Merge a7c1a558edb216b49789e189e0e3d5cc8ca46f51 into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6

* thx seproDev, yt-dlp/yt-dlp/pull/12694/commits/ae69e3c
* also add documenting comment in `InfoExtractor`

youtube_dl/extractor/bokecc.py

@@ -32,7 +32,7 @@ class BokeCCBaseIE(InfoExtractor):
 
 
 class BokeCCIE(BokeCCBaseIE):
-    _IE_DESC = 'CC视频'
+    IE_DESC = 'CC视频'
     _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
 
     _TESTS = [{

youtube_dl/extractor/camwhoresbay.py

@@ -0,0 +1,128 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+import re
+import itertools
+from ..utils import (
+    int_or_none,
+    js_to_json,
+    parse_resolution,
+    sanitize_url,
+    update_url_query,
+)
+
+
+class CamWhoresBayVideoIE(InfoExtractor):
+    IE_NAME = 'camwhoresbay:video'
+    _VALID_URL = r'https?://(?:www\.)?camwhoresbay\.com/videos/(?P<id>[0-9]+)/.+'
+    _TEST = {
+        'url': 'https://www.camwhoresbay.com/videos/484472/kirsten-xxx-2022-01-19/',
+        'md5': 'ae3c5c34866afbd062adf5d2321d66f3',
+        'info_dict': {
+            'id': '484472',
+            'ext': 'mp4',
+            'title': 'Kirsten_Xxx 2022-01-19',
+            'uploader': '789sani',
+            'url': r're:^https?://www\.camwhoresbay\.com/get_file/7/55259a27805bf1313318c14b2afb0dae1fef6e1dd4/484000/484472/484472_720p\.mp4/\?rnd=.+',
+            'thumbnail': r're:^https?://cwbstatic.cdntrex.com/contents/videos_screenshots/484000/484472/preview_720p.mp4.jpg',
+        }
+    }
+
+    @staticmethod
+    def _parse_formats(flashvars):
+        formats = []
+        rnd = flashvars.get('rnd')
+        for k, v in flashvars.items():
+            if re.match(r'^video_(alt_)?url\d?$', k):
+                f = {
+                    'url': update_url_query(v, {'rnd': rnd, })
+                }
+                f.update(parse_resolution(flashvars.get(k + '_text')))
+                formats.append(f)
+        return formats
+
+    @staticmethod
+    def _parse_thumbnails(flashvars):
+        thumbnails = []
+        for k, v in flashvars.items():
+            if re.match(r'^preview_url\d$', k):
+                t = {
+                    'url': sanitize_url(v),
+                    'height': int_or_none(flashvars.get(k.replace('_url', '_height'))),
+                }
+                thumbnails.append(t)
+        return thumbnails
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        if re.search(r'(?s)<div class=\"no-player\"', webpage):
+            print("Video is private, skipping.")
+            return
+
+        title = self._html_search_regex(r'<div class=\"headline\">\n\s*<h1>(.+?)</h1>', webpage, 'title')
+
+        flashvars = self._parse_json(
+            self._search_regex(r'(?s)var\s+flashvars\s*=\s*({.+?})\s*;', webpage, 'flashvars', default='{}'),
+            video_id, transform_source=js_to_json)
+        uploader = self._search_regex(r'''(?s)\bclass\s*=\s*["']avatar["'][^>]+?\btitle\s*=\s*["'](.+)["']''', webpage, 'uploader',
+                                      fatal=False)
+
+        formats = self._parse_formats(flashvars)
+        thumbnails = self._parse_thumbnails(flashvars)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'uploader': uploader,
+            'url': formats[0].get('url'),
+            'formats': formats,
+            'thumbnails': thumbnails,
+        }
+
+
+class CamWhoresBayModelIE(CamWhoresBayVideoIE):
+    IE_NAME = 'camwhoresbay:model'
+    _VALID_URL = r'https?://(?:www\.)?camwhoresbay\.com/models/(?P<id>[0-9a-z\-]+)/?'
+    _MORE_PAGES_INDICATOR = r'''<li\s[^>]*\bclass\s*=\s*["']next["'][^>]*><a\s[^>]*href\s*=\s*["']#videos["']'''
+    _TITLE = None
+    _TITLE_RE = r'''(?is)<div\s[^>]+?\bclass\s*=\s*["']headline["'][^>]*>\s*<h1\s[^>]*>\s*(.*?)'s\s+New\s+Videos\b'''
+    _BASE_URL_TEMPL = 'https://www.camwhoresbay.com/models/%s/?mode=async&function=get_block&block_id=list_videos_common_videos_list&sort_by=post_date&from='
+    _TEST = {
+        'url': 'https://www.camwhoresbay.com/models/kirsten-xxx/',
+        'info_dict': {
+            'id': 'kirsten-xxx',
+            'title': 'Kirsten_xxx',
+        }
+    }
+    _PAGE_SIZE = 35
+
+    def _extract_list_title(self, webpage):
+        return self._html_search_regex(
+            self._TITLE_RE, webpage, 'list title', fatal=False)
+
+    def _title_and_entries(self, model_id, base_url):
+        for page in itertools.count(1):
+            webpage = self._download_webpage('%s%d' % (base_url, page), model_id, 'Downloading page %s' % page)
+
+            if page == 1:
+                yield self._extract_list_title(webpage)
+
+            for video_id in re.findall(
+                    r'(?is)<div\s[^>]*\bclass\s*=\s*["\'.*?\bvideo\-item\b.*?["\'][^>]*>\s*<a\s[^>]*\bhref\s*=\s*["\'](.*?)["\']',
+                    webpage):
+                yield self.url_result(video_id)
+
+            if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
+                break
+
+    def _extract_videos(self, list_id, base_url):
+        title_and_entries = self._title_and_entries(list_id, base_url)
+        list_title = next(title_and_entries)
+        return self.playlist_result(title_and_entries, list_id, list_title)
+
+    def _real_extract(self, url):
+        model_id = self._match_id(url)
+        return self._extract_videos(model_id, self._BASE_URL_TEMPL % (model_id,))

