Imported Upstream version 2015.02.06

[youtubedl] / youtube_dl / extractor / niconico.py

diff --git a/youtube_dl/extractor/niconico.py b/youtube_dl/extractor/niconico.py
index c0c139b5df16ce900ba6920a1a004bc433eab4e9..4c18904169d3f69a0bf7e95fb21d98218bca7e91 100644 (file)
--- a/youtube_dl/extractor/niconico.py
+++ b/youtube_dl/extractor/niconico.py
@@ -2,15 +2,19 @@
 from __future__ import unicode_literals
 
 import re
 from __future__ import unicode_literals
 
 import re

+import json

 
 from .common import InfoExtractor
 
 from .common import InfoExtractor

-from ..utils import (
+from ..compat import (

     compat_urllib_parse,
     compat_urllib_request,
     compat_urlparse,
     compat_urllib_parse,
     compat_urllib_request,
     compat_urlparse,

-    unified_strdate,
-    parse_duration,
+)
+from ..utils import (
+    ExtractorError,

     int_or_none,
     int_or_none,

+    parse_duration,
+    unified_strdate,

 )
 
 
 )
 
 


@@ -39,18 +43,17 @@ class NiconicoIE(InfoExtractor):
 
     _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/((?:[a-z]{2})?[0-9]+)'
     _NETRC_MACHINE = 'niconico'
 
     _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/((?:[a-z]{2})?[0-9]+)'
     _NETRC_MACHINE = 'niconico'

-    # Determine whether the downloader uses authentication to download video
-    _AUTHENTICATE = False
+    # Determine whether the downloader used authentication to download video
+    _AUTHENTICATED = False

 
     def _real_initialize(self):
 
     def _real_initialize(self):

-        if self._downloader.params.get('username', None) is not None:
-            self._AUTHENTICATE = True
-
-        if self._AUTHENTICATE:
-            self._login()
+        self._login()

 
     def _login(self):
         (username, password) = self._get_login_info()
 
     def _login(self):
         (username, password) = self._get_login_info()

+        # No authentication to be performed
+        if not username:
+            return True

 
         # Log in
         login_form_strs = {
 
         # Log in
         login_form_strs = {


@@ -68,6 +71,8 @@ class NiconicoIE(InfoExtractor):
         if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None:
             self._downloader.report_warning('unable to log in: bad username or password')
             return False
         if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None:
             self._downloader.report_warning('unable to log in: bad username or password')
             return False

+        # Successful login
+        self._AUTHENTICATED = True

         return True
 
     def _real_extract(self, url):
         return True
 
     def _real_extract(self, url):


@@ -82,7 +87,7 @@ class NiconicoIE(InfoExtractor):
             'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
             note='Downloading video info page')
 
             'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
             note='Downloading video info page')
 

-        if self._AUTHENTICATE:
+        if self._AUTHENTICATED:

             # Get flv info
             flv_info_webpage = self._download_webpage(
                 'http://flapi.nicovideo.jp/api/getflv?v=' + video_id,
             # Get flv info
             flv_info_webpage = self._download_webpage(
                 'http://flapi.nicovideo.jp/api/getflv?v=' + video_id,


@@ -106,6 +111,9 @@ class NiconicoIE(InfoExtractor):
                 flv_info_request, video_id,
                 note='Downloading flv info', errnote='Unable to download flv info')
 
                 flv_info_request, video_id,
                 note='Downloading flv info', errnote='Unable to download flv info')
 

+        if 'deleted=' in flv_info_webpage:
+            raise ExtractorError('The video has been deleted.',
+                                 expected=True)

         video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0]
 
         # Start extracting information
         video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0]
 
         # Start extracting information


@@ -145,3 +153,37 @@ class NiconicoIE(InfoExtractor):
             'duration': duration,
             'webpage_url': webpage_url,
         }
             'duration': duration,
             'webpage_url': webpage_url,
         }

+
+
+class NiconicoPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.nicovideo\.jp/mylist/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.nicovideo.jp/mylist/27411728',
+        'info_dict': {
+            'id': '27411728',
+            'title': 'AKB48のオールナイトニッポン',
+        },
+        'playlist_mincount': 225,
+    }
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+        webpage = self._download_webpage(url, list_id)
+
+        entries_json = self._search_regex(r'Mylist\.preload\(\d+, (\[.*\])\);',
+                                          webpage, 'entries')
+        entries = json.loads(entries_json)
+        entries = [{
+            '_type': 'url',
+            'ie_key': NiconicoIE.ie_key(),
+            'url': ('http://www.nicovideo.jp/watch/%s' %
+                    entry['item_data']['video_id']),
+        } for entry in entries]
+
+        return {
+            '_type': 'playlist',
+            'title': self._search_regex(r'\s+name: "(.*?)"', webpage, 'title'),
+            'id': list_id,
+            'entries': entries,
+        }