Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-10 04:56:10 +08:00
Code Issues Releases Wiki Activity

Requested changes

Browse Source
This commit is contained in:
BrutuZ 2020-03-12 21:24:00 -03:00
parent ef753bc223
commit 9aaf20b0ed
1 changed files with 26 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
youtube_dl/extractor/hanime.py
View File

@ -7,10 +7,13 @@ from ..utils import (
parse_filesize, parse_filesize,
float_or_none, float_or_none,
int_or_none, int_or_none,
parse_iso8601,
unified_strdate, unified_strdate,
str_or_none, str_or_none,
url_or_none,
parse_duration, parse_duration,
sanitize_url,
compat_str,
try_get,
) )
@ -26,12 +29,12 @@ class HanimeIE(InfoExtractor):
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'release_date': '20120127', 'release_date': '20120127',
'upload_date': '20140509', 'upload_date': '20140509',
'timestamp': 1399624976,
'creator': 'Magin Label', 'creator': 'Magin Label',
'view_count': int, 'view_count': int,
'like_count': int, 'like_count': int,
'dislike_count': int, 'dislike_count': int,
'tags': list, 'tags': list,
'censored': 'True',
'ext': 'mp4', 'ext': 'mp4',
}, },
'params': { 'params': {
@ -42,60 +45,51 @@ class HanimeIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_slug = self._match_id(url) video_slug = self._match_id(url)
page_json = self._html_search_regex(r'<script>.+__NUXT__=(.+?);<\/script>', self._download_webpage(url, video_slug), 'Inline JSON')
webpage = self._download_webpage(url, video_slug) page_json = try_get(self._parse_json(page_json, video_slug), lambda x: x['state']['data']['video']['hentai_video'], dict) or {}
page_json = self._html_search_regex(r'window.__NUXT__=(.+?);<\/script>', webpage, 'Inline JSON')
page_json = self._parse_json(page_json, video_slug).get('state').get('data').get('video').get('hentai_video')
api_json = self._download_json( api_json = self._download_json(
'https://members.hanime.tv/api/v3/videos_manifests/%s' % video_slug, 'https://members.hanime.tv/api/v3/videos_manifests/%s' % video_slug,
video_slug, video_slug,
'API Call', headers={'X-Directive': 'api'}).get('videos_manifest').get('servers')[0].get('streams') 'API Call', headers={'X-Directive': 'api'}).get('videos_manifest').get('servers')[0].get('streams')
title = page_json.get('name') or api_json.get[0].get('video_stream_group_id') title = page_json.get('name') or api_json.get[0].get('video_stream_group_id')
tags = [t.get('text') for t in page_json.get('hentai_tags')] tags = []
for t in page_json.get('hentai_tags'):
if t.get('text'):
tags.append('text')
formats = [] formats = []
for f in api_json: for f in api_json:
item_url = url_or_none(f.get('url')) or url_or_none('https://hanime.tv/api/v1/m3u8s/%s.m3u8' % f.get('id')) item_url = sanitize_url(f.get('url')) or sanitize_url('https://hanime.tv/api/v1/m3u8s/%s.m3u8' % f.get('id'))
format = [{ width = float_or_none(f.get('width'))
'width': int_or_none(f.get('width')), height = float_or_none(f.get('height'))
'height': int_or_none(f.get('height')), format = {
'filesize_approx': parse_filesize('%sMb' % f.get('filesize_mbs')), 'width': width,
'height': height,
'filesize_approx': float_or_none(parse_filesize('%sMb' % f.get('filesize_mbs'))),
'protocol': 'm3u8', 'protocol': 'm3u8',
'format_id': 'mp4-%sp' % f.get('height'), 'format_id': 'mp4-%sp' % f.get('height'),
'tbr': float_or_none(float_or_none(f.get('filesize_mbs'), invscale=8388), int_or_none(f.get('duration_in_ms'), 1000)),
'ext': 'mp4', 'ext': 'mp4',
'url': item_url, 'url': item_url,
}, { }
'width': int_or_none(f.get('width')), formats.append(format)
'height': int_or_none(f.get('height')),
'protocol': 'https',
'format_id': 'm3u8-%sp' % f.get('height'),
'format_note': '~8-50.00Kib',
'ext': 'm3u8',
'url': item_url,
}]
for i in format:
formats.append(i)
formats.reverse() formats.reverse()
return { return {
'id': str_or_none(api_json[0].get('id')), 'id': compat_str(api_json[0].get('id')),
'display_id': video_slug, 'display_id': video_slug,
'title': title, 'title': title,
'description': clean_html(page_json.get('description')).strip(), 'description': clean_html(page_json.get('description')),
'thumbnails': [ 'thumbnails': [
{'preference': 0, 'id': 'Poster', 'url': url_or_none(page_json.get('poster_url'))}, {'preference': 0, 'id': 'Poster', 'url': page_json.get('poster_url')},
{'preference': 1, 'id': 'Cover', 'url': url_or_none(page_json.get('cover_url'))}, {'preference': 1, 'id': 'Cover', 'url': page_json.get('cover_url')},
], ],
'release_date': unified_strdate(page_json.get('released_at')), 'release_date': unified_strdate(page_json.get('released_at')),
'upload_date': unified_strdate(page_json.get('created_at')), 'upload_date': unified_strdate(page_json.get('created_at')),
'timestamp': parse_iso8601(page_json.get('created_at')),
'creator': str_or_none(page_json.get('brand')), 'creator': str_or_none(page_json.get('brand')),
'view_count': int_or_none(page_json.get('views')), 'view_count': int_or_none(page_json.get('views')),
'like_count': int_or_none(page_json.get('likes')), 'like_count': int_or_none(page_json.get('likes')),
'dislike_count': int_or_none(page_json.get('dislikes')), 'dislike_count': int_or_none(page_json.get('dislikes')),
'duration': parse_duration('%sms' % f.get('duration_in_ms')), 'duration': float_or_none(parse_duration('%sms' % f.get('duration_in_ms'))),
'tags': tags, 'tags': tags,
'censored': str_or_none(page_json.get('is_censored')),
'formats': formats, 'formats': formats,
} }