From d443aca86345508d3a8aa7a1c951fefc25f3dfcb Mon Sep 17 00:00:00 2001 From: Kevin Kwan Date: Tue, 25 Sep 2012 16:21:02 +0800 Subject: Add InfoExtractor for Google Plus video --- youtube_dl/InfoExtractors.py | 124 +++++++++++++++++++++++++++++++++++++++++++ youtube_dl/__init__.py | 1 + 2 files changed, 125 insertions(+) diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index ddb4aa16b..ddb9fbca1 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -2955,3 +2955,127 @@ class MTVIE(InfoExtractor): } return [info] + +class GooglePlusIE(InfoExtractor): + """Information extractor for plus.google.com.""" + + _VALID_URL = r'(?:https://)?plus\.google\.com/(\d+)/posts/(\w+)' + IE_NAME = u'plus.google' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_extract_entry(self, url): + """Report downloading extry""" + self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url.decode('utf-8')) + + def report_date(self, upload_date): + """Report downloading extry""" + self._downloader.to_screen(u'[plus.google] Entry date: %s' % upload_date) + + def report_uploader(self, uploader): + """Report downloading extry""" + self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader.decode('utf-8')) + + def report_title(self, video_title): + """Report downloading extry""" + self._downloader.to_screen(u'[plus.google] Title: %s' % video_title.decode('utf-8')) + + def report_extract_vid_page(self, video_page): + """Report information extraction.""" + self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page.decode('utf-8')) + + def _real_extract(self, url): + # Extract id from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + post_url = mobj.group(0) + video_id = mobj.group(2) + + video_extension = 'flv' + + # Step 1, Retrieve post webpage to extract further information + request = urllib2.Request(post_url) + try: + self.report_extract_entry(post_url) + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % str(err)) + return + + # Extract update date + upload_date = u'NA' + pattern = 'title="Timestamp">(.*?)' + mobj = re.search(pattern, webpage) + if mobj: + upload_date = mobj.group(1) + """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') + self.report_date(upload_date) + + # Extract uploader + uploader = u'NA' + pattern = r'rel\="author".*?>(.*?)' + mobj = re.search(pattern, webpage) + if mobj: + uploader = mobj.group(1) + self.report_uploader(uploader) + + # Extract title + """Get the first line for title""" + video_title = u'NA' + pattern = r'