
HQPornerSearchIE,
|
||||
)
|
||||
from .hrfernsehen import HRFernsehenIE
|
||||
from .hrti import (
|
||||
HRTiIE,
|
||||
|
@ -898,21 +903,13 @@ from .ooyala import (
|
|||
)
|
||||
from .ora import OraTVIE
|
||||
from .orf import (
|
||||
ORFTVthekIE,
|
||||
ORFFM4IE,
|
||||
ORFONIE,
|
||||
ORFONLiveIE,
|
||||
ORFFM4StoryIE,
|
||||
ORFOE1IE,
|
||||
ORFOE3IE,
|
||||
ORFNOEIE,
|
||||
ORFWIEIE,
|
||||
ORFBGLIE,
|
||||
ORFOOEIE,
|
||||
ORFSTMIE,
|
||||
ORFKTNIE,
|
||||
ORFSBGIE,
|
||||
ORFTIRIE,
|
||||
ORFVBGIE,
|
||||
ORFIPTVIE,
|
||||
ORFPodcastIE,
|
||||
ORFRadioIE,
|
||||
ORFRadioCollectionIE,
|
||||
)
|
||||
from .outsidetv import OutsideTVIE
|
||||
from .packtpub import (
|
||||
|
|
233
youtube_dl/extractor/hqporner.py
Normal file
233
youtube_dl/extractor/hqporner.py
Normal file
|
@ -0,0 +1,233 @@
|
|||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import itertools
|
||||
import re
|
||||
from string import capwords
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
date_from_str,
|
||||
get_element_by_class,
|
||||
get_element_by_id,
|
||||
int_or_none,
|
||||
join_nonempty,
|
||||
parse_duration,
|
||||
strip_or_none,
|
||||
unified_strdate,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
class HQPornerIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?hqporner\.com/hdporn/(?P<id>[\d]+)-'
|
||||
_TESTS = [{
|
||||
'url': 'https://hqporner.com/hdporn/110374-looking_for_a_change_of_pace.html',
|
||||
'md5': '7eb7b791a1ce8a619bde603b2dc334b5',
|
||||
'info_dict': {
|
||||
'id': '110374',
|
||||
'ext': 'mp4',
|
||||
'title': 'Looking For A Change Of Pace',
|
||||
'description': 'featuring Myra',
|
||||
'upload_date': '20230227',
|
||||
'age_limit': 18,
|
||||
'tags': list,
|
||||
'categories': list,
|
||||
'duration': 3271,
|
||||
'thumbnail': r're:https?://.*\.jpg',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://hqporner.com/hdporn/86482-all_night_rager.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
# some pages need a `referer` to avoid 404
|
||||
webpage = self._download_webpage(url, video_id, headers={'referer': 'https://hqporner.com/?q=porn'})
|
||||
|
||||
# details below video are in a <header> element
|
||||
heading = self._search_regex(r'''(?s)(<header>.+?</section>)\s*</div>''', webpage, 'heading', default='')
|
||||
title = (
|
||||
capwords(clean_html(get_element_by_class('main-h1', heading) or ''))
|
||||
or self._html_search_regex(
|
||||
r'<title\b[^>]*>\s*([^<]+)(?:\s+-\s+HQporner\.com)?\s*</title>',
|
||||
webpage, 'title'))
|
||||
# video details are in a page loaded by this <iframe>
|
||||
player = get_element_by_id('playerWrapper', webpage)
|
||||
player = self._search_regex(
|
||||
r'''<iframe [^>]*\bsrc\s*=\s*('|")(?P<url>(?:(?!\1)\S)+)''',
|
||||
player, 'player iframe', group='url')
|
||||
player = self._download_webpage(urljoin(url, player), video_id, note='Downloading player iframe')
|
||||
# select the complete set of videos
|
||||
player = self._search_regex(
|
||||
r'''\belse\s*\{\s*\$\s*\(\s*('|")#jw\1\s*\)\s*\.\s*html\s*\(\s*(?P<vstr>("|')\s*<video [^>]+>[^)]+</video>\s*\3)''',
|
||||
player, 'video element', group='vstr')
|
||||
# it's a string containing HTML5 video
|
||||
info = self._parse_html5_media_entries(
