From 7aca14a1ec9d92599b8871540cfde2dc8225eb8d Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 23 Jun 2013 20:55:15 +0200 Subject: [PATCH] Move G+ IE into its own file, and move google search into a more descriptive module --- youtube_dl/InfoExtractors.py | 76 +---------------- youtube_dl/extractor/googleplus.py | 82 +++++++++++++++++++ .../extractor/{google.py => googlesearch.py} | 0 3 files changed, 84 insertions(+), 74 deletions(-) create mode 100644 youtube_dl/extractor/googleplus.py rename youtube_dl/extractor/{google.py => googlesearch.py} (100%) 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.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 @@ def _real_extract(self, url): }] -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'(.*?)', + 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'