Compare commits

...

7 Commits

Author SHA1 Message Date
bibiak
f5dd875a02 moved txt_or_none outside if statement 2023-10-02 14:13:50 +00:00
bibiak
efee229d66
Merge branch 'ytdl-org:master' into master 2023-10-02 15:51:03 +02:00
dirkf
00ef748cc0 [downloader] Fix baa6c5e: show ETA of http download as ETA instead of total d/l time 2023-09-24 22:07:47 +01:00
dirkf
66ab0814c4 [utils] Revert bbd3e7e, updating docstring, test instead 2023-09-03 23:15:19 +01:00
dirkf
bbd3e7e999 [utils] Properly handle list values in update_url()
An actual list value in a query update could have been treated
as a list of values because of the key:list parse_qs format.
2023-09-03 01:18:22 +01:00
dirkf
21caaf2380 [test] Remove redundancy from lambda expected value regex 2023-09-03 01:13:40 +01:00
dirkf
31f50c8194 [S4C] Add thumbnail extraction, extract series as playlist
Based on https://github.com/yt-dlp/yt-dlp/pull/7776: thx ifan-t, bashonly
2023-08-31 23:16:50 +01:00
8 changed files with 88 additions and 38 deletions

View File

@ -142,7 +142,7 @@ def expect_value(self, got, expected, field):
self.assertTrue(
contains_str in got,
'field %s (value: %r) should contain %r' % (field, got, contains_str))
elif isinstance(expected, compat_str) and re.match(r'^lambda \w+:', expected):
elif isinstance(expected, compat_str) and re.match(r'lambda \w+:', expected):
fn = eval(expected)
suite = expected.split(':', 1)[1].strip()
self.assertTrue(

View File

@ -62,13 +62,14 @@ from youtube_dl.utils import (
OnDemandPagedList,
orderedSet,
parse_age_limit,
parse_bitrate,
parse_duration,
parse_filesize,
parse_codecs,
parse_count,
parse_iso8601,
parse_resolution,
parse_bitrate,
parse_qs,
pkcs1pad,
prepend_extension,
read_batch_urls,
@ -125,7 +126,6 @@ from youtube_dl.compat import (
compat_setenv,
compat_str,
compat_urlparse,
compat_parse_qs,
)
@ -683,38 +683,36 @@ class TestUtil(unittest.TestCase):
self.assertTrue(isinstance(data, bytes))
def test_update_url_query(self):
def query_dict(url):
return compat_parse_qs(compat_urlparse.urlparse(url).query)
self.assertEqual(query_dict(update_url_query(
self.assertEqual(parse_qs(update_url_query(
'http://example.com/path', {'quality': ['HD'], 'format': ['mp4']})),
query_dict('http://example.com/path?quality=HD&format=mp4'))
self.assertEqual(query_dict(update_url_query(
parse_qs('http://example.com/path?quality=HD&format=mp4'))
self.assertEqual(parse_qs(update_url_query(
'http://example.com/path', {'system': ['LINUX', 'WINDOWS']})),
query_dict('http://example.com/path?system=LINUX&system=WINDOWS'))
self.assertEqual(query_dict(update_url_query(
parse_qs('http://example.com/path?system=LINUX&system=WINDOWS'))
self.assertEqual(parse_qs(update_url_query(
'http://example.com/path', {'fields': 'id,formats,subtitles'})),
query_dict('http://example.com/path?fields=id,formats,subtitles'))
self.assertEqual(query_dict(update_url_query(
parse_qs('http://example.com/path?fields=id,formats,subtitles'))
self.assertEqual(parse_qs(update_url_query(
'http://example.com/path', {'fields': ('id,formats,subtitles', 'thumbnails')})),
query_dict('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails'))
self.assertEqual(query_dict(update_url_query(
parse_qs('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails'))
self.assertEqual(parse_qs(update_url_query(
'http://example.com/path?manifest=f4m', {'manifest': []})),
query_dict('http://example.com/path'))
self.assertEqual(query_dict(update_url_query(
parse_qs('http://example.com/path'))
self.assertEqual(parse_qs(update_url_query(
'http://example.com/path?system=LINUX&system=WINDOWS', {'system': 'LINUX'})),
query_dict('http://example.com/path?system=LINUX'))
self.assertEqual(query_dict(update_url_query(
parse_qs('http://example.com/path?system=LINUX'))
self.assertEqual(parse_qs(update_url_query(
'http://example.com/path', {'fields': b'id,formats,subtitles'})),
query_dict('http://example.com/path?fields=id,formats,subtitles'))
self.assertEqual(query_dict(update_url_query(
parse_qs('http://example.com/path?fields=id,formats,subtitles'))
self.assertEqual(parse_qs(update_url_query(
'http://example.com/path', {'width': 1080, 'height': 720})),
query_dict('http://example.com/path?width=1080&height=720'))
self.assertEqual(query_dict(update_url_query(
parse_qs('http://example.com/path?width=1080&height=720'))
self.assertEqual(parse_qs(update_url_query(
'http://example.com/path', {'bitrate': 5020.43})),
query_dict('http://example.com/path?bitrate=5020.43'))
self.assertEqual(query_dict(update_url_query(
parse_qs('http://example.com/path?bitrate=5020.43'))
self.assertEqual(parse_qs(update_url_query(
'http://example.com/path', {'test': '第二行тест'})),
query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
parse_qs('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
def test_multipart_encode(self):
self.assertEqual(

View File

@ -96,7 +96,7 @@ class FileDownloader(object):
return None
return int(float(remaining) / rate)
start, now = (start_or_rate, now_or_remaining)
total, current = args
total, current = args[:2]
if total is None:
return None
if now is None:

