Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-22 16:44:32 +01:00
Code Issues Releases Wiki Activity

Misc justin.tv fixes

Browse Source
This commit is contained in:
Dave Vasilevsky 2012-12-16 04:45:46 -05:00
parent 2ab1c5ed1a
commit 4096b60948
1 changed files with 13 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
youtube_dl/InfoExtractors.py
View File

@ -3641,21 +3641,22 @@ class JustinTVIE(InfoExtractor):
# 'broadcast_id' is the same for all parts, and 'broadcast_part' # 'broadcast_id' is the same for all parts, and 'broadcast_part'
# starts at 1 and increases. Can we treat all parts as one video? # starts at 1 and increases. Can we treat all parts as one video?
# _VALID_URL = r"""^(?:http(?:s?)://)?www\.(?:justin|twitch)\.tv/ _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?(?:twitch|justin)\.tv/
# ([^/]+)(?:/b/([^/]+))?/?(?:#.*)?$""" ([^/]+)(?:/b/([^/]+))?/?(?:\#.*)?$"""
_VALID_URL = r'^http://www.twitch.tv/(.*)$' _JUSTIN_PAGE_LIMIT = 100
IE_NAME = u'justin.tv' IE_NAME = u'justin.tv'
_max_justin_results = 1000
_justin_page_limit = 100
def report_extraction(self, file_id): def report_extraction(self, file_id):
"""Report information extraction.""" """Report information extraction."""
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
def report_download_page(self, channel, offset):
"""Report attempt to download a single page of videos."""
self._downloader.to_screen(u'[%s] %s: Downloading video information from %d to %d' %
(self.IE_NAME, channel, offset, offset + self._JUSTIN_PAGE_LIMIT))
# Return count of items, list of *valid* items # Return count of items, list of *valid* items
def _parse_page(self, url): def _parse_page(self, url):
print url
try: try:
urlh = compat_urllib_request.urlopen(url) urlh = compat_urllib_request.urlopen(url)
webpage_bytes = urlh.read() webpage_bytes = urlh.read()
@ -3675,11 +3676,10 @@ class JustinTVIE(InfoExtractor):
'id': clip['id'], 'id': clip['id'],
'url': video_url, 'url': video_url,
'title': clip['title'], 'title': clip['title'],
'uploader': clip['user_id'] or clip['channel_id'], 'uploader': clip.get('user_id', clip.get('channel_id')),
'upload_date': video_date, 'upload_date': video_date,
'ext': video_extension, 'ext': video_extension,
}) })
print len(response)
return (len(response), info) return (len(response), info)
def _real_extract(self, url): def _real_extract(self, url):
@ -3702,8 +3702,10 @@ class JustinTVIE(InfoExtractor):
info = [] info = []
offset = 0 offset = 0
limit = self._justin_page_limit limit = self._JUSTIN_PAGE_LIMIT
while offset < self._max_justin_results: while True:
if paged:
self.report_download_page(video_id, offset)
page_url = api + ('?offset=%d&limit=%d' % (offset, limit)) page_url = api + ('?offset=%d&limit=%d' % (offset, limit))
page_count, page_info = self._parse_page(page_url) page_count, page_info = self._parse_page(page_url)
info.extend(page_info) info.extend(page_info)