Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-02 17:22:31 +01:00
Code Issues Releases Activity

[funimation] Use mobile webpage for workaround hulu error

Browse Source
This commit is contained in:
Sergey M․ 2015-12-12 00:38:58 +06:00
parent 9c163950da
commit b59623ef43
1 changed files with 88 additions and 63 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

151
youtube_dl/extractor/funimation.py
View File

@ -18,7 +18,7 @@
class FunimationIE(InfoExtractor): class FunimationIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?funimation\.com/shows/[^/]+/videos/official/(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:www\.)?funimation\.com/shows/[^/]+/videos/official/(?P<id>[^/?#&]+)'
_TEST = { _TESTS = [{
'url': 'http://www.funimation.com/shows/air/videos/official/breeze', 'url': 'http://www.funimation.com/shows/air/videos/official/breeze',
'info_dict': { 'info_dict': {
'id': '658', 'id': '658',
@ -28,19 +28,17 @@ class FunimationIE(InfoExtractor):
'description': 'md5:1769f43cd5fc130ace8fd87232207892', 'description': 'md5:1769f43cd5fc130ace8fd87232207892',
'thumbnail': 're:https?://.*\.jpg', 'thumbnail': 're:https?://.*\.jpg',
}, },
} }, {
'url': 'http://www.funimation.com/shows/hacksign/videos/official/role-play',
def _download_webpage(self, url_or_request, video_id, note='Downloading webpage'): 'info_dict': {
HEADERS = { 'id': '31128',
'User-Agent': 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0', 'display_id': 'role-play',
} 'ext': 'mp4',
if isinstance(url_or_request, compat_urllib_request.Request): 'title': '.hack//SIGN - 1 - Role Play',
for header, value in HEADERS.items(): 'description': 'md5:b602bdc15eef4c9bbb201bb6e6a4a2dd',
url_or_request.add_header(header, value) 'thumbnail': 're:https?://.*\.jpg',
else: },
url_or_request = sanitized_Request(url_or_request, headers=HEADERS) }]
response = super(FunimationIE, self)._download_webpage(url_or_request, video_id, note)
return response
def _login(self): def _login(self):
(username, password) = self._get_login_info() (username, password) = self._get_login_info()
@ -51,6 +49,7 @@ def _login(self):
'password_field': password, 'password_field': password,
})) }))
login_request = sanitized_Request('http://www.funimation.com/login', data, headers={ login_request = sanitized_Request('http://www.funimation.com/login', data, headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0',
'Content-Type': 'application/x-www-form-urlencoded' 'Content-Type': 'application/x-www-form-urlencoded'
}) })
login = self._download_webpage( login = self._download_webpage(
@ -64,15 +63,8 @@ def _real_initialize(self):
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) errors = []
formats = []
items = self._parse_json(
self._search_regex(
r'var\s+playersData\s*=\s*(\[.+?\]);\n',
webpage, 'players data'),
display_id)[0]['playlist'][0]['items']
item = next(item for item in items if item.get('itemAK') == display_id)
ERRORS_MAP = { ERRORS_MAP = {
'ERROR_MATURE_CONTENT_LOGGED_IN': 'matureContentLoggedIn', 'ERROR_MATURE_CONTENT_LOGGED_IN': 'matureContentLoggedIn',
@ -87,48 +79,79 @@ def _real_extract(self, url):
'ERROR_STREAM_NOT_FOUND': 'streamNotFound', 'ERROR_STREAM_NOT_FOUND': 'streamNotFound',
} }
error_messages = {} USER_AGENTS = (
video_error_messages = self._search_regex( # PC UA is served with m3u8 that provides some bonus lower quality formats
r'var\s+videoErrorMessages\s*=\s*({.+?});\n', ('pc', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0'),
webpage, 'error messages', default=None) # Mobile UA allows to extract direct links and also does not fail when
if video_error_messages: # PC UA fails with hulu error (e.g.
error_messages_json = self._parse_json(video_error_messages, display_id, fatal=False) # http://www.funimation.com/shows/hacksign/videos/official/role-play)
if error_messages_json: ('mobile', 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'),
for _, error in error_messages_json.items(): )
type_ = error.get('type')
description = error.get('description')
content = error.get('content')
if type_ == 'text' and description and content:
error_message = ERRORS_MAP.get(description)
if error_message:
error_messages[error_message] = content
errors = [] for kind, user_agent in USER_AGENTS:
formats = [] request = sanitized_Request(url)
for video in item['videoSet']: request.add_header('User-Agent', user_agent)
auth_token = video.get('authToken') webpage = self._download_webpage(
if not auth_token: request, display_id, 'Downloading %s webpage' % kind)
continue
funimation_id = video.get('FUNImationID') or video.get('videoId') items = self._parse_json(
if not auth_token.startswith('?'): self._search_regex(
auth_token = '?%s' % auth_token r'var\s+playersData\s*=\s*(\[.+?\]);\n',
for quality in ('sd', 'hd', 'hd1080'): webpage, 'players data'),
format_url = video.get('%sUrl' % quality) display_id)[0]['playlist'][0]['items']
if not format_url:
item = next(item for item in items if item.get('itemAK') == display_id)
error_messages = {}
video_error_messages = self._search_regex(
r'var\s+videoErrorMessages\s*=\s*({.+?});\n',
webpage, 'error messages', default=None)
if video_error_messages:
error_messages_json = self._parse_json(video_error_messages, display_id, fatal=False)
if error_messages_json:
for _, error in error_messages_json.items():
type_ = error.get('type')
description = error.get('description')
content = error.get('content')
if type_ == 'text' and description and content:
error_message = ERRORS_MAP.get(description)
if error_message:
error_messages[error_message] = content
for video in item.get('videoSet', []):
auth_token = video.get('authToken')
if not auth_token:
continue continue
if not format_url.startswith(('http', '//')): funimation_id = video.get('FUNImationID') or video.get('videoId')
errors.append(format_url) preference = 1 if video.get('languageMode') == 'dub' else 0
continue if not auth_token.startswith('?'):
if determine_ext(format_url) == 'm3u8': auth_token = '?%s' % auth_token
m3u8_formats = self._extract_m3u8_formats( for quality in ('sd', 'hd', 'hd1080'):
format_url + auth_token, display_id, 'mp4', entry_protocol='m3u8_native', format_url = video.get('%sUrl' % quality)
m3u8_id=funimation_id or 'hls', fatal=False) if not format_url:
if m3u8_formats: continue
formats.extend(m3u8_formats) if not format_url.startswith(('http', '//')):
else: errors.append(format_url)
formats.append({ continue
'url': format_url + auth_token, if determine_ext(format_url) == 'm3u8':
}) m3u8_formats = self._extract_m3u8_formats(
format_url + auth_token, display_id, 'mp4', entry_protocol='m3u8_native',
preference=preference, m3u8_id=funimation_id or 'hls', fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
else:
f = {
'url': format_url + auth_token,
'format_id': funimation_id,
'preference': preference,
}
mobj = re.search(r'(?P<height>\d+)-(?P<tbr>\d+)[Kk]', format_url)
if mobj:
f.update({
'height': int(mobj.group('height')),
'tbr': int(mobj.group('tbr')),
})
formats.append(f)
if not formats and errors: if not formats and errors:
raise ExtractorError( raise ExtractorError(
@ -136,6 +159,8 @@ def _real_extract(self, url):
% (self.IE_NAME, clean_html(error_messages.get(errors[0], errors[0]))), % (self.IE_NAME, clean_html(error_messages.get(errors[0], errors[0]))),
expected=True) expected=True)
self._sort_formats(formats)
title = item['title'] title = item['title']
artist = item.get('artist') artist = item.get('artist')
if artist: if artist: