X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcrunchyroll.py;h=85a9a577f645395d6edde83e7b72a1f4001561f8;hb=43ebf77df3bbd93dbbd0336b0243d8d50895ab72;hp=ce2e2d3ba2c7f041f7a90eb85957c9e5800e838e;hpb=dca0e0040ae97b2fc0cd54d5e819a5a278937350;p=youtube-dl
diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py
index ce2e2d3ba..85a9a577f 100644
--- a/youtube_dl/extractor/crunchyroll.py
+++ b/youtube_dl/extractor/crunchyroll.py
@@ -3,7 +3,6 @@ from __future__ import unicode_literals
import re
import json
-import xml.etree.ElementTree as etree
import zlib
from hashlib import sha1
@@ -12,6 +11,7 @@ from .common import InfoExtractor
from .vrv import VRVIE
from ..compat import (
compat_b64decode,
+ compat_etree_Element,
compat_etree_fromstring,
compat_urllib_parse_urlencode,
compat_urllib_request,
@@ -60,7 +60,7 @@ class CrunchyrollBaseIE(InfoExtractor):
self._LOGIN_URL, None, 'Downloading login page')
def is_logged(webpage):
- return '
Redirecting' in webpage
+ return 'href="/logout"' in webpage
# Already logged in
if is_logged(login_page):
@@ -103,19 +103,6 @@ class CrunchyrollBaseIE(InfoExtractor):
def _real_initialize(self):
self._login()
- def _download_webpage(self, url_or_request, *args, **kwargs):
- request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
- else sanitized_Request(url_or_request))
- # Accept-Language must be set explicitly to accept any language to avoid issues
- # similar to https://github.com/rg3/youtube-dl/issues/6797.
- # Along with IP address Crunchyroll uses Accept-Language to guess whether georestriction
- # should be imposed or not (from what I can see it just takes the first language
- # ignoring the priority and requires it to correspond the IP). By the way this causes
- # Crunchyroll to not work in georestriction cases in some browsers that don't place
- # the locale lang first in header. However allowing any language seems to workaround the issue.
- request.add_header('Accept-Language', '*')
- return super(CrunchyrollBaseIE, self)._download_webpage(request, *args, **kwargs)
-
@staticmethod
def _add_skip_wall(url):
parsed_url = compat_urlparse.urlparse(url)
@@ -124,7 +111,7 @@ class CrunchyrollBaseIE(InfoExtractor):
# > This content may be inappropriate for some people.
# > Are you sure you want to continue?
# since it's not disabled by default in crunchyroll account's settings.
- # See https://github.com/rg3/youtube-dl/issues/7202.
+ # See https://github.com/ytdl-org/youtube-dl/issues/7202.
qs['skip_wall'] = ['1']
return compat_urlparse.urlunparse(
parsed_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
@@ -269,6 +256,19 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE):
'1080': ('80', '108'),
}
+ def _download_webpage(self, url_or_request, *args, **kwargs):
+ request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
+ else sanitized_Request(url_or_request))
+ # Accept-Language must be set explicitly to accept any language to avoid issues
+ # similar to https://github.com/ytdl-org/youtube-dl/issues/6797.
+ # Along with IP address Crunchyroll uses Accept-Language to guess whether georestriction
+ # should be imposed or not (from what I can see it just takes the first language
+ # ignoring the priority and requires it to correspond the IP). By the way this causes
+ # Crunchyroll to not work in georestriction cases in some browsers that don't place
+ # the locale lang first in header. However allowing any language seems to workaround the issue.
+ request.add_header('Accept-Language', '*')
+ return super(CrunchyrollBaseIE, self)._download_webpage(request, *args, **kwargs)
+
def _decrypt_subtitles(self, data, iv, id):
data = bytes_to_intlist(compat_b64decode(data))
iv = bytes_to_intlist(compat_b64decode(iv))
@@ -390,7 +390,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
'Downloading subtitles for ' + sub_name, data={
'subtitle_script_id': sub_id,
})
- if not isinstance(sub_doc, etree.Element):
+ if not isinstance(sub_doc, compat_etree_Element):
continue
sid = sub_doc.get('id')
iv = xpath_text(sub_doc, 'iv', 'subtitle iv')
@@ -507,7 +507,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
'video_quality': stream_quality,
'current_page': url,
})
- if isinstance(streamdata, etree.Element):
+ if isinstance(streamdata, compat_etree_Element):
stream_info = streamdata.find('./{default}preload/stream_info')
if stream_info is not None:
stream_infos.append(stream_info)
@@ -518,7 +518,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
'video_format': stream_format,
'video_encode_quality': stream_quality,
})
- if isinstance(stream_info, etree.Element):
+ if isinstance(stream_info, compat_etree_Element):
stream_infos.append(stream_info)
for stream_info in stream_infos:
video_encode_id = xpath_text(stream_info, './video_encode_id')
@@ -593,7 +593,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
season = episode = episode_number = duration = thumbnail = None
- if isinstance(metadata, etree.Element):
+ if isinstance(metadata, compat_etree_Element):
season = xpath_text(metadata, 'series_title')
episode = xpath_text(metadata, 'episode_title')
episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
@@ -661,9 +661,8 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
webpage = self._download_webpage(
self._add_skip_wall(url), show_id,
headers=self.geo_verification_headers())
- title = self._html_search_regex(
- r'(?s)]*>\s*(.*?)',
- webpage, 'title')
+ title = self._html_search_meta('name', webpage, default=None)
+
episode_paths = re.findall(
r'(?s)
]+>.*?