Merge tag 'upstream/2014.10.30'

[youtubedl] / youtube_dl / extractor / crunchyroll.py

diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py
index 026a9177e754de7d606961e6e4793af86da49fe2..cc612d08ee469ee1cb3cedc074ac132c20e983d9 100644 (file)
--- a/youtube_dl/extractor/crunchyroll.py
+++ b/youtube_dl/extractor/crunchyroll.py
@@ -5,10 +5,11 @@ import re
 import json
 import base64
 import zlib
 import json
 import base64
 import zlib

+import xml.etree.ElementTree

 
 from hashlib import sha1
 from math import pow, sqrt, floor
 
 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,
 from ..utils import (
     ExtractorError,
     compat_urllib_parse,


@@ -17,14 +18,16 @@ from ..utils import (
     intlist_to_bytes,
     unified_strdate,
     clean_html,
     intlist_to_bytes,
     unified_strdate,
     clean_html,

+    urlencode_postdata,

 )
 from ..aes import (
     aes_cbc_decrypt,
     inc,
 )
 )
 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]+))(?:[/?&]|$)'
     _TEST = {
         'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
     _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
     _TEST = {
         'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',


@@ -37,6 +40,7 @@ class CrunchyrollIE(InfoExtractor):
             'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
             'uploader': 'Yomiuri Telecasting Corporation (YTV)',
             'upload_date': '20131013',
             'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
             'uploader': 'Yomiuri Telecasting Corporation (YTV)',
             'upload_date': '20131013',

+            'url': 're:(?!.*&amp)',

         },
         'params': {
             # rtmp
         },
         'params': {
             # rtmp


@@ -51,6 +55,26 @@ class CrunchyrollIE(InfoExtractor):
         '1080': ('80', '108'),
     }
 
         '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)
     def _decrypt_subtitles(self, data, iv, id):
         data = bytes_to_intlist(data)
         iv = bytes_to_intlist(iv)


@@ -85,18 +109,81 @@ class CrunchyrollIE(InfoExtractor):
         decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
         return zlib.decompress(decrypted_data)
 
         decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
         return zlib.decompress(decrypted_data)
 

-    def _convert_subtitles_to_srt(self, subtitles):
+    def _convert_subtitles_to_srt(self, sub_root):

         output = ''
         output = ''

-        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)
-            text = text.replace('\\N', '\n')
-            if not text:
-                continue
+
+        for i, event in enumerate(sub_root.findall('./events/event'), 1):
+            start = event.attrib['start'].replace('.', ',')
+            end = event.attrib['end'].replace('.', ',')
+            text = event.attrib['text'].replace('\\N', '\n')

             output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
         return output
 
             output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
         return output
 

+    def _convert_subtitles_to_ass(self, sub_root):
+        output = ''
+
+        def ass_bool(strvalue):
+            assvalue = '0'
+            if strvalue == '1':
+                assvalue = '-1'
+            return assvalue
+
+        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):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('video_id')
     def _real_extract(self,url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('video_id')


@@ -146,18 +233,21 @@ class CrunchyrollIE(InfoExtractor):
             streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+'&media%5Fid='+stream_id+'&video%5Fformat='+stream_format
             streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
             streamdata_req.add_header('Content-Length', str(len(streamdata_req.data)))
             streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+'&media%5Fid='+stream_id+'&video%5Fformat='+stream_format
             streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
             streamdata_req.add_header('Content-Length', str(len(streamdata_req.data)))

-            streamdata = self._download_webpage(streamdata_req, video_id, note='Downloading media info for '+video_format)
-            video_url = self._search_regex(r'<host>([^<]+)', streamdata, 'video_url')
-            video_play_path = self._search_regex(r'<file>([^<]+)', streamdata, 'video_play_path')
+            streamdata = self._download_xml(
+                streamdata_req, video_id,
+                note='Downloading media info for %s' % video_format)
+            video_url = streamdata.find('.//host').text
+            video_play_path = streamdata.find('.//file').text

             formats.append({
                 'url': video_url,
             formats.append({
                 'url': video_url,

-                'play_path':   video_play_path,
+                'play_path': video_play_path,

                 'ext': 'flv',
                 'format': video_format,
                 'format_id': video_format,
             })
 
         subtitles = {}
                 'ext': 'flv',
                 'format': video_format,
                 'format_id': video_format,
             })
 
         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)
         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)


@@ -174,7 +264,17 @@ class CrunchyrollIE(InfoExtractor):
             lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
             if not lang_code:
                 continue
             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)
+            sub_root = xml.etree.ElementTree.fromstring(subtitle)
+            if not sub_root:
+                subtitles[lang_code] = ''
+            if sub_format == 'ass':
+                subtitles[lang_code] = self._convert_subtitles_to_ass(sub_root)
+            else:
+                subtitles[lang_code] = self._convert_subtitles_to_srt(sub_root)
+
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(video_id, subtitles)
+            return

 
         return {
             'id':          video_id,
 
         return {
             'id':          video_id,


@@ -186,3 +286,40 @@ class CrunchyrollIE(InfoExtractor):
             'subtitles':   subtitles,
             'formats':     formats,
         }
             '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<id>[\w\-]+))/?$'
+
+    _TESTS = [{
+        'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
+        'info_dict': {
+            'id': 'a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
+            'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi'
+        },
+        'playlist_count': 13,
+    }]
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, show_id)
+        title = self._html_search_regex(
+            r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
+            webpage, 'title')
+        episode_paths = re.findall(
+            r'(?s)<li id="showview_videos_media_[0-9]+"[^>]+>.*?<a href="([^"]+)"',
+            webpage)
+        entries = [
+            self.url_result('http://www.crunchyroll.com' + ep, 'Crunchyroll')
+            for ep in episode_paths
+        ]
+        entries.reverse()
+
+        return {
+            '_type': 'playlist',
+            'id': show_id,
+            'title': title,
+            'entries': entries,
+        }