import datetime import re from .common import InfoExtractor from ..utils import ( ExtractorError, ) 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">(.*?)', 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".*?>(.*?)', webpage, u'uploader', fatal=False) # Extract title # Get the first line for title video_title = self._html_search_regex(r'