depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-05-19 11:39:28 +00:00
Code Issues Releases Wiki Activity

Merge d2d6b49a5a into e0727e4ab6

Browse source
This commit is contained in:
dirkf 2024-04-09 17:54:44 +00:00 committed by GitHub
parent e0727e4ab6 d2d6b49a5a
commit 56c9943a68
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 67 additions and 38 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

105
youtube_dl/extractor/redtube.py
View file

@ -1,33 +1,49 @@
# coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
ExtractorError, ExtractorError,
int_or_none, int_or_none,
join_nonempty,
merge_dicts, merge_dicts,
str_to_int, str_to_int,
T,
traverse_obj,
unified_strdate, unified_strdate,
url_or_none, url_or_none,
urljoin,
) )
class RedTubeIE(InfoExtractor): class RedTubeIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:\w+\.)?redtube\.com/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)' _VALID_URL = r'https?://(?:(?:\w+\.)?redtube\.com/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)'
_EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)']
_TESTS = [{ _TESTS = [{
'url': 'http://www.redtube.com/66418', 'url': 'https://www.redtube.com/38864951',
'md5': 'fc08071233725f26b8f014dba9590005', 'md5': 'd7de9cb32e8adb3f6379f1a30f655fae',
'info_dict': { 'info_dict': {
'id': '66418', 'id': '38864951',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Sucked on a toilet', 'title': 'Public Sex on the Balcony in Freezing Paris! Amateur Couple LeoLulu',
'upload_date': '20110811', 'description': 'Watch video Public Sex on the Balcony in Freezing Paris! Amateur Couple LeoLulu on Redtube, home of free Blowjob porn videos and Blonde sex movies online. Video length: (10:46) - Uploaded by leolulu - Verified User - Starring Pornstar: LeoLulu',
'duration': 596, 'upload_date': '20210111',
'timestamp': 1610343109,
'duration': 646,
'view_count': int, 'view_count': int,
'age_limit': 18, 'age_limit': 18,
} 'thumbnail': r're:https://\wi-ph\.rdtcdn\.com/videos/.+/.+\.jpg',
},
'expected_warnings': [
'Failed to download m3u8 information: HTTP Error 404',
],
'params': {
'format': '[format_id !^= hls]',
},
}, { }, {
'url': 'http://embed.redtube.com/?bgcolor=000000&id=1443286', 'url': 'http://embed.redtube.com/?bgcolor=000000&id=1443286',
'only_matching': True, 'only_matching': True,
@ -36,11 +52,11 @@ class RedTubeIE(InfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
@staticmethod @classmethod
def _extract_urls(webpage): def _extract_urls(cls, webpage):
return re.findall( for embed_re in cls._EMBED_REGEX:
r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)', for from_ in re.findall(embed_re, webpage):
webpage) yield from_
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
@ -71,40 +87,53 @@ class RedTubeIE(InfoExtractor):
self._search_regex( self._search_regex(
r'sources\s*:\s*({.+?})', webpage, 'source', default='{}'), r'sources\s*:\s*({.+?})', webpage, 'source', default='{}'),
video_id, fatal=False) video_id, fatal=False)
if sources and isinstance(sources, dict):
for format_id, format_url in sources.items(): def full_url(u):
if format_url: return urljoin(url, u)
formats.append({
'url': format_url, for fmt in traverse_obj(sources, (T(dict.items), {
'format_id': format_id, 'url': (1, T(full_url)),
'height': int_or_none(format_id), 'format_id': (2, T(compat_str)),
}) 'height': (2, T(int_or_none)), })):
medias = self._parse_json( if 'url' in fmt:
self._search_regex( formats.append(fmt)
r'mediaDefinition["\']?\s*:\s*(\[.+?}\s*\])', webpage,
'media definitions', default='{}'), medias = self._search_regex(
video_id, fatal=False) r'''mediaDefinitions?["']?\s*:\s*(\[[\s\S]+?}\s*\])''', webpage,
if medias and isinstance(medias, list): 'media definitions', default='{}')
for media in medias: medias = self._parse_json(medias, video_id, fatal=False)
format_url = url_or_none(media.get('videoUrl')) for fmt in traverse_obj(medias, (Ellipsis, T(dict))):
format_url = full_url(fmt.get('videoUrl'))
if not format_url:
continue
more_media = None
if fmt['format'] == 'hls' or (fmt['format'] == 'mp4' and not fmt.get('quality')):
more_media = self._download_json(format_url, video_id, fatal=False)
if more_media is None:
more_media = [fmt]
for fmt in traverse_obj(more_media, (Ellipsis, {
'url': ('videoUrl', T(full_url)),
'ext': ('format', T(compat_str)),
'format_id': ('quality', T(compat_str)), })):
format_url = fmt.get('url')
if not format_url: if not format_url:
continue continue
if media.get('format') == 'hls' or determine_ext(format_url) == 'm3u8': if fmt.get('ext') == 'hls' or determine_ext(format_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats( formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4', format_url, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls', entry_protocol='m3u8_native', m3u8_id='hls',
fatal=False)) fatal=False))
continue continue
format_id = media.get('quality') fmt['height'] = int_or_none(fmt.get('format_id'))
formats.append({ fmt['format_id'] = join_nonempty('ext', 'format_id', from_dict=fmt)
'url': format_url, formats.append(fmt)
'format_id': format_id,
'height': int_or_none(format_id),
})
if not formats: if not formats:
video_url = self._html_search_regex( video_url = url_or_none(self._html_search_regex(
r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL') r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL'))
formats.append({'url': video_url}) if video_url:
formats.append({'url': video_url})
self._check_formats(formats, video_id)
self._sort_formats(formats) self._sort_formats(formats)
thumbnail = self._og_search_thumbnail(webpage) thumbnail = self._og_search_thumbnail(webpage)