youtube_dl/extractor/cloudy.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class CloudyIE(InfoExtractor):
-    _IE_DESC = 'cloudy.ec'
+    IE_DESC = 'cloudy.ec'
     _VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
     _TESTS = [{
         'url': 'https://www.cloudy.ec/v/af511e2527aac',

youtube_dl/extractor/common.py

@@ -422,6 +422,8 @@ class InfoExtractor(object):
     _GEO_COUNTRIES = None
     _GEO_IP_BLOCKS = None
     _WORKING = True
+    # supply this in public subclasses: used in supported sites list, etc
+    # IE_DESC = 'short description of IE'
 
     def __init__(self, downloader=None):
         """Constructor. Receives an optional downloader."""

youtube_dl/extractor/extractors.py

@@ -167,6 +167,10 @@ from .camdemy import (
 )
 from .cammodels import CamModelsIE
 from .camtube import CamTubeIE
+from .camwhoresbay import (
+    CamWhoresBayVideoIE,
+    CamWhoresBayModelIE,
+)
 from .camwithher import CamWithHerIE
 from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE

youtube_dl/extractor/itv.py

@@ -35,15 +35,6 @@ from ..utils import (
 
 class ITVBaseIE(InfoExtractor):
 
-    def _search_nextjs_data(self, webpage, video_id, **kw):
-        transform_source = kw.pop('transform_source', None)
-        fatal = kw.pop('fatal', True)
-        return self._parse_json(
-            self._search_regex(
-                r'''<script\b[^>]+\bid=('|")__NEXT_DATA__\1[^>]*>(?P<js>[^<]+)</script>''',
-                webpage, 'next.js data', group='js', fatal=fatal, **kw),
-            video_id, transform_source=transform_source, fatal=fatal)
-
     def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True):
         if errnote is False:
             return False
@@ -109,7 +100,9 @@ class ITVBaseIE(InfoExtractor):
 
 class ITVIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)'
-    _IE_DESC = 'ITVX'
+    IE_DESC = 'ITVX'
+    _WORKING = False
+
     _TESTS = [{
         'note': 'Hub URLs redirect to ITVX',
         'url': 'https://www.itv.com/hub/liar/2a4547a0012',
@@ -270,7 +263,7 @@ class ITVIE(ITVBaseIE):
                 'ext': determine_ext(href, 'vtt'),
             })
 
-        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default='{}')
+        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default={})
         video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {})
         title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
         info = self._og_extract(webpage, require_title=not title)
@@ -323,7 +316,7 @@ class ITVIE(ITVBaseIE):
 
 class ITVBTCCIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)'
-    _IE_DESC = 'ITV articles: News, British Touring Car Championship'
+    IE_DESC = 'ITV articles: News, British Touring Car Championship'
     _TESTS = [{
         'note': 'British Touring Car Championship',
         'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch',

youtube_dl/extractor/senateisvp.py

@@ -47,7 +47,7 @@ class SenateISVPIE(InfoExtractor):
         ['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
         ['arch', '', 'http://ussenate-f.akamaihd.net/']
     ]
-    _IE_NAME = 'senate.gov'
+    IE_NAME = 'senate.gov'
     _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
     _TESTS = [{
         'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',

youtube_dl/jsinterp.py

@@ -686,6 +686,8 @@ class JSInterpreter(object):
             raise self.Exception('Cannot get index {idx!r:.100}'.format(**locals()), expr=repr(obj), cause=e)
 
     def _dump(self, obj, namespace):
+        if obj is JS_Undefined:
+            return 'undefined'
         try:
             return json.dumps(obj)
         except TypeError: