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

[ie/ard] Revert to using old id #8916

Merged
merged 4 commits into from Jan 5, 2024
Merged

[ie/ard] Revert to using old id #8916

Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
baebef4
Revert to using old id
Grub4K Jan 2, 2024
40420cc
Use old id for log output
Grub4K Jan 2, 2024
18a327f
Fix old archive id
Grub4K Jan 5, 2024
51910a4
Review
Grub4K Jan 5, 2024
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
40 changes: 25 additions & 15 deletions yt_dlp/extractor/ard.py
View file
Open in desktop
Expand Up @@ -4,6 +4,7 @@
from .common import InfoExtractor
from ..utils import (
OnDemandPagedList,
bug_reports_message,
determine_ext,
int_or_none,
join_nonempty,
Expand Down Expand Up @@ -233,7 +234,7 @@ class ARDBetaMediathekIE(InfoExtractor):
(?:(?:beta|www)\.)?ardmediathek\.de/
(?:[^/]+/)?
(?:player|live|video)/
(?:(?P<display_id>[^?#]+)/)?
(?:[^?#]+/)?
(?P<id>[a-zA-Z0-9]+)
/?(?:[?#]|$)'''
_GEO_COUNTRIES = ['DE']
Expand All @@ -242,8 +243,8 @@ class ARDBetaMediathekIE(InfoExtractor):
'url': 'https://www.ardmediathek.de/video/filme-im-mdr/liebe-auf-vier-pfoten/mdr-fernsehen/Y3JpZDovL21kci5kZS9zZW5kdW5nLzI4MjA0MC80MjIwOTEtNDAyNTM0',
'md5': 'b6e8ab03f2bcc6e1f9e6cef25fcc03c4',
'info_dict': {
'display_id': 'filme-im-mdr/liebe-auf-vier-pfoten/mdr-fernsehen',
'id': 'Y3JpZDovL21kci5kZS9zZW5kdW5nLzI4MjA0MC80MjIwOTEtNDAyNTM0',
'display_id': 'Y3JpZDovL21kci5kZS9zZW5kdW5nLzI4MjA0MC80MjIwOTEtNDAyNTM0',
'id': '12939099',
'title': 'Liebe auf vier Pfoten',
'description': r're:^Claudia Schmitt, Anwältin in Salzburg',
'duration': 5222,
Expand All @@ -255,7 +256,7 @@ class ARDBetaMediathekIE(InfoExtractor):
'series': 'Filme im MDR',
'age_limit': 0,
'channel': 'MDR',
'_old_archive_ids': ['ardbetamediathek 12939099'],
'_old_archive_ids': ['ardbetamediathek Y3JpZDovL21kci5kZS9zZW5kdW5nLzI4MjA0MC80MjIwOTEtNDAyNTM0'],
},
}, {
'url': 'https://www.ardmediathek.de/mdr/video/die-robuste-roswita/Y3JpZDovL21kci5kZS9iZWl0cmFnL2Ntcy84MWMxN2MzZC0wMjkxLTRmMzUtODk4ZS0wYzhlOWQxODE2NGI/',
Expand All @@ -276,37 +277,37 @@ class ARDBetaMediathekIE(InfoExtractor):
'url': 'https://www.ardmediathek.de/video/tagesschau-oder-tagesschau-20-00-uhr/das-erste/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhZ2Vzc2NoYXUvZmM4ZDUxMjgtOTE0ZC00Y2MzLTgzNzAtNDZkNGNiZWJkOTll',
'md5': '1e73ded21cb79bac065117e80c81dc88',
'info_dict': {
'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhZ2Vzc2NoYXUvZmM4ZDUxMjgtOTE0ZC00Y2MzLTgzNzAtNDZkNGNiZWJkOTll',
'id': '10049223',
'ext': 'mp4',
'title': 'tagesschau, 20:00 Uhr',
'timestamp': 1636398000,
'description': 'md5:39578c7b96c9fe50afdf5674ad985e6b',
'upload_date': '20211108',
'display_id': 'tagesschau-oder-tagesschau-20-00-uhr/das-erste',
'display_id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhZ2Vzc2NoYXUvZmM4ZDUxMjgtOTE0ZC00Y2MzLTgzNzAtNDZkNGNiZWJkOTll',
'duration': 915,
'episode': 'tagesschau, 20:00 Uhr',
'series': 'tagesschau',
'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:fbb21142783b0a49?w=960&ch=ee69108ae344f678',
'channel': 'ARD-Aktuell',
'_old_archive_ids': ['ardbetamediathek 10049223'],
'_old_archive_ids': ['ardbetamediathek Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhZ2Vzc2NoYXUvZmM4ZDUxMjgtOTE0ZC00Y2MzLTgzNzAtNDZkNGNiZWJkOTll'],
},
}, {
'url': 'https://www.ardmediathek.de/video/7-tage/7-tage-unter-harten-jungs/hr-fernsehen/N2I2YmM5MzgtNWFlOS00ZGFlLTg2NzMtYzNjM2JlNjk4MDg3',
'md5': 'c428b9effff18ff624d4f903bda26315',
'info_dict': {
'id': 'N2I2YmM5MzgtNWFlOS00ZGFlLTg2NzMtYzNjM2JlNjk4MDg3',
'id': '94834686',
'ext': 'mp4',
'duration': 2700,
'episode': '7 Tage ... unter harten Jungs',
'description': 'md5:0f215470dcd2b02f59f4bd10c963f072',
'upload_date': '20231005',
'timestamp': 1696491171,
'display_id': '7-tage/7-tage-unter-harten-jungs/hr-fernsehen',
'display_id': 'N2I2YmM5MzgtNWFlOS00ZGFlLTg2NzMtYzNjM2JlNjk4MDg3',
'series': '7 Tage ...',
'channel': 'HR',
'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:f6e6d5ffac41925c?w=960&ch=fa32ba69bc87989a',
'title': '7 Tage ... unter harten Jungs',
'_old_archive_ids': ['ardbetamediathek 94834686'],
'_old_archive_ids': ['ardbetamediathek N2I2YmM5MzgtNWFlOS00ZGFlLTg2NzMtYzNjM2JlNjk4MDg3'],
},
}, {
'url': 'https://beta.ardmediathek.de/ard/video/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
Expand Down Expand Up @@ -357,14 +358,25 @@ def _extract_episode_info(self, title):
}), get_all=False)

