Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-13 14:37:43 +01:00
Code Issues Packages Projects Releases Wiki Activity

youtube IE: Correct bytes vs str

Browse Source
This commit is contained in:
Philipp Hagemeister 2012-11-28 00:31:59 +01:00
parent 5bd9cc7a6a
commit 72f976701a
1 changed files with 17 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
youtube_dl/InfoExtractors.py
View File

@ -308,11 +308,13 @@ def _real_extract(self, url):
self.report_video_webpage_download(video_id) self.report_video_webpage_download(video_id)
request = compat_urllib_request.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id) request = compat_urllib_request.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
try: try:
video_webpage = compat_urllib_request.urlopen(request).read() video_webpage_bytes = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
return return
video_webpage = video_webpage_bytes.decode('utf-8', 'ignore')
# Attempt to extract SWF player URL # Attempt to extract SWF player URL
mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
if mobj is not None: if mobj is not None:
@ -327,7 +329,8 @@ def _real_extract(self, url):
% (video_id, el_type)) % (video_id, el_type))
request = compat_urllib_request.Request(video_info_url) request = compat_urllib_request.Request(video_info_url)
try: try:
video_info_webpage = compat_urllib_request.urlopen(request).read() video_info_webpage_bytes = compat_urllib_request.urlopen(request).read()
video_info_webpage = video_info_webpage_bytes.decode('utf-8', 'ignore')
video_info = compat_parse_qs(video_info_webpage) video_info = compat_parse_qs(video_info_webpage)
if 'token' in video_info: if 'token' in video_info:
break break
@ -360,7 +363,6 @@ def _real_extract(self, url):
self._downloader.trouble(u'ERROR: unable to extract video title') self._downloader.trouble(u'ERROR: unable to extract video title')
return return
video_title = compat_urllib_parse.unquote_plus(video_info['title'][0]) video_title = compat_urllib_parse.unquote_plus(video_info['title'][0])
video_title = video_title.decode('utf-8')
# thumbnail image # thumbnail image
if 'thumbnail_url' not in video_info: if 'thumbnail_url' not in video_info:
@ -382,10 +384,12 @@ def _real_extract(self, url):
pass pass
# description # description
video_description = get_element_by_id("eow-description", video_webpage.decode('utf8')) video_description = get_element_by_id("eow-description", video_webpage)
if video_description: video_description = clean_html(video_description) if video_description:
else: video_description = '' video_description = clean_html(video_description)
else:
video_description = ''
# closed captions # closed captions
video_subtitles = None video_subtitles = None
if self._downloader.params.get('writesubtitles', False): if self._downloader.params.get('writesubtitles', False):
@ -480,18 +484,18 @@ def _real_extract(self, url):
# Extension # Extension
video_extension = self._video_extensions.get(format_param, 'flv') video_extension = self._video_extensions.get(format_param, 'flv')
video_format = '{} - {}'.format(format_param.decode('utf-8') if format_param else video_extension.decode('utf-8'), video_format = '{} - {}'.format(format_param if format_param else video_extension,
self._video_dimensions.get(format_param, '???')) self._video_dimensions.get(format_param, '???'))
results.append({ results.append({
'id': video_id.decode('utf-8'), 'id': video_id,
'url': video_real_url.decode('utf-8'), 'url': video_real_url,
'uploader': video_uploader.decode('utf-8'), 'uploader': video_uploader,
'upload_date': upload_date, 'upload_date': upload_date,
'title': video_title, 'title': video_title,
'ext': video_extension.decode('utf-8'), 'ext': video_extension,
'format': video_format, 'format': video_format,
'thumbnail': video_thumbnail.decode('utf-8'), 'thumbnail': video_thumbnail,
'description': video_description, 'description': video_description,
'player_url': player_url, 'player_url': player_url,
'subtitles': video_subtitles, 'subtitles': video_subtitles,