View File

@ -294,7 +294,7 @@ class HttpFD(FileDownloader):
# Progress message
speed = self.calc_speed(start, now, byte_counter - ctx.resume_len)
eta = self.calc_eta(speed, ctx.data_len and (ctx.data_len - ctx.resume_len))
eta = self.calc_eta(speed, ctx.data_len and (ctx.data_len - byte_counter))
self._hook_progress({
'status': 'downloading',

View File

@ -1087,7 +1087,10 @@ from .rutube import (
from .rutv import RUTVIE
from .ruutu import RuutuIE
from .ruv import RuvIE
from .s4c import S4CIE
from .s4c import (
S4CIE,
S4CSeriesIE,
)
from .safari import (
SafariIE,
SafariApiIE,

View File

@ -2,6 +2,8 @@
from __future__ import unicode_literals
from functools import partial as partial_f
from .common import InfoExtractor
from ..utils import (
float_or_none,
@ -9,6 +11,7 @@ from ..utils import (
T,
traverse_obj,
txt_or_none,
url_or_none,
)
@ -21,7 +24,8 @@ class S4CIE(InfoExtractor):
'ext': 'mp4',
'title': 'Y Swn',
'description': 'md5:f7681a30e4955b250b3224aa9fe70cf0',
'duration': 5340
'duration': 5340,
'thumbnail': 'https://www.s4c.cymru/amg/1920x1080/Y_Swn_2023S4C_099_ii.jpg',
},
}, {
'url': 'https://www.s4c.cymru/clic/programme/856636948',
@ -31,6 +35,7 @@ class S4CIE(InfoExtractor):
'title': 'Am Dro',
'duration': 2880,
'description': 'md5:100d8686fc9a632a0cb2db52a3433ffe',
'thumbnail': 'https://www.s4c.cymru/amg/1920x1080/Am_Dro_2022-23S4C_P6_4005.jpg',
},
}]
@ -43,7 +48,7 @@ class S4CIE(InfoExtractor):
'programme_id': video_id,
}, fatal=False)
filename = self._download_json(
player_config = self._download_json(
'https://player-api.s4c-cdn.co.uk/player-configuration/prod', video_id, query={
'programme_id': video_id,
'signed': '0',
@ -51,7 +56,8 @@ class S4CIE(InfoExtractor):
'mode': 'od',
'appId': 'clic',
'streamName': '',
}, note='Downloading player config JSON')['filename']
}, note='Downloading player config JSON')
m3u8_url = self._download_json(
'https://player-api.s4c-cdn.co.uk/streaming-urls/prod', video_id, query={
'mode': 'od',
@ -59,18 +65,60 @@ class S4CIE(InfoExtractor):
'region': 'WW',
'extra': 'false',
'thirdParty': 'false',
'filename': filename,
'filename': player_config['filename'],
}, note='Downloading streaming urls JSON')['hls']
# ... self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4', m3u8_id='hls')
formats, subtitles = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls', entry_protocol='m3u8_native'), {}
formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls', entry_protocol='m3u8_native')
self._sort_formats(formats)
subtitles = {}
for sub in traverse_obj(player_config, ('subtitles', lambda _, v: url_or_none(v['0']))):
subtitles.setdefault(sub.get('3', 'en'), []).append({
'url': sub['0'],
'name': sub.get('1'),
})
return merge_dicts({
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'thumbnail': url_or_none(player_config.get('poster')),
}, traverse_obj(details, ('full_prog_details', 0, {
'title': (('programme_title', 'series_title'), T(txt_or_none)),
'description': ('full_billing', T(txt_or_none)),
'duration': ('duration', T(lambda x: float_or_none(x, invscale=60))),
'duration': ('duration', T(partial_f(float_or_none, invscale=60))),
}), get_all=False),
rev=True)
class S4CSeriesIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?s4c\.cymru/clic/series/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.s4c.cymru/clic/series/864982911',
'playlist_mincount': 6,
'info_dict': {
'id': '864982911',
'title': 'Iaith ar Daith',
},
}, {
'url': 'https://www.s4c.cymru/clic/series/866852587',
'playlist_mincount': 8,
'info_dict': {
'id': '866852587',
'title': 'FFIT Cymru',
},
}]
def _real_extract(self, url):
series_id = self._match_id(url)
series_details = self._download_json(
'https://www.s4c.cymru/df/series_details', series_id, query={
'lang': 'e',
'series_id': series_id,
'show_prog_in_series': 'Y'
}, note='Downloading series details JSON')
return self.playlist_result(
(self.url_result('https://www.s4c.cymru/clic/programme/' + episode_id, S4CIE, episode_id)
for episode_id in traverse_obj(series_details, ('other_progs_in_series', Ellipsis, 'id'))),
playlist_id=series_id, playlist_title=traverse_obj(
series_details, ('full_prog_details', 0, 'series_title', T(txt_or_none))))

View File

@ -21,6 +21,9 @@ from ..utils import (
)
def txt_or_none(v, default=None):
return default if v is None else (compat_str(v).strip() or default)
if not hasattr(InfoExtractor, '_match_valid_url'):
import sys
@ -35,9 +38,6 @@ if not hasattr(InfoExtractor, '_match_valid_url'):
RegexNotFoundError,
)
def txt_or_none(v, default=None):
return default if v is None else (compat_str(v).strip() or default)
BaseIE = InfoExtractor
class InfoExtractor(BaseIE):

View File

@ -4248,6 +4248,7 @@ def update_url(url, **kwargs):
url: compat_str or parsed URL tuple
if query_update is in kwargs, update query with
its value instead of replacing (overrides any `query`)
NB: query_update expects parse_qs() format: [key: value_list, ...]
returns: compat_str
"""
if not kwargs: