from __future__ import unicode_literals
import re
+import itertools
from .common import InfoExtractor
from ..utils import (
class BiliBiliIE(InfoExtractor):
_VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>[0-9]+)/'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.bilibili.tv/video/av1074402/',
'md5': '2c301e4dab317596e837c3e7633e7d86',
'info_dict': {
- 'id': '1074402',
+ 'id': '1074402_part1',
'ext': 'flv',
'title': '【金坷垃】金泡沫',
'duration': 308,
'upload_date': '20140420',
'thumbnail': 're:^https?://.+\.jpg',
},
- }
+ }, {
+ 'url': 'http://www.bilibili.com/video/av1041170/',
+ 'info_dict': {
+ 'id': '1041170',
+ 'title': '【BD1080P】刀语【诸神&异域】',
+ },
+ 'playlist_count': 9,
+ }]
def _real_extract(self, url):
video_id = self._match_id(url)
cid = self._search_regex(r'cid=(\d+)', webpage, 'cid')
+ entries = []
+
lq_doc = self._download_xml(
'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid,
video_id,
note='Downloading LQ video info'
)
- lq_durl = lq_doc.find('./durl')
- formats = [{
- 'format_id': 'lq',
- 'quality': 1,
- 'url': lq_durl.find('./url').text,
- 'filesize': int_or_none(
- lq_durl.find('./size'), get_attr='text'),
- }]
+ lq_durls = lq_doc.findall('./durl')
hq_doc = self._download_xml(
'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid,
note='Downloading HQ video info',
fatal=False,
)
- if hq_doc is not False:
- hq_durl = hq_doc.find('./durl')
- formats.append({
- 'format_id': 'hq',
- 'quality': 2,
- 'ext': 'flv',
- 'url': hq_durl.find('./url').text,
+ hq_durls = hq_doc.findall('./durl') if hq_doc is not False else itertools.repeat(None)
+
+ assert len(lq_durls) == len(hq_durls)
+
+ i = 1
+ for lq_durl, hq_durl in zip(lq_durls, hq_durls):
+ formats = [{
+ 'format_id': 'lq',
+ 'quality': 1,
+ 'url': lq_durl.find('./url').text,
'filesize': int_or_none(
- hq_durl.find('./size'), get_attr='text'),
+ lq_durl.find('./size'), get_attr='text'),
+ }]
+ if hq_durl:
+ formats.append({
+ 'format_id': 'hq',
+ 'quality': 2,
+ 'ext': 'flv',
+ 'url': hq_durl.find('./url').text,
+ 'filesize': int_or_none(
+ hq_durl.find('./size'), get_attr='text'),
+ })
+ self._sort_formats(formats)
+
+ entries.append({
+ 'id': '%s_part%d' % (video_id, i),
+ 'title': title,
+ 'formats': formats,
+ 'duration': duration,
+ 'upload_date': upload_date,
+ 'thumbnail': thumbnail,
})
- self._sort_formats(formats)
+ i += 1
+
return {
+ '_type': 'multi_video',
+ 'entries': entries,
'id': video_id,
- 'title': title,
- 'formats': formats,
- 'duration': duration,
- 'upload_date': upload_date,
- 'thumbnail': thumbnail,
+ 'title': title
}
'timestamp': 1198527840, # timestamp field has different value if logged in
'duration': 304,
},
+ }, {
+ 'url': 'http://www.nicovideo.jp/watch/so22543406',
+ 'info_dict': {
+ 'id': '1388129933',
+ 'ext': 'mp4',
+ 'title': '【第1回】RADIOアニメロミックス ラブライブ！～のぞえりRadio Garden～',
+ 'description': 'md5:b27d224bb0ff53d3c8269e9f8b561cf1',
+ 'timestamp': 1388851200,
+ 'upload_date': '20140104',
+ 'uploader': 'アニメロチャンネル',
+ 'uploader_id': '312',
+ }
}]
_VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
# Get video webpage. We are not actually interested in it for normal
# cases, but need the cookies in order to be able to download the
# info webpage
- webpage = self._download_webpage('http://www.nicovideo.jp/watch/' + video_id, video_id)
+ webpage, handle = self._download_webpage_handle(
+ 'http://www.nicovideo.jp/watch/' + video_id, video_id)
+ if video_id.startswith('so'):
+ video_id = self._match_id(handle.geturl())
video_info = self._download_xml(
'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
class VeeHDIE(InfoExtractor):
_VALID_URL = r'https?://veehd\.com/video/(?P<id>\d+)'
- _TEST = {
+ # Seems VeeHD videos have multiple copies on several servers, all of
+ # whom have different MD5 checksums, so omit md5 field in all tests
+ _TESTS = [{
'url': 'http://veehd.com/video/4639434_Solar-Sinter',
'info_dict': {
'id': '4639434',
'uploader_id': 'VideoEyes',
'description': 'md5:46a840e8692ddbaffb5f81d9885cb457',
},
- }
+ 'skip': 'Video deleted',
+ }, {
+ 'url': 'http://veehd.com/video/4905758_Elysian-Fields-Channeling',
+ 'info_dict': {
+ 'id': '4905758',
+ 'ext': 'mp4',
+ 'title': 'Elysian Fields - Channeling',
+ 'description': 'md5:360e4e95fdab58aefbea0f2a19e5604b',
+ 'uploader_id': 'spotted',
+ }
+ }, {
+ 'url': 'http://veehd.com/video/4665804_Tell-No-One-Ne-le-dis-a-personne-2006-French-EngSoftSubs-Re-Up',
+ 'info_dict': {
+ 'id': '4665804',
+ 'ext': 'avi',
+ 'title': 'Tell No One (Ne le dis a personne) 2006 French(EngSoftSubs) Re-Up',
+ 'description': 'md5:d660cca685549776f37165e9a10b60ba',
+ 'uploader_id': 'belial2549',
+ }
+ }]
def _real_extract(self, url):
video_id = self._match_id(url)
player_page = self._download_webpage(
player_url, video_id, 'Downloading player page')
+ video_url = None
+
config_json = self._search_regex(
r'value=\'config=({.+?})\'', player_page, 'config json', default=None)
if config_json:
config = json.loads(config_json)
video_url = compat_urlparse.unquote(config['clip']['url'])
- else:
+
+ if not video_url:
+ video_url = self._html_search_regex(
+ r'<embed[^>]+type="video/divx"[^>]+src="([^"]+)"',
+ player_page, 'video url', default=None)
+
+ if not video_url:
iframe_src = self._search_regex(
r'<iframe[^>]+src="/?([^"]+)"', player_page, 'iframe url')
iframe_url = 'http://veehd.com/%s' % iframe_src
'id': video_id,
'title': title,
'url': video_url,
- 'ext': 'mp4',
'uploader_id': uploader_id,
'thumbnail': thumbnail,
'description': description,
projects / youtube-dl / commitdiff