|
||||
url, self._parse_json(player, video_id), video_id)[0] # not used now: m3u8_id='hls', m3u8_entry_protocol='m3u8_native', mpd_id='dash')
|
||||
# site offers no timestamp, but may have "however-many date-units ago"
|
||||
upload_date = get_element_by_class('fa-calendar', heading) or ''
|
||||
if upload_date.endswith(' ago'):
|
||||
upload_date = date_from_str('now-' + upload_date[:-len(' ago')].replace(' ', '').replace('one', '1'))
|
||||
if upload_date:
|
||||
upload_date = upload_date.isoformat().replace('-', '')
|
||||
else:
|
||||
# probably ineffective
|
||||
upload_date = unified_strdate(upload_date)
|
||||
|
||||
# utils candidate
|
||||
def tag_list(s, delim=','):
|
||||
return [t for t in map(strip_or_none, s.split(delim)) if t] or None
|
||||
|
||||
desc = self._html_search_meta('description', webpage, default='')
|
||||
|
||||
info.update({
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'age_limit': 18,
|
||||
'upload_date': upload_date,
|
||||
'description': clean_html(get_element_by_class('icon fa-star-o', heading)),
|
||||
'duration': parse_duration(
|
||||
get_element_by_class('fa-clock-o', heading)
|
||||
or self._search_regex(r'Video duration is\s+([^.]+)', desc, 'duration', default='')),
|
||||
'categories': tag_list(
|
||||
clean_html(self._search_regex(r'(?s)</h3>\s*<p>(.+?)</p>', heading, 'categories', default='').replace('</a>', ','))
|
||||
or self._html_search_meta('keywords', webpage, default='')),
|
||||
'tags': tag_list(self._search_regex(r'Tags [\w\s-]+:\s+([^.]+)', desc, 'tags', default='')),
|
||||
})
|
||||
return info
|
||||
|
||||
|
||||
class HQPornerListBaseIE(InfoExtractor):
|
||||
|
||||
# yt-dlp shim
|
||||
@classmethod
|
||||
def _match_valid_url(cls, url):
|
||||
return re.match(cls._VALID_URL, url)
|
||||
|
||||
def _real_extract(self, url):
|
||||
pl_id, pg = self._match_valid_url(url).group('id', 'pg')
|
||||
pg = int_or_none(pg)
|
||||
|
||||
def entries():
|
||||
"""
|
||||
Generate the playlist
|
||||
If `pg` is a page number, get the list for that page
|
||||
Otherwise continue from `url` until exhausted
|
||||
"""
|
||||
next = url
|
||||
for pnum in itertools.count(start=pg or 1):
|
||||
p_url = urljoin(url, next)
|
||||
first = (pg or 1) == pnum
|
||||
if not p_url and not first:
|
||||
break
|
||||
page = self._download_webpage(
|
||||
p_url, pl_id,
|
||||
note='Downloading page' + ('' if first else (' %d' % pnum)),
|
||||
fatal=first)
|
||||
if not page:
|
||||
break
|
||||
for m in re.finditer(
|
||||
# each entry in a playlist page has a hyperlinked <img> followed by the caption:
|
||||
# <h3> containing a hyperlinked title, followed by a <span> containing duration
|
||||
r'''(?sx)
|
||||
# <img> with thumbnail (extracted), then closing containing <a><div>
|
||||
(?:<img\b[^>]+\bsrc\s*=\s*("|')(?P<thm>(?:(?!\1).)+)\1[^>]*>.*?)?
|
||||
# caption: extract href and title
|
||||
<h3\b[^>]+\bclass\s*=\s*("|')(?:(?:(?!\3).)+\s)*?meta-data-title(?:\s(?:(?!\3).)+)*\3[^>]*>\s*
|
||||
<a\b[^>]+\bhref\b=("|')(?P<url>(?:(?!\4).)+)\4[^>]*>(?P<ttl>[^<]*)</a>\s*
|
||||
</h3>\s*
|
||||
# extract duration
|
||||
(?:<span\b[^>]+\bclass\s*=\s*("|')(?:(?:(?!\7).)+\s)*?fa-clock-o(?:\s(?:(?!\7).)+)*\7[^>]*>(?P<dur>[^<]+)</span>)?
