from __future__ import unicode_literals
import re
+import json
import base64
import zlib
+import xml.etree.ElementTree
from hashlib import sha1
from math import pow, sqrt, floor
-from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
from ..utils import (
ExtractorError,
compat_urllib_parse,
intlist_to_bytes,
unified_strdate,
clean_html,
+ urlencode_postdata,
)
from ..aes import (
aes_cbc_decrypt,
inc,
)
+from .common import InfoExtractor
-class CrunchyrollIE(InfoExtractor):
+class CrunchyrollIE(SubtitlesInfoExtractor):
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
_TEST = {
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
'1080': ('80', '108'),
}
+ def _login(self):
+ (username, password) = self._get_login_info()
+ if username is None:
+ return
+ self.report_login()
+ login_url = 'https://www.crunchyroll.com/?a=formhandler'
+ data = urlencode_postdata({
+ 'formname': 'RpcApiUser_Login',
+ 'name': username,
+ 'password': password,
+ })
+ login_request = compat_urllib_request.Request(login_url, data)
+ login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+ self._download_webpage(login_request, None, False, 'Wrong login info')
+
+
+ def _real_initialize(self):
+ self._login()
+
+
def _decrypt_subtitles(self, data, iv, id):
data = bytes_to_intlist(data)
iv = bytes_to_intlist(iv)
return zlib.decompress(decrypted_data)
def _convert_subtitles_to_srt(self, subtitles):
- i = 1
output = ''
- for start, end, text in re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles):
+ for i, (start, end, text) in enumerate(re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles), 1):
start = start.replace('.', ',')
end = end.replace('.', ',')
text = clean_html(text)
if not text:
continue
output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
- i += 1
+ return output
+
+ def _convert_subtitles_to_ass(self, subtitles):
+ output = ''
+
+ def ass_bool(strvalue):
+ assvalue = '0'
+ if strvalue == '1':
+ assvalue = '-1'
+ return assvalue
+
+ sub_root = xml.etree.ElementTree.fromstring(subtitles)
+ if not sub_root:
+ return output
+
+ output = '[Script Info]\n'
+ output += 'Title: %s\n' % sub_root.attrib["title"]
+ output += 'ScriptType: v4.00+\n'
+ output += 'WrapStyle: %s\n' % sub_root.attrib["wrap_style"]
+ output += 'PlayResX: %s\n' % sub_root.attrib["play_res_x"]
+ output += 'PlayResY: %s\n' % sub_root.attrib["play_res_y"]
+ output += """ScaledBorderAndShadow: yes
+
+[V4+ Styles]
+Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding
+"""
+ for style in sub_root.findall('./styles/style'):
+ output += 'Style: ' + style.attrib["name"]
+ output += ',' + style.attrib["font_name"]
+ output += ',' + style.attrib["font_size"]
+ output += ',' + style.attrib["primary_colour"]
+ output += ',' + style.attrib["secondary_colour"]
+ output += ',' + style.attrib["outline_colour"]
+ output += ',' + style.attrib["back_colour"]
+ output += ',' + ass_bool(style.attrib["bold"])
+ output += ',' + ass_bool(style.attrib["italic"])
+ output += ',' + ass_bool(style.attrib["underline"])
+ output += ',' + ass_bool(style.attrib["strikeout"])
+ output += ',' + style.attrib["scale_x"]
+ output += ',' + style.attrib["scale_y"]
+ output += ',' + style.attrib["spacing"]
+ output += ',' + style.attrib["angle"]
+ output += ',' + style.attrib["border_style"]
+ output += ',' + style.attrib["outline"]
+ output += ',' + style.attrib["shadow"]
+ output += ',' + style.attrib["alignment"]
+ output += ',' + style.attrib["margin_l"]
+ output += ',' + style.attrib["margin_r"]
