[misc] Add `hatch`, `ruff`, `pre-commit` and improve dev docs (#7409)

[yt-dlp.git] / yt_dlp / extractor / vimeo.py

diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py
index e5e8144bb10b4a4f465423df217ed81468d51b09..ac96ade18695a060995d5496e7332d8e3ef31d0d 100644 (file)
--- a/yt_dlp/extractor/vimeo.py
+++ b/yt_dlp/extractor/vimeo.py
@@ -1,32 +1,33 @@
 import base64
 import functools
-import re
 import itertools
+import re
 
 from .common import InfoExtractor
 from ..compat import compat_str, compat_urlparse
 from ..networking import HEADRequest, Request
 from ..networking.exceptions import HTTPError
 from ..utils import (
+    ExtractorError,
+    OnDemandPagedList,
     clean_html,
     determine_ext,
-    ExtractorError,
     get_element_by_class,
-    js_to_json,
     int_or_none,
+    js_to_json,
     merge_dicts,
-    OnDemandPagedList,
     parse_filesize,
     parse_iso8601,
     parse_qs,
     smuggle_url,
     str_or_none,
+    traverse_obj,
     try_get,
     unified_timestamp,
     unsmuggle_url,
     urlencode_postdata,
-    urljoin,
     urlhandle_detect_ext,
+    urljoin,
 )
 
 
@@ -48,17 +49,15 @@ def _unsmuggle_headers(self, url):
         return url, data, headers
 
     def _perform_login(self, username, password):
-        webpage = self._download_webpage(
-            self._LOGIN_URL, None, 'Downloading login page')
-        token, vuid = self._extract_xsrft_and_vuid(webpage)
+        viewer = self._download_json('https://vimeo.com/_next/viewer', None, 'Downloading login token')
         data = {
             'action': 'login',
             'email': username,
             'password': password,
             'service': 'vimeo',
-            'token': token,
+            'token': viewer['xsrft'],
         }
-        self._set_vimeo_cookie('vuid', vuid)
+        self._set_vimeo_cookie('vuid', viewer['vuid'])
         try:
             self._download_webpage(
                 self._LOGIN_URL, None, 'Logging in',
@@ -123,7 +122,13 @@ def _parse_config(self, config, video_id):
         video_data = config['video']
         video_title = video_data.get('title')
         live_event = video_data.get('live_event') or {}
-        is_live = live_event.get('status') == 'started'
+        live_status = {
+            'pending': 'is_upcoming',
+            'active': 'is_upcoming',
+            'started': 'is_live',
+            'ended': 'post_live',
+        }.get(live_event.get('status'))
+        is_live = live_status == 'is_live'
         request = config.get('request') or {}
 
         formats = []
@@ -232,7 +237,8 @@ def _parse_config(self, config, video_id):
             'chapters': chapters or None,
             'formats': formats,
             'subtitles': subtitles,
-            'is_live': is_live,
+            'live_status': live_status,
+            'release_timestamp': traverse_obj(live_event, ('ingest', 'scheduled_start_time', {parse_iso8601})),
             # Note: Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
             # at the same time without actual units specified.
             '_format_sort_fields': ('quality', 'res', 'fps', 'hdr:12', 'source'),
@@ -269,7 +275,7 @@ def _extract_original_format(self, url, video_id, unlisted_hash=None):
             'https://vimeo.com/_rv/viewer', video_id, note='Downloading jwt token', fatal=False) or {}
         if not jwt_response.get('jwt'):
             return
-        headers = {'Authorization': 'jwt %s' % jwt_response['jwt']}
+        headers = {'Authorization': 'jwt %s' % jwt_response['jwt'], 'Accept': 'application/json'}
         original_response = self._download_json(
             f'https://api.vimeo.com/videos/{video_id}', video_id,
             headers=headers, fatal=False, expected_status=(403, 404)) or {}
@@ -369,7 +375,6 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
                 'uploader_id': 'businessofsoftware',
                 'duration': 3610,
-                'description': None,
                 'thumbnail': 'https://i.vimeocdn.com/video/376682406-f34043e7b766af6bef2af81366eacd6724f3fc3173179a11a97a1e26587c9529-d_1280',
             },
             'params': {
@@ -751,6 +756,7 @@ def _extract_from_api(self, video_id, unlisted_hash=None):
         video = self._download_json(
             api_url, video_id, headers={
                 'Authorization': 'jwt ' + token,
+                'Accept': 'application/json',
             }, query={
                 'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
             })
@@ -785,7 +791,7 @@ def _try_album_password(self, url):
         jwt = viewer['jwt']
         album = self._download_json(
             'https://api.vimeo.com/albums/' + album_id,
-            album_id, headers={'Authorization': 'jwt ' + jwt},
+            album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
             query={'fields': 'description,name,privacy'})
         if try_get(album, lambda x: x['privacy']['view']) == 'password':
             password = self.get_param('videopassword')
@@ -1147,10 +1153,12 @@ def _fetch_page(self, album_id, authorization, hashed_pass, page):
                 'https://api.vimeo.com/albums/%s/videos' % album_id,
                 album_id, 'Downloading page %d' % api_page, query=query, headers={
                     'Authorization': 'jwt ' + authorization,
+                    'Accept': 'application/json',
                 })['data']
         except ExtractorError as e:
             if isinstance(e.cause, HTTPError) and e.cause.status == 400:
                 return
+            raise
         for video in videos:
             link = video.get('link')
             if not link:
@@ -1171,7 +1179,7 @@ def _real_extract(self, url):
         jwt = viewer['jwt']
         album = self._download_json(
             'https://api.vimeo.com/albums/' + album_id,
-            album_id, headers={'Authorization': 'jwt ' + jwt},
+            album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
             query={'fields': 'description,name,privacy'})
         hashed_pass = None
         if try_get(album, lambda x: x['privacy']['view']) == 'password':