|
||||
''', page):
|
||||
a_url = self._proto_relative_url(urljoin(url, m.group('url')))
|
||||
if a_url:
|
||||
res = self.url_result(a_url, video_title=capwords(clean_html(m.group('ttl')) or '') or None)
|
||||
res.update({
|
||||
'duration': parse_duration(m.group('dur')),
|
||||
'thumbnail': self._proto_relative_url(urljoin(a_url, m.group('thm'))),
|
||||
})
|
||||
yield res
|
||||
if pg is not None:
|
||||
break
|
||||
# next is the last link in the pagination block, unless that's the current URL
|
||||
maybe_next = urljoin(url, self._search_regex(
|
||||
r'''(?s)<a\b[^>]+\bhref\s*=\s*("|')(?P<url>(?:(?!\1).)+)\1[^>]*>[^>]*</a>\s*</li>\s*$''',
|
||||
get_element_by_class('pagination', page) or '', 'next page',
|
||||
group='url', default=None))
|
||||
next = maybe_next if maybe_next != next else None
|
||||
|
||||
return self.playlist_result(entries(), playlist_id=join_nonempty(pl_id, pg, delim=':'))
|
||||
|
||||
@staticmethod
|
||||
def _set_title(info):
|
||||
pl_id, _, pg = info['id'].rpartition(':')
|
||||
if not pl_id:
|
||||
pl_id = pg
|
||||
pg = None
|
||||
info['title'] = pl_id.replace('/', ': ')
|
||||
if pg:
|
||||
info['title'] += ' [%s]' % (pg, )
|
||||
|
||||
|
||||
class HQPornerListIE(HQPornerListBaseIE):
|
||||
|
||||
_VALID_URL = r'https?://(?:www\.)?hqporner\.com/(?P<id>(?:top|(?:category|actress)/[^/]+))(?:/(?P<pg>\d+))?'
|
||||
_TESTS = [{
|
||||
'url': 'https://hqporner.com/category/beach-porn',
|
||||
'info_dict': {
|
||||
'id': 'category/beach-porn',
|
||||
'title': 'Category: beach-porn',
|
||||
},
|
||||
'playlist_mincount': 250,
|
||||
}, {
|
||||
'url': 'https://hqporner.com/category/beach-porn/2',
|
||||
'info_dict': {
|
||||
'id': 'category/beach-porn:2',
|
||||
'title': 'Category: beach-porn [2]',
|
||||
},
|
||||
'playlist_count': 50,
|
||||
}, {
|
||||
'url': 'https://hqporner.com/actress/mary/1',
|
||||
'info_dict': {
|
||||
'id': 'actress/mary:1',
|
||||
'title': 'Actress: mary [1]',
|
||||
},
|
||||
'playlist_count': 50,
|
||||
},
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
res = super(HQPornerListIE, self)._real_extract(url)
|
||||
self._set_title(res)
|
||||
res['title'] = res['title'].capitalize()
|
||||
return res
|
||||
|
||||
|
||||
class HQPornerSearchIE(HQPornerListBaseIE):
|
||||
|
||||
_VALID_URL = r'https?://(?:www\.)?hqporner\.com/\?q=(?P<id>[^&]+)(?:&p=(?P<pg>\d+))?'
