xZero707/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 15:40:18 +01:00
Code Issues Packages Projects Releases Wiki Activity

[iwara] Fix extraction (closes #11781)

Browse Source
This commit is contained in:
Yen Chi Hsuan 2017-02-05 21:48:13 +08:00
parent e4e50f60b1
commit caf0f5f8b7
No known key found for this signature in database
GPG Key ID: 7F902A182457CA23
2 changed files with 30 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
ChangeLog
View File

@ -1,6 +1,7 @@
version <unreleased> version <unreleased>
Extractors Extractors
* [iwara] Fix extraction (#11781)
* [googledrive] Fix extraction on Python 3.6 * [googledrive] Fix extraction on Python 3.6

41
youtube_dl/extractor/iwara.py
View File

@ -3,14 +3,18 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlparse from ..compat import compat_urllib_parse_urlparse
from ..utils import remove_end from ..utils import (
int_or_none,
mimetype2ext,
remove_end,
)
class IwaraIE(InfoExtractor): class IwaraIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.|ecchi\.)?iwara\.tv/videos/(?P<id>[a-zA-Z0-9]+)' _VALID_URL = r'https?://(?:www\.|ecchi\.)?iwara\.tv/videos/(?P<id>[a-zA-Z0-9]+)'
_TESTS = [{ _TESTS = [{
'url': 'http://iwara.tv/videos/amVwUl1EHpAD9RD', 'url': 'http://iwara.tv/videos/amVwUl1EHpAD9RD',
'md5': '1d53866b2c514b23ed69e4352fdc9839', # md5 is unstable
'info_dict': { 'info_dict': {
'id': 'amVwUl1EHpAD9RD', 'id': 'amVwUl1EHpAD9RD',
'ext': 'mp4', 'ext': 'mp4',
@ -23,17 +27,17 @@ class IwaraIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '0B1LvuHnL-sRFNXB1WHNqbGw4SXc', 'id': '0B1LvuHnL-sRFNXB1WHNqbGw4SXc',
'ext': 'mp4', 'ext': 'mp4',
'title': '[3D Hentai] Kyonyu Ã\x97 Genkai Ã\x97 Emaki Shinobi Girls.mp4', 'title': '[3D Hentai] Kyonyu × Genkai × Emaki Shinobi Girls.mp4',
'age_limit': 18, 'age_limit': 18,
}, },
'add_ie': ['GoogleDrive'], 'add_ie': ['GoogleDrive'],
}, { }, {
'url': 'http://www.iwara.tv/videos/nawkaumd6ilezzgq', 'url': 'http://www.iwara.tv/videos/nawkaumd6ilezzgq',
'md5': '1d85f1e5217d2791626cff5ec83bb189', # md5 is unstable
'info_dict': { 'info_dict': {
'id': '6liAP9s2Ojc', 'id': '6liAP9s2Ojc',
'ext': 'mp4', 'ext': 'mp4',
'age_limit': 0, 'age_limit': 18,
'title': '[MMD] Do It Again Ver.2 [1080p 60FPS] (Motion,Camera,Wav+DL)', 'title': '[MMD] Do It Again Ver.2 [1080p 60FPS] (Motion,Camera,Wav+DL)',
'description': 'md5:590c12c0df1443d833fbebe05da8c47a', 'description': 'md5:590c12c0df1443d833fbebe05da8c47a',
'upload_date': '20160910', 'upload_date': '20160910',
@ -52,9 +56,9 @@ def _real_extract(self, url):
# ecchi is 'sexy' in Japanese # ecchi is 'sexy' in Japanese
age_limit = 18 if hostname.split('.')[0] == 'ecchi' else 0 age_limit = 18 if hostname.split('.')[0] == 'ecchi' else 0
entries = self._parse_html5_media_entries(url, webpage, video_id) video_data = self._download_json('http://www.iwara.tv/api/video/%s' % video_id, video_id)
if not entries: if not video_data:
iframe_url = self._html_search_regex( iframe_url = self._html_search_regex(
r'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1', r'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1',
webpage, 'iframe URL', group='url') webpage, 'iframe URL', group='url')
@ -67,11 +71,24 @@ def _real_extract(self, url):
title = remove_end(self._html_search_regex( title = remove_end(self._html_search_regex(
r'<title>([^<]+)</title>', webpage, 'title'), ' | Iwara') r'<title>([^<]+)</title>', webpage, 'title'), ' | Iwara')
info_dict = entries[0] formats = []
info_dict.update({ for a_format in video_data:
format_id = a_format.get('resolution')
height = int_or_none(self._search_regex(
r'(\d+)p', format_id, 'height', default=None))
formats.append({
'url': a_format['uri'],
'format_id': format_id,
'ext': mimetype2ext(a_format.get('mime')) or 'mp4',
'height': height,
'quality': 1 if format_id == 'Source' else 0,
})
self._sort_formats(formats)
return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'age_limit': age_limit, 'age_limit': age_limit,
}) 'formats': formats,
}
return info_dict