Tidy up cleanup rule and keep lintian happy.

[youtubedl] / youtube_dl / extractor / crunchyroll.py

diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py
index c7032ffa220dc94f7f7b0e419d56b43d38d6c7ba..6d3abb52f735de655e11ce88c70a4b6b9cc287d6 100644 (file)
--- a/youtube_dl/extractor/crunchyroll.py
+++ b/youtube_dl/extractor/crunchyroll.py
@@ -11,8 +11,7 @@ from math import pow, sqrt, floor
 from .common import InfoExtractor
 from ..compat import (
     compat_etree_fromstring,
 from .common import InfoExtractor
 from ..compat import (
     compat_etree_fromstring,

-    compat_urllib_parse,
-    compat_urllib_parse_unquote,
+    compat_urllib_parse_urlencode,

     compat_urllib_request,
     compat_urlparse,
 )
     compat_urllib_request,
     compat_urlparse,
 )


@@ -27,6 +26,7 @@ from ..utils import (
     unified_strdate,
     urlencode_postdata,
     xpath_text,
     unified_strdate,
     urlencode_postdata,
     xpath_text,

+    extract_attributes,

 )
 from ..aes import (
     aes_cbc_decrypt,
 )
 from ..aes import (
     aes_cbc_decrypt,


@@ -54,7 +54,7 @@ class CrunchyrollBaseIE(InfoExtractor):
     def _real_initialize(self):
         self._login()
 
     def _real_initialize(self):
         self._login()
 

-    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None):
+    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
         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


@@ -65,8 +65,7 @@ class CrunchyrollBaseIE(InfoExtractor):
         # 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', '*')
         # 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, video_id, note, errnote, fatal, tries, timeout, encoding)
+        return super(CrunchyrollBaseIE, self)._download_webpage(request, *args, **kwargs)

 
     @staticmethod
     def _add_skip_wall(url):
 
     @staticmethod
     def _add_skip_wall(url):


@@ -79,7 +78,7 @@ class CrunchyrollBaseIE(InfoExtractor):
         # See https://github.com/rg3/youtube-dl/issues/7202.
         qs['skip_wall'] = ['1']
         return compat_urlparse.urlunparse(
         # See https://github.com/rg3/youtube-dl/issues/7202.
         qs['skip_wall'] = ['1']
         return compat_urlparse.urlunparse(

-            parsed_url._replace(query=compat_urllib_parse.urlencode(qs, True)))
+            parsed_url._replace(query=compat_urllib_parse_urlencode(qs, True)))

 
 
 class CrunchyrollIE(CrunchyrollBaseIE):
 
 
 class CrunchyrollIE(CrunchyrollBaseIE):


@@ -115,6 +114,21 @@ class CrunchyrollIE(CrunchyrollBaseIE):
             # rtmp
             'skip_download': True,
         },
             # rtmp
             'skip_download': True,
         },

+    }, {
+        'url': 'http://www.crunchyroll.com/rezero-starting-life-in-another-world-/episode-5-the-morning-of-our-promise-is-still-distant-702409',
+        'info_dict': {
+            'id': '702409',
+            'ext': 'mp4',
+            'title': 'Re:ZERO -Starting Life in Another World- Episode 5 – The Morning of Our Promise Is Still Distant',
+            'description': 'md5:97664de1ab24bbf77a9c01918cb7dca9',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'TV TOKYO',
+            'upload_date': '20160508',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },

     }, {
         'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
         'only_matching': True,
     }, {
         'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
         'only_matching': True,


@@ -307,31 +321,48 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', webpage,
             'video_uploader', fatal=False)
 
             r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', webpage,
             'video_uploader', fatal=False)
 

-        playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
-        playerdata_req = sanitized_Request(playerdata_url)
-        playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url})
-        playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        playerdata = self._download_webpage(playerdata_req, video_id, note='Downloading media info')
-
-        stream_id = self._search_regex(r'<media_id>([^<]+)', playerdata, 'stream_id')
-        video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False)
-
+        available_fmts = []
+        for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage):
+            attrs = extract_attributes(a)
+            href = attrs.get('href')
+            if href and '/freetrial' in href:
+                continue
+            available_fmts.append(fmt)
+        if not available_fmts:
+            for p in (r'token=["\']showmedia\.([0-9]{3,4})p"', r'showmedia\.([0-9]{3,4})p'):
+                available_fmts = re.findall(p, webpage)
+                if available_fmts:
+                    break
+        video_encode_ids = []

         formats = []
         formats = []

-        for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage):
+        for fmt in available_fmts:

             stream_quality, stream_format = self._FORMAT_IDS[fmt]
             video_format = fmt + 'p'
             streamdata_req = sanitized_Request(
                 'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'
             stream_quality, stream_format = self._FORMAT_IDS[fmt]
             video_format = fmt + 'p'
             streamdata_req = sanitized_Request(
                 'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'

-                % (stream_id, stream_format, stream_quality),
-                compat_urllib_parse.urlencode({'current_page': url}).encode('utf-8'))
+                % (video_id, stream_format, stream_quality),
+                compat_urllib_parse_urlencode({'current_page': url}).encode('utf-8'))

             streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
             streamdata = self._download_xml(
                 streamdata_req, video_id,
                 note='Downloading media info for %s' % video_format)
             stream_info = streamdata.find('./{default}preload/stream_info')
             streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
             streamdata = self._download_xml(
                 streamdata_req, video_id,
                 note='Downloading media info for %s' % video_format)
             stream_info = streamdata.find('./{default}preload/stream_info')

+            video_encode_id = xpath_text(stream_info, './video_encode_id')
+            if video_encode_id in video_encode_ids:
+                continue
+            video_encode_ids.append(video_encode_id)
+
+            video_file = xpath_text(stream_info, './file')
+            if not video_file:
+                continue
+            if video_file.startswith('http'):
+                formats.extend(self._extract_m3u8_formats(
+                    video_file, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+                continue
+

             video_url = xpath_text(stream_info, './host')
             video_url = xpath_text(stream_info, './host')

-            video_play_path = xpath_text(stream_info, './file')
-            if not video_url or not video_play_path:
+            if not video_url:

                 continue
             metadata = stream_info.find('./metadata')
             format_info = {
                 continue
             metadata = stream_info.find('./metadata')
             format_info = {


@@ -346,7 +377,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                 parsed_video_url = compat_urlparse.urlparse(video_url)
                 direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace(
                     netloc='v.lvlt.crcdn.net',
                 parsed_video_url = compat_urlparse.urlparse(video_url)
                 direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace(
                     netloc='v.lvlt.crcdn.net',

-                    path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_play_path.split(':')[-1])))
+                    path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_file.split(':')[-1])))

                 if self._is_valid_url(direct_video_url, video_id, video_format):
                     format_info.update({
                         'url': direct_video_url,
                 if self._is_valid_url(direct_video_url, video_id, video_format):
                     format_info.update({
                         'url': direct_video_url,


@@ -356,10 +387,18 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
             format_info.update({
                 'url': video_url,
 
             format_info.update({
                 'url': video_url,

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

                 'ext': 'flv',
             })
             formats.append(format_info)
                 'ext': 'flv',
             })
             formats.append(format_info)

+        self._sort_formats(formats)
+
+        metadata = self._download_xml(
+            'http://www.crunchyroll.com/xml', video_id,
+            note='Downloading media info', query={
+                'req': 'RpcApiVideoPlayer_GetMediaMetadata',
+                'media_id': video_id,
+            })

 
         subtitles = self.extract_subtitles(video_id, webpage)
 
 
         subtitles = self.extract_subtitles(video_id, webpage)
 


@@ -367,9 +406,12 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             'id': video_id,
             'title': video_title,
             'description': video_description,
             'id': video_id,
             'title': video_title,
             'description': video_description,

-            'thumbnail': video_thumbnail,
+            'thumbnail': xpath_text(metadata, 'episode_image_url'),

             'uploader': video_uploader,
             'upload_date': video_upload_date,
             'uploader': video_uploader,
             'upload_date': video_upload_date,

+            'series': xpath_text(metadata, 'series_title'),
+            'episode': xpath_text(metadata, 'episode_title'),
+            'episode_number': int_or_none(xpath_text(metadata, 'episode_number')),

             'subtitles': subtitles,
             'formats': formats,
         }
             'subtitles': subtitles,
             'formats': formats,
         }