aboutsummaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'yt_dlp/extractor')
-rw-r--r--yt_dlp/extractor/bbc.py31
-rw-r--r--yt_dlp/extractor/go.py50
-rw-r--r--yt_dlp/extractor/youtube.py11
3 files changed, 74 insertions, 18 deletions
diff --git a/yt_dlp/extractor/bbc.py b/yt_dlp/extractor/bbc.py
index 333796c80..edc2c697b 100644
--- a/yt_dlp/extractor/bbc.py
+++ b/yt_dlp/extractor/bbc.py
@@ -11,6 +11,7 @@ from ..compat import (
compat_etree_Element,
compat_HTTPError,
compat_parse_qs,
+ compat_str,
compat_urllib_parse_urlparse,
compat_urlparse,
)
@@ -25,8 +26,10 @@ from ..utils import (
js_to_json,
parse_duration,
parse_iso8601,
+ strip_or_none,
try_get,
unescapeHTML,
+ unified_timestamp,
url_or_none,
urlencode_postdata,
urljoin,
@@ -761,8 +764,17 @@ class BBCIE(BBCCoUkIE):
'only_matching': True,
}, {
# custom redirection to www.bbc.com
+ # also, video with window.__INITIAL_DATA__
'url': 'http://www.bbc.co.uk/news/science-environment-33661876',
- 'only_matching': True,
+ 'info_dict': {
+ 'id': 'p02xzws1',
+ 'ext': 'mp4',
+ 'title': "Pluto may have 'nitrogen glaciers'",
+ 'description': 'md5:6a95b593f528d7a5f2605221bc56912f',
+ 'thumbnail': r're:https?://.+/.+\.jpg',
+ 'timestamp': 1437785037,
+ 'upload_date': '20150725',
+ },
}, {
# single video article embedded with data-media-vpid
'url': 'http://www.bbc.co.uk/sport/rowing/35908187',
@@ -1164,12 +1176,29 @@ class BBCIE(BBCCoUkIE):
continue
formats, subtitles = self._download_media_selector(item_id)
self._sort_formats(formats)
+ item_desc = None
+ blocks = try_get(media, lambda x: x['summary']['blocks'], list)
+ if blocks:
+ summary = []
+ for block in blocks:
+ text = try_get(block, lambda x: x['model']['text'], compat_str)
+ if text:
+ summary.append(text)
+ if summary:
+ item_desc = '\n\n'.join(summary)
+ item_time = None
+ for meta in try_get(media, lambda x: x['metadata']['items'], list) or []:
+ if try_get(meta, lambda x: x['label']) == 'Published':
+ item_time = unified_timestamp(meta.get('timestamp'))
+ break
entries.append({
'id': item_id,
'title': item_title,
'thumbnail': item.get('holdingImageUrl'),
'formats': formats,
'subtitles': subtitles,
+ 'timestamp': item_time,
+ 'description': strip_or_none(item_desc),
})
for resp in (initial_data.get('data') or {}).values():
name = resp.get('name')
diff --git a/yt_dlp/extractor/go.py b/yt_dlp/extractor/go.py
index c31e07a0c..7dcdc864f 100644
--- a/yt_dlp/extractor/go.py
+++ b/yt_dlp/extractor/go.py
@@ -4,12 +4,14 @@ from __future__ import unicode_literals
import re
from .adobepass import AdobePassIE
+from ..compat import compat_str
from ..utils import (
int_or_none,
determine_ext,
parse_age_limit,
remove_start,
remove_end,
+ try_get,
urlencode_postdata,
ExtractorError,
)
@@ -119,6 +121,18 @@ class GoIE(AdobePassIE):
'skip_download': True,
},
}, {
+ 'url': 'https://abc.com/shows/modern-family/episode-guide/season-01/101-pilot',
+ 'info_dict': {
+ 'id': 'VDKA22600213',
+ 'ext': 'mp4',
+ 'title': 'Pilot',
+ 'description': 'md5:74306df917cfc199d76d061d66bebdb4',
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ }, {
'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
'only_matching': True,
}, {
@@ -154,18 +168,30 @@ class GoIE(AdobePassIE):
brand = site_info.get('brand')
if not video_id or not site_info:
webpage = self._download_webpage(url, display_id or video_id)
- video_id = self._search_regex(
- (
- # There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
- # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
- r'data-video-id=["\']*(VDKA\w+)',
- # https://github.com/ytdl-org/youtube-dl/pull/25216/files
- # The following is based on the pull request on the line above. Changed the ABC.com URL to a show available now.
- # https://abc.com/shows/the-rookie/episode-guide/season-02/19-the-q-word
- r'\bvideoIdCode["\']\s*:\s*["\'](vdka\w+)',
- # Deprecated fallback pattern
- r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)'
- ), webpage, 'video id', default=video_id)
+ data = self._parse_json(
+ self._search_regex(
+ r'["\']__abc_com__["\']\s*\]\s*=\s*({.+?})\s*;', webpage,
+ 'data', default='{}'),
+ display_id or video_id, fatal=False)
+ # https://abc.com/shows/modern-family/episode-guide/season-01/101-pilot
+ layout = try_get(data, lambda x: x['page']['content']['video']['layout'], dict)
+ video_id = None
+ if layout:
+ video_id = try_get(
+ layout,
+ (lambda x: x['videoid'], lambda x: x['video']['id']),
+ compat_str)
+ if not video_id:
+ video_id = self._search_regex(
+ (
+ # There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
+ # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
+ r'data-video-id=["\']*(VDKA\w+)',
+ # page.analytics.videoIdCode
+ r'\bvideoIdCode["\']\s*:\s*["\']((?:vdka|VDKA)\w+)',
+ # https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet
+ r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)'
+ ), webpage, 'video id', default=video_id)
if not site_info:
brand = self._search_regex(
(r'data-brand=\s*["\']\s*(\d+)',
diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py
index eaa2db1da..edc985d19 100644
--- a/yt_dlp/extractor/youtube.py
+++ b/yt_dlp/extractor/youtube.py
@@ -77,11 +77,6 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
_PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
- def _ids_to_results(self, ids):
- return [
- self.url_result(vid_id, 'Youtube', video_id=vid_id)
- for vid_id in ids]
-
def _login(self):
"""
Attempt to log in to YouTube.
@@ -1313,6 +1308,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
@classmethod
def suitable(cls, url):
+ # Hack for lazy extractors until more generic solution is implemented
+ # (see #28780)
+ from .youtube import parse_qs
qs = parse_qs(url)
if qs.get('list', [None])[0]:
return False
@@ -3595,6 +3593,9 @@ class YoutubePlaylistIE(InfoExtractor):
def suitable(cls, url):
if YoutubeTabIE.suitable(url):
return False
+ # Hack for lazy extractors until more generic solution is implemented
+ # (see #28780)
+ from .youtube import parse_qs
qs = parse_qs(url)
if qs.get('v', [None])[0]:
return False
generated by cgit v1.2.3 (git 2.25.1) at 2025-06-13 22:12:27 +0000