From df297c879434d5306afec95c9abdb39a7ba7e870 Mon Sep 17 00:00:00 2001 From: Sergey M․ Date: Sun, 27 Apr 2014 09:32:01 +0700 Subject: [http] Improve download mechanism when Range HTTP header is ignored --- youtube_dl/downloader/http.py | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/youtube_dl/downloader/http.py b/youtube_dl/downloader/http.py index cc8b9c9a7..7e1c1d715 100644 --- a/youtube_dl/downloader/http.py +++ b/youtube_dl/downloader/http.py @@ -14,6 +14,8 @@ from ..utils import ( class HttpFD(FileDownloader): + _TEST_FILE_SIZE = 10241 + def real_download(self, filename, info_dict): url = info_dict['url'] tmpfilename = self.temp_name(filename) @@ -28,8 +30,10 @@ class HttpFD(FileDownloader): 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') + 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)): @@ -100,6 +104,15 @@ class HttpFD(FileDownloader): 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 > 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) @@ -118,7 +131,7 @@ class HttpFD(FileDownloader): 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 @@ -162,6 +175,9 @@ class HttpFD(FileDownloader): 'speed': speed, }) + if is_test and byte_counter == data_len: + break + # Apply rate limit self.slow_down(start, byte_counter - resume_len) -- cgit v1.2.3