def _real_extract(self, url):
video_id, display_id = self._match_valid_url(url).group('id', 'display_id')
display_id = self._match_id(url)

page_data = self._download_json(
f'https://api.ardmediathek.de/page-gateway/pages/ard/item/{video_id}', video_id, query={
f'https://api.ardmediathek.de/page-gateway/pages/ard/item/{display_id}', display_id, query={
'embedded': 'false',
'mcV6': 'true',
})

# For user convenience we use the old contentId instead of the longer crid
# Ref: https://github.com/yt-dlp/yt-dlp/issues/8731#issuecomment-1874398283
old_id = traverse_obj(page_data, ('tracking', 'atiCustomVars', 'contentId', {str_or_none}))
if old_id:
video_id = old_id
archive_ids = [make_archive_id(ARDBetaMediathekIE, display_id)]
Grub4K marked this conversation as resolved.
Show resolved Hide resolved
else:
self.report_warning(f'Could not extract contentId{bug_reports_message()}')
video_id = display_id
archive_ids = None

player_data = traverse_obj(
page_data, ('widgets', lambda _, v: v['type'] in ('player_ondemand', 'player_live'), {dict}), get_all=False)
is_live = player_data.get('type') == 'player_live'
Expand Down Expand Up @@ -419,8 +431,6 @@ def _real_extract(self, url):
})

age_limit = traverse_obj(page_data, ('fskRating', {lambda x: remove_start(x, 'FSK')}, {int_or_none}))
old_id = traverse_obj(page_data, ('tracking', 'atiCustomVars', 'contentId'))

return {
'id': video_id,
'display_id': display_id,
Expand All @@ -438,7 +448,7 @@ def _real_extract(self, url):
'channel': 'clipSourceName',
})),
**self._extract_episode_info(page_data.get('title')),
'_old_archive_ids': [make_archive_id(ARDBetaMediathekIE, old_id)],
'_old_archive_ids': archive_ids,
}


Expand Down