Merge pull request #8 from soimort/master

merge

src/you_get/common.py

@@ -235,7 +235,7 @@ def url_save(url, filepath, bar, refer = None, is_part = False, faker = False):
                 if bar:
                     bar.update_received(len(buffer))
     
-    assert received == os.path.getsize(temp_filepath), '%s == %s == %s' % (received, os.path.getsize(temp_filepath))
+    assert received == os.path.getsize(temp_filepath), '%s == %s == %s' % (received, os.path.getsize(temp_filepath), temp_filepath)
     
     if os.access(filepath, os.W_OK):
         os.remove(filepath) # on Windows rename could fail if destination filepath exists
@@ -444,8 +444,8 @@ def download_urls(urls, title, ext, total_size, output_dir = '.', refer = None,
             except:
                 from .processor.ffmpeg import has_ffmpeg_installed
                 if has_ffmpeg_installed():
-                    from .processor.ffmpeg import ffmpeg_concat_mp4_to_mpg
+                    from .processor.ffmpeg import ffmpeg_concat_mp4_to_mp4
-                    ffmpeg_concat_mp4_to_mpg(parts, os.path.join(output_dir, title + '.mp4'))
+                    ffmpeg_concat_mp4_to_mp4(parts, os.path.join(output_dir, title + '.mp4'))
                     for part in parts:
                         os.remove(part)
                 else:

src/you_get/downloader/mixcloud.py

@@ -7,9 +7,9 @@ from ..common import *
 def mixcloud_download(url, output_dir = '.', merge = True, info_only = False):
     html = get_html(url)
     title = r1(r'<meta property="og:title" content="([^"]*)"', html)
-    url = r1("data-preview-url=\"([^\"]+)\"", html)
+    preview_url = r1("data-preview-url=\"([^\"]+)\"", html)
     
-    url = re.sub(r'previews', r'cloudcasts/originals', url)
+    url = re.sub(r'previews', r'cloudcasts/originals', preview_url)
     for i in range(10, 30):
         url = re.sub(r'stream[^.]*', r'stream' + str(i), url)
         
@@ -19,6 +19,20 @@ def mixcloud_download(url, output_dir = '.', merge = True, info_only = False):
         except:
             continue
     
+    try:
+        type
+    except:
+        url = re.sub('cloudcasts/originals', r'cloudcasts/m4a/64', url)
+        url = re.sub('.mp3', '.m4a', url)
+        for i in range(10, 30):
+            url = re.sub(r'stream[^.]*', r'stream' + str(i), url)
+            
+            try:
+                type, ext, size = url_info(url)
+                break
+            except:
+                continue
+    
     print_info(site_info, title, type, size)
     if not info_only:
         download_urls([url], title, ext, size, output_dir, merge = merge)

src/you_get/downloader/tudou.py

@@ -22,12 +22,17 @@ def tudou_download_by_iid(iid, title, output_dir = '.', merge = True, info_only
         #url_save(url, filepath, bar):
         download_urls([url], title, ext, total_size = None, output_dir = output_dir, merge = merge)
 
-def tudou_download_by_id(id, title, output_dir = '.', merge = True):
+def tudou_download_by_id(id, title, output_dir = '.', merge = True, info_only = False):
     html = get_html('http://www.tudou.com/programs/view/%s/' % id)
-    iid = r1(r'iid\s*=\s*(\S+)', html)
+    iid = r1(r'iid\s*[:=]\s*(\S+)', html)
-    tudou_download_by_iid(iid, title, output_dir = output_dir, merge = merge)
+    tudou_download_by_iid(iid, title, output_dir = output_dir, merge = merge, info_only = info_only)
 
 def tudou_download(url, output_dir = '.', merge = True, info_only = False):
+    # Embedded player
+    id = r1(r'http://www.tudou.com/v/([^/]+)/', url)
+    if id:
+        return tudou_download_by_id(id, title="", info_only=info_only)
+    
     html = get_decoded_html(url)
     
     title = r1(r'kw\s*[:=]\s*[\'\"]([^\']+?)[\'\"]', html)

src/you_get/processor/ffmpeg.py

@@ -96,3 +96,31 @@ def ffmpeg_concat_flv_to_mp4(files, output = 'output.mp4'):
         return True
     else:
         raise
+
+def ffmpeg_concat_mp4_to_mp4(files, output = 'output.mp4'):
+    for file in files:
+        if os.path.isfile(file):
+            params = [FFMPEG, '-i']
+            params.append(file)
+            params += ['-c', 'copy', '-f', 'mpegts', '-bsf:v', 'h264_mp4toannexb']
+            params.append(file + '.ts')
+            
+            subprocess.call(params)
+    
+    params = [FFMPEG, '-i']
+    params.append('concat:')
+    for file in files:
+        f = file + '.ts'
+        if os.path.isfile(f):
+            params[-1] += f + '|'
+    if FFMPEG == 'avconv':
+        params += ['-c', 'copy', output]
+    else:
+        params += ['-c', 'copy', '-absf', 'aac_adtstoasc', output]
+    
+    if subprocess.call(params) == 0:
+        for file in files:
+            os.remove(file + '.ts')
+        return True
+    else:
+        raise

tests/test.py

@@ -19,7 +19,7 @@ class YouGetTests(unittest.TestCase):
         
     def test_jpopsuki(self):
         test_urls([
-            "http://jpopsuki.tv/video/Dragon-Ash---Run-to-the-Sun/8ad7aec604badd0b0798cd999b63ae17",
+            #"http://jpopsuki.tv/video/Dragon-Ash---Run-to-the-Sun/8ad7aec604badd0b0798cd999b63ae17",
         ])
         
     def test_mixcloud(self):