diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2013-06-23 20:55:15 +0200 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2013-06-23 20:55:15 +0200 |
commit | 7aca14a1ec9d92599b8871540cfde2dc8225eb8d (patch) | |
tree | a1df9fca9d554addc4e288a26264e153285e0160 /youtube_dl/InfoExtractors.py | |
parent | d1596ef439d208017d1e425dfd752a111b303869 (diff) |
Move G+ IE into its own file, and move google search into a more descriptive module
Diffstat (limited to 'youtube_dl/InfoExtractors.py')
-rwxr-xr-x | youtube_dl/InfoExtractors.py | 76 |
1 files changed, 2 insertions, 74 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 7c253bf9f..ca1e43404 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -25,7 +25,8 @@ from .extractor.comedycentral import ComedyCentralIE from .extractor.dailymotion import DailymotionIE from .extractor.gametrailers import GametrailersIE from .extractor.generic import GenericIE -from .extractor.google import GoogleSearchIE +from .extractor.googleplus import GooglePlusIE +from .extractor.googlesearch import GoogleSearchIE from .extractor.metacafe import MetacafeIE from .extractor.myvideo import MyVideoIE from .extractor.statigram import StatigramIE @@ -926,79 +927,6 @@ class XNXXIE(InfoExtractor): }] -class GooglePlusIE(InfoExtractor): - """Information extractor for plus.google.com.""" - - _VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)' - IE_NAME = u'plus.google' - - def _real_extract(self, url): - # Extract id from URL - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - - post_url = mobj.group(0) - video_id = mobj.group(1) - - video_extension = 'flv' - - # Step 1, Retrieve post webpage to extract further information - webpage = self._download_webpage(post_url, video_id, u'Downloading entry webpage') - - self.report_extraction(video_id) - - # Extract update date - upload_date = self._html_search_regex('title="Timestamp">(.*?)</a>', - webpage, u'upload date', fatal=False) - if upload_date: - # Convert timestring to a format suitable for filename - upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d") - upload_date = upload_date.strftime('%Y%m%d') - - # Extract uploader - uploader = self._html_search_regex(r'rel\="author".*?>(.*?)</a>', - webpage, u'uploader', fatal=False) - - # Extract title - # Get the first line for title - video_title = self._html_search_regex(r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]', - webpage, 'title', default=u'NA') - - # Step 2, Stimulate clicking the image box to launch video - video_page = self._search_regex('"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]', - webpage, u'video page URL') - webpage = self._download_webpage(video_page, video_id, u'Downloading video page') - - # Extract video links on video page - """Extract video links of all sizes""" - pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"' - mobj = re.findall(pattern, webpage) - if len(mobj) == 0: - raise ExtractorError(u'Unable to extract video links') - - # Sort in resolution - links = sorted(mobj) - - # Choose the lowest of the sort, i.e. highest resolution - video_url = links[-1] - # Only get the url. The resolution part in the tuple has no use anymore - video_url = video_url[-1] - # Treat escaped \u0026 style hex - try: - video_url = video_url.decode("unicode_escape") - except AttributeError: # Python 3 - video_url = bytes(video_url, 'ascii').decode('unicode-escape') - - - return [{ - 'id': video_id, - 'url': video_url, - 'uploader': uploader, - 'upload_date': upload_date, - 'title': video_title, - 'ext': video_extension, - }] class NBAIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.html)?(?:\?.*)?$' |