From 3d3423574d35a0fe71062f21dd57ada02a5225b4 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Fri, 8 Mar 2013 20:47:06 +0100 Subject: [PATCH] Fix Unicode handling GenericIE (Fixes #734) --- test/tests.json | 6 ++++++ youtube_dl/InfoExtractors.py | 10 +++------- 2 files changed, 9 insertions(+), 7 deletions(-) diff --git a/test/tests.json b/test/tests.json index 7af3c28929..e4ea0b41e7 100644 --- a/test/tests.json +++ b/test/tests.json @@ -293,5 +293,11 @@ "info_dict": { "title": "Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2" } + }, + { + "name": "Generic", + "url": "http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html", + "file": "13601338388002.mp4", + "md5": "85b90ccc9d73b4acd9138d3af4c27f89" } ] diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 6b03bf3075..baba4a9a2f 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -1281,7 +1281,8 @@ def __init__(self, downloader=None): def report_download_webpage(self, video_id): """Report webpage download.""" - self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.') + if not self._downloader.params.get('test', False): + self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.') self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id) def report_extraction(self, video_id): @@ -1351,13 +1352,8 @@ def _real_extract(self, url): if self._test_redirect(url): return video_id = url.split('/')[-1] - request = compat_urllib_request.Request(url) try: - self.report_download_webpage(video_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) - return + webpage = self._download_webpage(url, video_id) except ValueError as err: # since this is the last-resort InfoExtractor, if # this error is thrown, it'll be thrown here