Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[svt] Fix download of wrong episode and update test #7789

Merged
merged 10 commits into from
Sep 2, 2023
Merged

[svt] Fix download of wrong episode and update test #7789

Changes from 7 commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
6ee025b
[svt] Fix download of wrong episode and update test
wader Aug 8, 2023
2ebec0f
Update yt_dlp/extractor/svt.py
wader Aug 27, 2023
5944aa2
Update yt_dlp/extractor/svt.py
wader Aug 27, 2023
11d5947
Update yt_dlp/extractor/svt.py
wader Aug 27, 2023
65f16c0
svt: Readd videoSvtId RE to fix some pages
wader Aug 27, 2023
9810d49
Revert "svt: Readd videoSvtId RE to fix some pages"
bashonly Aug 31, 2023
bf7ae78
Parse and traverse nextjs data for svt id
bashonly Aug 31, 2023
b91796a
Correct the traversal
bashonly Sep 1, 2023
a29b23a
Remove last JSON regex pattern
bashonly Sep 1, 2023
acd9ba6
Add/update tests
bashonly Sep 1, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
39 changes: 32 additions & 7 deletions yt_dlp/extractor/svt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
import json
import re

from .common import InfoExtractor
Expand All @@ -6,10 +7,11 @@
determine_ext,
dict_get,
int_or_none,
unified_timestamp,
str_or_none,
strip_or_none,
traverse_obj,
try_get,
unified_timestamp,
)


Expand Down Expand Up @@ -145,6 +147,7 @@ class SVTPlayIE(SVTPlayBaseIE):
)
'''
_TESTS = [{
'skip': 'Episode is no longer available',
'url': 'https://www.svtplay.se/video/30479064',
'md5': '2382036fd6f8c994856c323fe51c426e',
'info_dict': {
Expand All @@ -168,6 +171,27 @@ class SVTPlayIE(SVTPlayBaseIE):
# AssertionError: Expected test_SVTPlay_jNwpV9P.mp4 to be at least 9.77KiB, but it's only 864.00B
'skip_download': True,
},
}, {
'url': 'https://www.svtplay.se/video/emBxBQj',
'md5': '2382036fd6f8c994856c323fe51c426e',
'info_dict': {
'id': 'eyBd9aj',
'ext': 'mp4',
'title': '1. Farlig kryssning',
'timestamp': 1491019200,
'upload_date': '20170401',
'duration': 2566,
'thumbnail': r're:^https?://(?:.*[\.-]jpg|www.svtstatic.se/image/.*)$',
'age_limit': 0,
'episode': '1. Farlig kryssning',
'series': 'Rederiet',
'subtitles': {
'sv': 'count:3'
},
},
'params': {
'skip_download': 'm3u8',
},
}, {
'url': 'https://www.svtplay.se/video/30479064/husdrommar/husdrommar-sasong-8-designdrommar-i-stenungsund?modalId=8zVbDPA',
'only_matching': True,
Expand Down Expand Up @@ -247,15 +271,16 @@ def _real_extract(self, url):
data, lambda x: x['statistics']['dataLake']['content']['id'],
compat_str)

if not svt_id:
nextjs_data = self._search_nextjs_data(webpage, video_id, fatal=False)
bashonly marked this conversation as resolved.
Show resolved Hide resolved
svt_id = traverse_obj(nextjs_data, (
'props', 'urqlState', ..., 'data', {json.loads}, 'detailsPageByPath', 'id', {str}), get_all=False)

if not svt_id:
svt_id = self._search_regex(
(r'<video[^>]+data-video-id=["\']([\da-zA-Z-]+)',
r'<[^>]+\bdata-rt=["\']top-area-play-button["\'][^>]+\bhref=["\'][^"\']*video/%s/[^"\']*\b(?:modalId|id)=([\da-zA-Z-]+)' % re.escape(video_id),
r'["\']videoSvtId["\']\s*:\s*["\']([\da-zA-Z-]+)',
r'["\']videoSvtId\\?["\']\s*:\s*\\?["\']([\da-zA-Z-]+)',
r'"content"\s*:\s*{.*?"id"\s*:\s*"([\da-zA-Z-]+)"',
r'["\']svtId["\']\s*:\s*["\']([\da-zA-Z-]+)',
r'["\']svtId\\?["\']\s*:\s*\\?["\']([\da-zA-Z-]+)'),
r'<[^>]+\bdata-rt=["\']top-area-play-button["\'][^>]+\bhref=["\'][^"\']*video/[\w-]+/[^"\']*\b(?:modalId|id)=([\w-]+)',
r'"content"\s*:\s*{.*?"id"\s*:\s*"([\da-zA-Z-]+)"'),
webpage, 'video id')

info_dict = self._extract_by_video_id(svt_id, webpage)
Expand Down