def fix_url(cls, url): # 2033
if not re.match('https?://.+', url, re.IGNORECASE):
url = 'https://www.youtube.com/watch?v={}'.format(url)
qs = query_url(url)
if 'v' in qs:
url = url.split('?')[0] + '?v={}'.format(qs['v'][0])
return url
def get_id(url):
for pattern in PATTERNS:
m = re.match(pattern, url)
if m is None:
continue
username = m.group('username')
pid = m.group('pid')
break
else:
username, pid = None, None
return username, pid
def init(self):
if not re.match('https?://.+', self.url, re.IGNORECASE):
self.url = 'https://www.nicovideo.jp/watch/{}'.format(self.url)
def fix_url(cls, url):
if not re.match('https?://.+', url, re.IGNORECASE):
url = 'https://video.fc2.com/content/{}'.format(url)
return url
def id(self):
mobj = re.match(_VALID_URL, self.url)
video_id = mobj.group('id')
anime_id = mobj.group('anime_id')
return video_id
def get_videos(url, cw=None, depth=0):
print_ = get_print(cw)
if utils.ui_setting:
res_text = compatstr(utils.ui_setting.youtubeCombo_res.currentText())
res = {
'720p': 720,
'1080p': 1080,
'2K': 1440,
'4K': 2160,
'8K': 4320
}[res_text]
else:
res = 720
mobj = re.match(_VALID_URL, url)
video_id = mobj.group('id')
anime_id = mobj.group('anime_id')
print(video_id, anime_id)
print_ = get_print(cw)
html = downloader.read_html(url, methods={'requests'})
soup = Soup(html)
title = soup.find('h1').attrs['title'].strip()
url_thumb = soup.find('meta', {'property': 'og:image'}).attrs['content']
p = get_page(url)
if p is None:
p = 1
print('page:', p)
if p > 1:
pages = get_pages(html)
cid = pages[(p - 1)]['cid']
else:
cid = re.findall('\\bcid(?:["\\\']:|=)(\\d+)', html)[0]
print_('cid: {}'.format(cid))
headers = {'Referer': url}
entries = []
RENDITIONS = [
'qn={}&quality={}&type='.format(qlt, qlt) for qlt in RESOLS.keys()
] # + ['quality=2&type=mp4']
for num, rendition in enumerate(RENDITIONS, start=1):
print('####', num, rendition)
payload = 'appkey=%s&cid=%s&otype=json&%s' % (_APP_KEY, cid, rendition)
sign = hashlib.md5(
(payload + _BILIBILI_KEY).encode('utf-8')).hexdigest()
url_json = 'http://interface.bilibili.com/v2/playurl?%s&sign=%s' % (
payload, sign)
s_json = downloader.read_html(url_json)
print(s_json[:1000])
video_info = json.loads(s_json)
if not video_info:
continue
if 'durl' not in video_info:
print('#### error', num)
if num < len(RENDITIONS):
continue
msg = video_info.get('message')
if msg:
raise Exception(msg)
quality = video_info['quality']
resolution = get_resolution(quality)
s = (u'resolution: {}').format(resolution)
print_(s)
# 2184
if int(re.find('([0-9]+)p', resolution)) > res:
print_('skip resolution')
continue
for idx, durl in enumerate(video_info['durl']):
# 1343
if idx == 0:
size = downloader.get_size(durl['url'], referer=url)
if size < 1024 * 1024 and depth == 0:
print_('size is too small')
return get_videos(url, cw, depth + 1)
formats = [{
'url': durl['url'],
'filesize': int_or_none(durl['size'])
}]
for backup_url in durl.get('backup_url', []):
formats.append({
'url':
backup_url,
'preference':
-2 if 'hd.mp4' in backup_url else -3
})
for a_format in formats:
a_format.setdefault('http_headers',
{}).update({'Referer': url})
entries.append({
'id': '%s_part%s' % (video_id, idx),
'duration': float_or_none(durl.get('length'), 1000),
'formats': formats
})
break
videos = []
for entry in entries:
url_video = entry['formats'][0]['url']
video = Video(url_video, url, video_id, len(videos))
videos.append(video)
info = {'title': clean_title(title), 'url_thumb': url_thumb}
return (videos, info)
def init(self):
if not re.match('https?://.+', self.url, re.IGNORECASE):
self.url = 'https://tv.naver.com/v/{}'.format(self.url)
def url_or_none(url):
if not url or not isinstance(url, str):
return None
url = url.strip()
return url if re.match(r'^(?:(?:https?|rt(?:m(?:pt?[es]?|fp)|sp[su]?)|mms|ftps?):)?//', url) else None