+ output += ',' + style.attrib["margin_v"]
+ output += ',' + style.attrib["encoding"]
+ output += '\n'
+
+ output += """
+[Events]
+Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
+"""
+ for event in sub_root.findall('./events/event'):
+ output += 'Dialogue: 0'
+ output += ',' + event.attrib["start"]
+ output += ',' + event.attrib["end"]
+ output += ',' + event.attrib["style"]
+ output += ',' + event.attrib["name"]
+ output += ',' + event.attrib["margin_l"]
+ output += ',' + event.attrib["margin_r"]
+ output += ',' + event.attrib["margin_v"]
+ output += ',' + event.attrib["effect"]
+ output += ',' + event.attrib["text"]
+ output += '\n'
+
return output
def _real_extract(self,url):
if note_m:
raise ExtractorError(note_m)
+ mobj = re.search(r'Page\.messaging_box_controller\.addItems\(\[(?P<msg>{.+?})\]\)', webpage)
+ if mobj:
+ msg = json.loads(mobj.group('msg'))
+ if msg.get('type') == 'error':
+ raise ExtractorError('crunchyroll returned error: %s' % msg['message_body'], expected=True)
+
video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, 'video_title', flags=re.DOTALL)
video_title = re.sub(r' {2,}', ' ', video_title)
video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='')
})
subtitles = {}
+ sub_format = self._downloader.params.get('subtitlesformat', 'srt')
for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage):
sub_page = self._download_webpage('http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id='+sub_id,\
video_id, note='Downloading subtitles for '+sub_name)
data = base64.b64decode(data)
subtitle = self._decrypt_subtitles(data, iv, id).decode('utf-8')
- lang_code = self._search_regex(r'lang_code=\'([^\']+)', subtitle, 'subtitle_lang_code', fatal=False)
+ lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
if not lang_code:
continue
- subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)
+ if sub_format == 'ass':
+ subtitles[lang_code] = self._convert_subtitles_to_ass(subtitle)
+ else:
+ subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)
+
+ if self._downloader.params.get('listsubtitles', False):
+ self._list_available_subtitles(video_id, subtitles)
+ return
return {
'id': video_id,
'upload_date': video_upload_date,
'subtitles': subtitles,
'formats': formats,
+ }
+
+
+class CrunchyrollShowPlaylistIE(InfoExtractor):
+ IE_NAME = "crunchyroll:playlist"
+ _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<show>[\w\-]+))/?$'
+ _TITLE_EXTR = r'<span\s+itemprop="name">\s*(?P<showtitle>[\w\s]+)'
+
+ _TESTS = [{
+ 'url' : 'http://www.crunchyroll.com/attack-on-titan',
+ 'info_dict' : {
+ 'title' : 'Attack on Titan'
+ },
+ 'playlist_count' : 15
+ }]
+
+ def _extract_title_entries(self,id,webpage):
+ _EPISODE_ID_EXTR = r'id="showview_videos_media_(?P<vidid>\d+)".*?href="/{0}/(?P<vidurl>[\w\-]+-(?P=vidid))"'.format(id)
+ title = self._html_search_regex(self._TITLE_EXTR,webpage,"title",flags=re.UNICODE|re.MULTILINE)
+ episode_urls = [self.url_result('http://www.crunchyroll.com/{0}/{1}'.format(id, showmatch[1])) for
+ showmatch in re.findall(_EPISODE_ID_EXTR, webpage,re.UNICODE|re.MULTILINE|re.DOTALL)]
+ episode_urls.reverse()
+ return title, episode_urls
+
+
+ def _real_extract(self, url):
+ url_match = re.match(self._VALID_URL,url)
+ show_id = url_match.group('show')
+ webpage = self._download_webpage(url,show_id)
+ (title,entries) = self._extract_title_entries(show_id,webpage)
+ return {
+ '_type' : 'playlist',
+ 'id' : show_id,
+ 'title' : title,
+ 'entries' : entries
}
\ No newline at end of file
projects / youtube-dl / blobdiff