[ie/filmarchiv] Add extractor (#13490)

Closes #14821
Authored by: 4elta

yt_dlp/extractor/_extractors.py

@@ -638,6 +638,7 @@ from .fc2 import (
 )
 from .fczenit import FczenitIE
 from .fifa import FifaIE
+from .filmarchiv import FilmArchivIE
 from .filmon import (
     FilmOnChannelIE,
     FilmOnIE,

yt_dlp/extractor/dropbox.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class DropboxIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dropbox\.com/(?:(?:e/)?scl/fi|sh?)/(?P<id>\w+)'
+    _VALID_URL = r'https?://(?:www\.)?dropbox\.com/(?:(?:e/)?scl/f[io]|sh?)/(?P<id>\w+)'
     _TESTS = [
         {
             'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4?dl=0',
@@ -35,6 +35,9 @@ class DropboxIE(InfoExtractor):
         }, {
             'url': 'https://www.dropbox.com/e/scl/fi/r2kd2skcy5ylbbta5y1pz/DJI_0003.MP4?dl=0&rlkey=wcdgqangn7t3lnmmv6li9mu9h',
             'only_matching': True,
+        }, {
+            'url': 'https://www.dropbox.com/scl/fo/zjfqse5txqfd7twa8iewj/AOfZzSYWUSKle2HD7XF7kzQ/A-BEAT%20C.mp4?rlkey=6tg3jkp4tv6a5vt58a6dag0mm&dl=0',
+            'only_matching': True,
         },
     ]
 

yt_dlp/extractor/filmarchiv.py

@@ -0,0 +1,52 @@
+from .common import InfoExtractor
+from ..utils import clean_html
+from ..utils.traversal import (
+    find_element,
+    find_elements,
+    traverse_obj,
+)
+
+
+class FilmArchivIE(InfoExtractor):
+    IE_DESC = 'FILMARCHIV ON'
+    _VALID_URL = r'https?://(?:www\.)?filmarchiv\.at/de/filmarchiv-on/video/(?P<id>f_[0-9a-zA-Z]{5,})'
+    _TESTS = [{
+        'url': 'https://www.filmarchiv.at/de/filmarchiv-on/video/f_0305p7xKrXUPBwoNE9x6mh',
+        'md5': '54a6596f6a84624531866008a77fa27a',
+        'info_dict': {
+            'id': 'f_0305p7xKrXUPBwoNE9x6mh',
+            'ext': 'mp4',
+            'title': 'Der Wurstelprater zur Kaiserzeit',
+            'description': 'md5:9843f92df5cc9a4975cee7aabcf6e3b2',
+            'thumbnail': r're:https://cdn\.filmarchiv\.at/f_0305/p7xKrXUPBwoNE9x6mh_v1/poster\.jpg',
+        },
+    }, {
+        'url': 'https://www.filmarchiv.at/de/filmarchiv-on/video/f_0306vI3wO0tJIsfrqYFQXF',
+        'md5': '595385d7f54cb6529140ee8de7d1c3c7',
+        'info_dict': {
+            'id': 'f_0306vI3wO0tJIsfrqYFQXF',
+            'ext': 'mp4',
+            'title': 'Vor 70 Jahren: Wettgehen der Briefträger in Wien',
+            'description': 'md5:b2a2e4230923cd1969d471c552e62811',
+            'thumbnail': r're:https://cdn\.filmarchiv\.at/f_0306/vI3wO0tJIsfrqYFQXF_v1/poster\.jpg',
+        },
+    }]
+
+    def _real_extract(self, url):
+        media_id = self._match_id(url)
+        webpage = self._download_webpage(url, media_id)
+        path = '/'.join((media_id[:6], media_id[6:]))
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            f'https://cdn.filmarchiv.at/{path}_v1_sv1/playlist.m3u8', media_id)
+
+        return {
+            'id': media_id,
+            'title': traverse_obj(webpage, ({find_element(tag='title-div')}, {clean_html})),
+            'description': traverse_obj(webpage, (
+                {find_elements(tag='div', attr='class', value=r'.*\bborder-base-content\b', regex=True)}, ...,
+                {find_elements(tag='div', attr='class', value=r'.*\bprose\b', html=False, regex=True)}, ...,
+                {clean_html}, any)),
+            'thumbnail': f'https://cdn.filmarchiv.at/{path}_v1/poster.jpg',
+            'formats': formats,
+            'subtitles': subtitles,
+        }

yt_dlp/extractor/gofile.py

@@ -46,6 +46,7 @@ class GofileIE(InfoExtractor):
             'videopassword': 'password',
         },
     }]
+    _STATIC_TOKEN = '4fd6sg89d7s6'  # From https://gofile.io/dist/js/config.js
     _TOKEN = None
 
     def _real_initialize(self):
@@ -60,13 +61,16 @@ class GofileIE(InfoExtractor):
         self._set_cookie('.gofile.io', 'accountToken', self._TOKEN)
 
     def _entries(self, file_id):
-        query_params = {'wt': '4fd6sg89d7s6'}  # From https://gofile.io/dist/js/alljs.js
-        password = self.get_param('videopassword')
-        if password:
+        query_params = {}
+        if password := self.get_param('videopassword'):
             query_params['password'] = hashlib.sha256(password.encode()).hexdigest()
+
         files = self._download_json(
             f'https://api.gofile.io/contents/{file_id}', file_id, 'Getting filelist',
-            query=query_params, headers={'Authorization': f'Bearer {self._TOKEN}'})
+            query=query_params, headers={
+                'Authorization': f'Bearer {self._TOKEN}',
+                'X-Website-Token': self._STATIC_TOKEN,
+            })
 
         status = files['status']
         if status == 'error-passwordRequired':

yt_dlp/extractor/tubitv.py

@@ -15,7 +15,7 @@ from ..utils import (
 
 class TubiTvIE(InfoExtractor):
     IE_NAME = 'tubitv'
-    _VALID_URL = r'https?://(?:www\.)?tubitv\.com/(?P<type>video|movies|tv-shows)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?tubitv\.com/(?:[a-z]{2}-[a-z]{2}/)?(?P<type>video|movies|tv-shows)/(?P<id>\d+)'
     _LOGIN_URL = 'http://tubitv.com/login'
     _NETRC_MACHINE = 'tubitv'
     _TESTS = [{
@@ -73,6 +73,9 @@ class TubiTvIE(InfoExtractor):
             'release_year': 1979,
         },
         'skip': 'Content Unavailable',
+    }, {
+        'url': 'https://tubitv.com/es-mx/tv-shows/477363/s01-e03-jacob-dos-dos-y-la-tarjets-de-hockey-robada',
+        'only_matching': True,
     }]
 
     # DRM formats are included only to raise appropriate error

yt_dlp/options.py

@@ -1212,7 +1212,7 @@ def create_parser():
         help='Maximum number of seconds to sleep. Can only be used along with --min-sleep-interval')
     workarounds.add_option(
         '--sleep-subtitles', metavar='SECONDS',
-        dest='sleep_interval_subtitles', default=0, type=int,
+        dest='sleep_interval_subtitles', default=0, type=float,
         help='Number of seconds to sleep before each subtitle download')
 
     verbosity = optparse.OptionGroup(parser, 'Verbosity and Simulation Options')