|
||||
_TESTS = [{
|
||||
'url': 'https://hqporner.com/?q=french',
|
||||
'info_dict': {
|
||||
'id': 'french',
|
||||
'title': 'Searching: french',
|
||||
},
|
||||
'playlist_mincount': 250,
|
||||
}, {
|
||||
'url': 'https://hqporner.com/?q=french&p=2',
|
||||
'info_dict': {
|
||||
'id': 'french:2',
|
||||
'title': 'Searching: french [2]',
|
||||
},
|
||||
'playlist_count': 50,
|
||||
},
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
res = super(HQPornerSearchIE, self)._real_extract(url)
|
||||
self._set_title(res)
|
||||
res['title'] = 'Searching: ' + res['title']
|
||||
return res
|
|
@ -1,3 +1,4 @@
|
|||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import itertools
|
||||
|
@ -10,7 +11,7 @@ from ..compat import (
|
|||
compat_ord,
|
||||
compat_str,
|
||||
compat_urllib_parse_unquote,
|
||||
compat_zip
|
||||
compat_zip as zip,
|
||||
)
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
|
@ -24,7 +25,7 @@ class MixcloudBaseIE(InfoExtractor):
|
|||
def _call_api(self, object_type, object_fields, display_id, username, slug=None):
|
||||
lookup_key = object_type + 'Lookup'
|
||||
return self._download_json(
|
||||
'https://www.mixcloud.com/graphql', display_id, query={
|
||||
'https://app.mixcloud.com/graphql', display_id, query={
|
||||
'query': '''{
|
||||
%s(lookup: {username: "%s"%s}) {
|
||||
%s
|
||||
|
@ -44,7 +45,7 @@ class MixcloudIE(MixcloudBaseIE):
|
|||
'ext': 'm4a',
|
||||
'title': 'Cryptkeeper',
|
||||
'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
|
||||
'uploader': 'Daniel Holbach',
|
||||
'uploader': 'dholbach', # was: 'Daniel Holbach',
|
||||
'uploader_id': 'dholbach',
|
||||
'thumbnail': r're:https?://.*\.jpg',
|
||||
'view_count': int,
|
||||
|
@ -57,7 +58,7 @@ class MixcloudIE(MixcloudBaseIE):
|
|||
'id': 'gillespeterson_caribou-7-inch-vinyl-mix-chat',
|
||||
'ext': 'mp3',
|
||||
'title': 'Caribou 7 inch Vinyl Mix & Chat',
|
||||
'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
|
||||
'description': r're:Last week Dan Snaith aka Caribou swung by the Brownswood.{136}',
|
||||
'uploader': 'Gilles Peterson Worldwide',
|
||||
'uploader_id': 'gillespeterson',
|
||||
'thumbnail': 're:https?://.*',
|
||||
|
@ -65,6 +66,23 @@ class MixcloudIE(MixcloudBaseIE):
|
|||
'timestamp': 1422987057,
|
||||
'upload_date': '20150203',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': '404 not found',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.mixcloud.com/gillespeterson/carnival-m%C3%BAsica-popular-brasileira-mix/',
|
||||
'info_dict': {
|
||||
'id': 'gillespeterson_carnival-música-popular-brasileira-mix',
|
||||
'ext': 'm4a',
|
||||
'title': 'Carnival Música Popular Brasileira Mix',
|
||||
'description': r're:Gilles was recently in Brazil to play at Boiler Room.{208}',
|
||||
'timestamp': 1454347174,
|
||||
'upload_date': '20160201',
|
||||
'uploader': 'Gilles Peterson Worldwide',
|
||||
'uploader_id': 'gillespeterson',
|
||||
'thumbnail': 're:https?://.*',
|
||||
'view_count': int,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/',
|
||||
'only_matching': True,
|
||||
|
@ -76,10 +94,10 @@ class MixcloudIE(MixcloudBaseIE):
|
|||
"""Encrypt/Decrypt XOR cipher. Both ways are possible because it's XOR."""
|
||||
return ''.join([
|
||||
compat_chr(compat_ord(ch) ^ compat_ord(k))
|
||||
for ch, k in compat_zip(ciphertext, itertools.cycle(key))])
|
||||
for ch, k in zip(ciphertext, itertools.cycle(key))])
|
||||
|
||||
def _real_extract(self, url):
|
||||
username, slug = re.match(self._VALID_URL, url).groups()
|
||||
username, slug = self._match_valid_url(url).groups()
|
||||
username, slug = compat_urllib_parse_unquote(username), compat_urllib_parse_unquote(slug)
|
||||
track_id = '%s_%s' % (username, slug)
|
||||
|
||||
|
|
File diff suppressed because it is too large
Load Diff
|
@ -4,6 +4,7 @@ from __future__ import unicode_literals
|
|||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
from ..utils import (
|
||||
float_or_none,
|
||||
get_element_by_id,
|
||||
|
@ -11,6 +12,7 @@ from ..utils import (
|
|||
strip_or_none,
|
||||
unified_strdate,
|
||||
urljoin,
|
||||
str_to_int,
|
||||
)
|
||||
|
||||
|
||||
|
@ -35,6 +37,26 @@ class VidLiiIE(InfoExtractor):
|
|||
'categories': ['News & Politics'],
|
||||
'tags': ['Vidlii', 'Jan', 'Videogames'],
|
||||
}
|
||||
}, {
|
||||
# HD
|
||||
'url': 'https://www.vidlii.com/watch?v=2Ng8Abj2Fkl',
|
||||
'md5': '450e7da379c884788c3a4fa02a3ce1a4',
|
||||
'info_dict': {
|
||||
'id': '2Ng8Abj2Fkl',
|
||||
'ext': 'mp4',
|
||||
'title': 'test',
|
||||
'description': 'md5:cc55a86032a7b6b3cbfd0f6b155b52e9',
|
||||
'thumbnail': 'https://www.vidlii.com/usfi/thmp/2Ng8Abj2Fkl.jpg',
|
||||
'uploader': 'VidLii',
|
||||
'uploader_url': 'https://www.vidlii.com/user/VidLii',
|
||||
'upload_date': '20200927',
|
||||
'duration': 5,
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
'average_rating': float,
|
||||
'categories': ['Film & Animation'],
|
||||
'tags': list,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.vidlii.com/embed?v=tJluaH4BJ3v&a=0',
|
||||
'only_matching': True,
|
||||
|
@ -46,11 +68,32 @@ class VidLiiIE(InfoExtractor):
|
|||
webpage = self._download_webpage(
|
||||
'https://www.vidlii.com/watch?v=%s' % video_id, video_id)
|
||||
|
||||
video_url = self._search_regex(
|
||||
r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1', webpage,
|
||||
'video url', group='url')
|
||||
formats = []
|
||||
|
||||
title = self._search_regex(
|
||||
def add_format(format_url, height=None):
|
||||
height = int(self._search_regex(r'(\d+)\.mp4',
|
||||
format_url, 'height', default=360))
|
||||
|
||||
formats.append({
|
||||
'url': format_url,
|
||||
'format_id': '%dp' % height if height else None,
|
||||
'height': height,
|
||||
})
|
||||
|
||||
sources = re.findall(
|
||||
r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1',
|
||||
webpage)
|
||||
|
||||
formats = []
|
||||
if len(sources) > 1:
|
||||
add_format(sources[1][1])
|
||||
self._check_formats(formats, video_id)
|
||||
if len(sources) > 0:
|
||||
add_format(sources[0][1])
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
title = self._html_search_regex(
|
||||
(r'<h1>([^<]+)</h1>', r'<title>([^<]+) - VidLii<'), webpage,
|
||||
'title')
|
||||
|
||||
|
@ -82,9 +125,9 @@ class VidLiiIE(InfoExtractor):
|
|||
default=None) or self._search_regex(
|
||||
r'duration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
|
||||
|
||||
view_count = int_or_none(self._search_regex(
|
||||
(r'<strong>(\d+)</strong> views',
|
||||
r'Views\s*:\s*<strong>(\d+)</strong>'),
|
||||
view_count = str_to_int(self._html_search_regex(
|
||||
(r'<strong>([\d,.]+)</strong> views',
|
||||
r'Views\s*:\s*<strong>([\d,.]+)</strong>'),
|
||||
webpage, 'view count', fatal=False))
|
||||
|
||||
comment_count = int_or_none(self._search_regex(
|
||||
|
@ -109,7 +152,7 @@ class VidLiiIE(InfoExtractor):
|
|||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'formats': formats,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
|
|
Loading…
Reference in New Issue
Block a user