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

[VidLii] Add 720p support (yt-dlp backport-ish) #30924

Merged
merged 12 commits into from
Jun 11, 2024
Merged

[VidLii] Add 720p support (yt-dlp backport-ish) #30924

Changes from 4 commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
13b0b2d
[VidLii] Add HD support
mrpapersonic May 7, 2022
a0832f1
Use compat for HTTPError
mrpapersonic May 7, 2022
3c87b05
Python 2
mrpapersonic May 7, 2022
c184420
hm?
mrpapersonic May 7, 2022
643433d
Double quotes -> single quotes, backslash to period
mrpapersonic May 20, 2022
2e8e7d6
Import str_to_int from ..utils
mrpapersonic May 20, 2022
ef49e32
Apply suggestions from code review
mrpapersonic May 20, 2022
f9eef66
Add periods to accepted view count, get str_to_int to handle them for us
mrpapersonic May 20, 2022
b6b629f
TypeError: `formats` needs to be a dictionary, not a list
mrpapersonic May 21, 2022
dbedd60
Move source check back up to the if statement
mrpapersonic May 21, 2022
e558c3d
Force re-run CI
dirkf Jun 11, 2024
d687b6a
Revert unused import
dirkf Jun 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
57 changes: 50 additions & 7 deletions youtube_dl/extractor/vidlii.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,9 @@
import re

from .common import InfoExtractor

from ..utils import (
ExtractorError,
dirkf marked this conversation as resolved.
Show resolved Hide resolved
float_or_none,
get_element_by_id,
int_or_none,
Expand Down Expand Up @@ -35,6 +37,25 @@ class VidLiiIE(InfoExtractor):
'categories': ['News & Politics'],
'tags': ['Vidlii', 'Jan', 'Videogames'],
}
}, { # HD
dirkf marked this conversation as resolved.
Show resolved Hide resolved
'url': 'https://www.vidlii.com/watch?v=2Ng8Abj2Fkl',
'md5': '450e7da379c884788c3a4fa02a3ce1a4',
'info_dict': {
'id': '2Ng8Abj2Fkl',
'ext': 'mp4',
'title': 'test',
'description': 'md5:cc55a86032a7b6b3cbfd0f6b155b52e9',
'thumbnail': 'https://www.vidlii.com/usfi/thmp/2Ng8Abj2Fkl.jpg',
'uploader': 'VidLii',
'uploader_url': 'https://www.vidlii.com/user/VidLii',
'upload_date': '20200927',
'duration': 5,
'view_count': int,
'comment_count': int,
'average_rating': float,
'categories': ['Film & Animation'],
'tags': ['1', '2'],
mrpapersonic marked this conversation as resolved.
Show resolved Hide resolved
},
}, {
'url': 'https://www.vidlii.com/embed?v=tJluaH4BJ3v&a=0',
'only_matching': True,
Expand All @@ -46,9 +67,31 @@ def _real_extract(self, url):
webpage = self._download_webpage(
'https://www.vidlii.com/watch?v=%s' % video_id, video_id)

video_url = self._search_regex(
r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1', webpage,
'video url', group='url')
formats = []

def add_format(format_url, height=None):
height = int(self._search_regex(r"(\d+).mp4",
format_url, "height", default=360))
mrpapersonic marked this conversation as resolved.
Show resolved Hide resolved

formats.append({
'url': format_url,
'format_id': '%dp' % height if height else None,
'height': height,
})

sources = re.findall(
r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1',
mrpapersonic marked this conversation as resolved.
Show resolved Hide resolved
webpage)

try:
self._request_webpage(sources[1][1], video_id, 'Checking HD URL')
add_format(sources[1][1])
except ExtractorError:
pass

add_format(sources[0][1])
mrpapersonic marked this conversation as resolved.
Show resolved Hide resolved

self._sort_formats(formats)

title = self._search_regex(
mrpapersonic marked this conversation as resolved.
Show resolved Hide resolved
(r'<h1>([^<]+)</h1>', r'<title>([^<]+) - VidLii<'), webpage,
Expand Down Expand Up @@ -83,9 +126,9 @@ def _real_extract(self, url):
r'duration\s*:\s*(\d+)', webpage, 'duration', fatal=False))

view_count = int_or_none(self._search_regex(
(r'<strong>(\d+)</strong> views',
r'Views\s*:\s*<strong>(\d+)</strong>'),
webpage, 'view count', fatal=False))
(r'<strong>([\d,]+)</strong> views',
r'Views\s*:\s*<strong>([\d,]+)</strong>'),
webpage, 'view count', fatal=False).replace(",", ""))
mrpapersonic marked this conversation as resolved.
Show resolved Hide resolved

comment_count = int_or_none(self._search_regex(
(r'<span[^>]+id=["\']cmt_num[^>]+>(\d+)',
Expand All @@ -109,7 +152,7 @@ def _real_extract(self, url):

return {
'id': video_id,
'url': video_url,
'formats': formats,
'title': title,
'description': description,
'thumbnail': thumbnail,
Expand Down