Merge tag 'upstream/2014.10.30'

[youtubedl] / youtube_dl / downloader / http.py

diff --git a/youtube_dl/downloader/http.py b/youtube_dl/downloader/http.py
index 748f9f3adfe0555024cce272b8eb872c55558d6c..f62555ce0e33353f5eac848e3956b263f9d43bcb 100644 (file)
--- a/youtube_dl/downloader/http.py
+++ b/youtube_dl/downloader/http.py
@@ -23,11 +23,23 @@ class HttpFD(FileDownloader):
         headers = {'Youtubedl-no-compression': 'True'}
         if 'user_agent' in info_dict:
             headers['Youtubedl-user-agent'] = info_dict['user_agent']
         headers = {'Youtubedl-no-compression': 'True'}
         if 'user_agent' in info_dict:
             headers['Youtubedl-user-agent'] = info_dict['user_agent']

-        basic_request = compat_urllib_request.Request(url, None, headers)
-        request = compat_urllib_request.Request(url, None, headers)
-
-        if self.params.get('test', False):
-            request.add_header('Range', 'bytes=0-10240')
+        if 'http_referer' in info_dict:
+            headers['Referer'] = info_dict['http_referer']
+        add_headers = info_dict.get('http_headers')
+        if add_headers:
+            headers.update(add_headers)
+        data = info_dict.get('http_post_data')
+        http_method = info_dict.get('http_method')
+        basic_request = compat_urllib_request.Request(url, data, headers)
+        request = compat_urllib_request.Request(url, data, headers)
+        if http_method is not None:
+            basic_request.get_method = lambda: http_method
+            request.get_method = lambda: http_method
+
+        is_test = self.params.get('test', False)
+
+        if is_test:
+            request.add_header('Range', 'bytes=0-%s' % str(self._TEST_FILE_SIZE - 1))

 
         # Establish possible resume length
         if os.path.isfile(encodeFilename(tmpfilename)):
 
         # Establish possible resume length
         if os.path.isfile(encodeFilename(tmpfilename)):


@@ -49,7 +61,7 @@ class HttpFD(FileDownloader):
         while count <= retries:
             # Establish connection
             try:
         while count <= retries:
             # Establish connection
             try:

-                data = compat_urllib_request.urlopen(request)
+                data = self.ydl.urlopen(request)

                 break
             except (compat_urllib_error.HTTPError, ) as err:
                 if (err.code < 500 or err.code >= 600) and err.code != 416:
                 break
             except (compat_urllib_error.HTTPError, ) as err:
                 if (err.code < 500 or err.code >= 600) and err.code != 416:


@@ -59,7 +71,7 @@ class HttpFD(FileDownloader):
                     # Unable to resume (requested range not satisfiable)
                     try:
                         # Open the connection again without the range header
                     # Unable to resume (requested range not satisfiable)
                     try:
                         # Open the connection again without the range header

-                        data = compat_urllib_request.urlopen(basic_request)
+                        data = self.ydl.urlopen(basic_request)

                         content_length = data.info()['Content-Length']
                     except (compat_urllib_error.HTTPError, ) as err:
                         if err.code < 500 or err.code >= 600:
                         content_length = data.info()['Content-Length']
                     except (compat_urllib_error.HTTPError, ) as err:
                         if err.code < 500 or err.code >= 600:


@@ -85,6 +97,7 @@ class HttpFD(FileDownloader):
                         else:
                             # The length does not match, we start the download over
                             self.report_unable_to_resume()
                         else:
                             # The length does not match, we start the download over
                             self.report_unable_to_resume()

+                            resume_len = 0

                             open_mode = 'wb'
                             break
             # Retry
                             open_mode = 'wb'
                             break
             # Retry


@@ -97,6 +110,15 @@ class HttpFD(FileDownloader):
             return False
 
         data_len = data.info().get('Content-length', None)
             return False
 
         data_len = data.info().get('Content-length', None)

+
+        # Range HTTP header may be ignored/unsupported by a webserver
+        # (e.g. extractor/scivee.py, extractor/bambuser.py).
+        # However, for a test we still would like to download just a piece of a file.
+        # To achieve this we limit data_len to _TEST_FILE_SIZE and manually control
+        # block size when downloading a file.
+        if is_test and (data_len is None or int(data_len) > self._TEST_FILE_SIZE):
+            data_len = self._TEST_FILE_SIZE
+

         if data_len is not None:
             data_len = int(data_len) + resume_len
             min_data_len = self.params.get("min_filesize", None)
         if data_len is not None:
             data_len = int(data_len) + resume_len
             min_data_len = self.params.get("min_filesize", None)


@@ -115,7 +137,7 @@ class HttpFD(FileDownloader):
         while True:
             # Download and write
             before = time.time()
         while True:
             # Download and write
             before = time.time()

-            data_block = data.read(block_size)
+            data_block = data.read(block_size if not is_test else min(block_size, data_len - byte_counter))

             after = time.time()
             if len(data_block) == 0:
                 break
             after = time.time()
             if len(data_block) == 0:
                 break


@@ -159,6 +181,9 @@ class HttpFD(FileDownloader):
                 'speed': speed,
             })
 
                 'speed': speed,
             })
 

+            if is_test and byte_counter == data_len:
+                break
+

             # Apply rate limit
             self.slow_down(start, byte_counter - resume_len)
 
             # Apply rate limit
             self.slow_down(start, byte_counter - resume_len)
 


@@ -166,7 +191,8 @@ class HttpFD(FileDownloader):
             self.to_stderr(u"\n")
             self.report_error(u'Did not get any data blocks')
             return False
             self.to_stderr(u"\n")
             self.report_error(u'Did not get any data blocks')
             return False

-        stream.close()
+        if tmpfilename != u'-':
+            stream.close()

         self.report_finish(data_len_str, (time.time() - start))
         if data_len is not None and byte_counter != data_len:
             raise ContentTooShortError(byte_counter, int(data_len))
         self.report_finish(data_len_str, (time.time() - start))
         if data_len is not None and byte_counter != data_len:
             raise ContentTooShortError(byte_counter, int(data_len))