X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/5920ef2b4969021b7f83d154b325036d9b598877..20205e79eb4216762c923790b27dbe38f945293a:/youtube_dl/extractor/crunchyroll.py?ds=sidebyside
diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py
index 4a68d09..bc2d1fa 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
@@ -12,7 +11,9 @@ from .common import InfoExtractor
from .vrv import VRVIE
from ..compat import (
compat_b64decode,
+ compat_etree_Element,
compat_etree_fromstring,
+ compat_str,
compat_urllib_parse_urlencode,
compat_urllib_request,
compat_urlparse,
@@ -25,9 +26,9 @@ from ..utils import (
intlist_to_bytes,
int_or_none,
lowercase_escape,
+ merge_dicts,
remove_end,
sanitized_Request,
- unified_strdate,
urlencode_postdata,
xpath_text,
)
@@ -56,22 +57,11 @@ class CrunchyrollBaseIE(InfoExtractor):
if username is None:
return
- self._download_webpage(
- 'https://www.crunchyroll.com/?a=formhandler',
- None, 'Logging in', 'Wrong login info',
- data=urlencode_postdata({
- 'formname': 'RpcApiUser_Login',
- 'next_url': 'https://www.crunchyroll.com/acct/membership',
- 'name': username,
- 'password': password,
- }))
-
- '''
login_page = self._download_webpage(
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):
@@ -110,24 +100,10 @@ class CrunchyrollBaseIE(InfoExtractor):
raise ExtractorError('Unable to login: %s' % error, expected=True)
raise ExtractorError('Unable to log in')
- '''
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)
@@ -136,7 +112,7 @@ 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)))
@@ -144,7 +120,7 @@ class CrunchyrollBaseIE(InfoExtractor):
class CrunchyrollIE(CrunchyrollBaseIE, VRVIE):
IE_NAME = 'crunchyroll'
- _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P[0-9]+))(?:[/?&]|$)'
+ _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|(?:[^/]*/){1,2}[^/?&]*?)(?P[0-9]+))(?:[/?&]|$)'
_TESTS = [{
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
'info_dict': {
@@ -161,6 +137,7 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE):
# rtmp
'skip_download': True,
},
+ 'skip': 'Video gone',
}, {
'url': 'http://www.crunchyroll.com/media-589804/culture-japan-1',
'info_dict': {
@@ -182,11 +159,12 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE):
'info_dict': {
'id': '702409',
'ext': 'mp4',
- 'title': 'Re:ZERO -Starting Life in Another World- Episode 5 â The Morning of Our Promise Is Still Distant',
- 'description': 'md5:97664de1ab24bbf77a9c01918cb7dca9',
+ 'title': compat_str,
+ 'description': compat_str,
'thumbnail': r're:^https?://.*\.jpg$',
- 'uploader': 'TV TOKYO',
- 'upload_date': '20160508',
+ 'uploader': 'Re:Zero Partners',
+ 'timestamp': 1462098900,
+ 'upload_date': '20160501',
},
'params': {
# m3u8 download
@@ -197,12 +175,13 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE):
'info_dict': {
'id': '727589',
'ext': 'mp4',
- 'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 â Give Me Deliverance From This Judicial Injustice!",
- 'description': 'md5:cbcf05e528124b0f3a0a419fc805ea7d',
+ 'title': compat_str,
+ 'description': compat_str,
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Kadokawa Pictures Inc.',
- 'upload_date': '20170118',
- 'series': "KONOSUBA -God's blessing on this wonderful world!",
+ 'timestamp': 1484130900,
+ 'upload_date': '20170111',
+ 'series': compat_str,
'season': "KONOSUBA -God's blessing on this wonderful world! 2",
'season_number': 2,
'episode': 'Give Me Deliverance From This Judicial Injustice!',
@@ -225,10 +204,11 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE):
'info_dict': {
'id': '535080',
'ext': 'mp4',
- 'title': '11eyes Episode 1 â Red Night ~ Piros éjszaka',
- 'description': 'Kakeru and Yuka are thrown into an alternate nightmarish world they call "Red Night".',
+ 'title': compat_str,
+ 'description': compat_str,
'uploader': 'Marvelous AQL Inc.',
- 'upload_date': '20091021',
+ 'timestamp': 1255512600,
+ 'upload_date': '20091014',
},
'params': {
# Just test metadata extraction
@@ -249,15 +229,17 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE):
# just test metadata extraction
'skip_download': True,
},
+ 'skip': 'Video gone',
}, {
# A video with a vastly different season name compared to the series name
'url': 'http://www.crunchyroll.com/nyarko-san-another-crawling-chaos/episode-1-test-590532',
'info_dict': {
'id': '590532',
'ext': 'mp4',
- 'title': 'Haiyoru! Nyaruani (ONA) Episode 1 â Test',
- 'description': 'Mahiro and Nyaruko talk about official certification.',
+ 'title': compat_str,
+ 'description': compat_str,
'uploader': 'TV TOKYO',
+ 'timestamp': 1330956000,
'upload_date': '20120305',
'series': 'Nyarko-san: Another Crawling Chaos',
'season': 'Haiyoru! Nyaruani (ONA)',
@@ -269,6 +251,9 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE):
}, {
'url': 'http://www.crunchyroll.com/media-723735',
'only_matching': True,
+ }, {
+ 'url': 'https://www.crunchyroll.com/en-gb/mob-psycho-100/episode-2-urban-legends-encountering-rumors-780921',
+ 'only_matching': True,
}]
_FORMAT_IDS = {
@@ -278,6 +263,19 @@ 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))
@@ -399,7 +397,7 @@ 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')
@@ -451,23 +449,21 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
webpage, 'language', default=None, group='lang')
video_title = self._html_search_regex(
- r'(?s)]*>((?:(?!]+itemprop=["\']title["\'][^>]*>(?:(?!',
- webpage, 'video_title')
+ (r'(?s)]*>((?:(?!]+itemprop=["\']title["\']|meta[^>]+itemprop=["\']position["\'])[^>]*>(?:(?!',
+ r'(.+?),\s+-\s+.+? Crunchyroll'),
+ webpage, 'video_title', default=None)
+ if not video_title:
+ video_title = re.sub(r'^Watch\s+', '', self._og_search_description(webpage))
video_title = re.sub(r' {2,}', ' ', video_title)
video_description = (self._parse_json(self._html_search_regex(
r'