X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Fextractor%2Fcamdemy.py;h=6ffbeabd371fd6f80a9ead1d23762f760a13ba2f;hb=daa0df9e8beac1325e5fb55d828e7a3a38e74bf6;hp=9a6341f0f6e3595ffc4764870da0b0dfcc91a583;hpb=8367d3f3cbad7ddae5116c3cd5d39ebfed9711c5;p=youtube-dl

diff --git a/youtube_dl/extractor/camdemy.py b/youtube_dl/extractor/camdemy.py
index 9a6341f0f..6ffbeabd3 100644
--- a/youtube_dl/extractor/camdemy.py
+++ b/youtube_dl/extractor/camdemy.py
@@ -1,15 +1,22 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import datetime
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
-from ..utils import parse_iso8601
+from ..compat import (
+    compat_urllib_parse_urlencode,
+    compat_urlparse,
+)
+from ..utils import (
+    parse_iso8601,
+    str_to_int,
+)
 
 
 class CamdemyIE(InfoExtractor):
-    _VALID_URL = r'http://www.camdemy.com/media/(?P<id>\d+).*'
+    _VALID_URL = r'https?://(?:www\.)?camdemy\.com/media/(?P<id>\d+)'
     _TESTS = [{
         # single file
         'url': 'http://www.camdemy.com/media/5181/',
@@ -23,6 +30,7 @@ class CamdemyIE(InfoExtractor):
             'creator': 'ss11spring',
             'upload_date': '20130114',
             'timestamp': 1358154556,
+            'view_count': int,
         }
     }, {
         # With non-empty description
@@ -55,44 +63,91 @@ class CamdemyIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
         page = self._download_webpage(url, video_id)
 
-        srcFrom = self._html_search_regex(
+        src_from = self._html_search_regex(
             r"<div class='srcFrom'>Source: <a title='([^']+)'", page,
             'external source', default=None)
-
-        if srcFrom:
-            return self.url_result(srcFrom)
+        if src_from:
+            return self.url_result(src_from)
 
         oembed_obj = self._download_json(
             'http://www.camdemy.com/oembed/?format=json&url=' + url, video_id)
 
         thumb_url = oembed_obj['thumbnail_url']
         video_folder = compat_urlparse.urljoin(thumb_url, 'video/')
-        fileListXML = self._download_xml(
+        file_list_doc = self._download_xml(
             compat_urlparse.urljoin(video_folder, 'fileList.xml'),
             video_id, 'Filelist XML')
-        fileName = fileListXML.find('./video/item/fileName').text
-
-        creation_time = self._html_search_regex(
-            r"<div class='title'>Posted :</div>.*<div class='value'>([0-9:\- ]+)<",
-            page, 'creation time', flags=re.MULTILINE | re.DOTALL) + '+08:00'
-        creation_timestamp = parse_iso8601(creation_time, delimiter=' ')
+        file_name = file_list_doc.find('./video/item/fileName').text
+        video_url = compat_urlparse.urljoin(video_folder, file_name)
 
-        view_count_str = self._html_search_regex(
-            r"<div class='title'>Views :</div>.*<div class='value'>([0-9,]+)<",
-            page, 'view count', flags=re.MULTILINE | re.DOTALL)
-        views = int(view_count_str.replace(',', ''))
+        timestamp = parse_iso8601(self._html_search_regex(
+            r"<div class='title'>Posted\s*:</div>\s*<div class='value'>([^<>]+)<",
+            page, 'creation time', fatal=False),
+            delimiter=' ', timezone=datetime.timedelta(hours=8))
+        view_count = str_to_int(self._html_search_regex(
+            r"<div class='title'>Views\s*:</div>\s*<div class='value'>([^<>]+)<",
+            page, 'view count', fatal=False))
 
         return {
             'id': video_id,
-            'url': compat_urlparse.urljoin(video_folder, fileName),
+            'url': video_url,
             'title': oembed_obj['title'],
             'thumbnail': thumb_url,
             'description': self._html_search_meta('description', page),
             'creator': oembed_obj['author_name'],
             'duration': oembed_obj['duration'],
-            'timestamp': creation_timestamp,
-            'view_count': views,
+            'timestamp': timestamp,
+            'view_count': view_count,
         }
+
+
+class CamdemyFolderIE(InfoExtractor):
+    _VALID_URL = r'https?://www.camdemy.com/folder/(?P<id>\d+)'
+    _TESTS = [{
+        # links with trailing slash
+        'url': 'http://www.camdemy.com/folder/450',
+        'info_dict': {
+            'id': '450',
+            'title': '信號與系統 2012 & 2011 (Signals and Systems)',
+        },
+        'playlist_mincount': 145
+    }, {
+        # links without trailing slash
+        # and multi-page
+        'url': 'http://www.camdemy.com/folder/853',
+        'info_dict': {
+            'id': '853',
+            'title': '科學計算 - 使用 Matlab'
+        },
+        'playlist_mincount': 20
+    }, {
+        # with displayMode parameter. For testing the codes to add parameters
+        'url': 'http://www.camdemy.com/folder/853/?displayMode=defaultOrderByOrg',
+        'info_dict': {
+            'id': '853',
+            'title': '科學計算 - 使用 Matlab'
+        },
+        'playlist_mincount': 20
+    }]
+
+    def _real_extract(self, url):
+        folder_id = self._match_id(url)
+
+        # Add displayMode=list so that all links are displayed in a single page
+        parsed_url = list(compat_urlparse.urlparse(url))
+        query = dict(compat_urlparse.parse_qsl(parsed_url[4]))
+        query.update({'displayMode': 'list'})
+        parsed_url[4] = compat_urllib_parse_urlencode(query)
+        final_url = compat_urlparse.urlunparse(parsed_url)
+
+        page = self._download_webpage(final_url, folder_id)
+        matches = re.findall(r"href='(/media/\d+/?)'", page)
+
+        entries = [self.url_result('http://www.camdemy.com' + media_path)
+                   for media_path in matches]
+
+        folder_title = self._html_search_meta('keywords', page)
+
+        return self.playlist_result(entries, folder_id, folder_title)