@@ -1,6 +1,6 @@ """ * Scrapes the archive pages of one or more lists in a Mailman installation and republishes the contents, with an optional RSS feed. -* v1.11, 2009-05-04 +* v1.12, 2009-05-04 * http://github.com/philgyford/mailman-archive-scraper/ * * Only works with Monthly archives at the moment. @@ -193,7 +193,11 @@ class MailmanArchiveScraper: #body_html = str(soup.pre) # Body of the message (everything within <pre></pre> tags) with all HTML tags stripped. - body_text = 'From: '+sender+'. '+''.join(soup.pre.findAll(text=True)) + body_text = ''.join(soup.pre.findAll(text=True)) + if sender: + # Just in case sender is empty because the contents have been stripped + # by the filtering process. + body_text = 'From: '+sender+'. '+ body_text # Add this message to the RSS feed. self.rss_items.append( @@ -394,8 +398,9 @@ class MailmanArchiveScraper: # eg http://www.example.com/list-name/2009-February/000042.html local_message_url = self.publish_url + url_parts[-2] + '/' + url_parts[-1] - # Add this message to the RSS feed items... - self.addRSSItem(local_message_url, message_time, soup) + if self.messages_fetched < self.items_for_rss: + # Add this message to the RSS feed items... + self.addRSSItem(local_message_url, message_time, soup) return hours_ago MailmanArchiveScraper.py @@ -1,7 +1,7 @@ # Mailman Archive Scraper By Phil Gyford <phil@gyford.com> -v1.11, 2009-05-04 +v1.12, 2009-05-04 Latest version is available from <http://github.com/philgyford/mailman-archive-scraper/> README.markdown 733c780b222b262b1f7c0f3564abdab2070cc9de Phil Gyford phil@gyford.com http://github.com/philgyford/mailman-archive-scraper/commit/bcbd8f4f70e8a33834a07317b2a6fa244ccb8cf3 bcbd8f4f70e8a33834a07317b2a6fa244ccb8cf3 2009-05-04T08:09:32-07:00 2009-05-04T08:09:32-07:00 Fixed an error that occurred when trying to add an email sender's name to the start of an RSS item's description, when the name has been erased by the content filtering. Now, in such a case, the name and 'From: ' text is not included in the RSS item. Also fixed the maximum number of RSS items that will appear in the feed (or it would have included ALL messages scraped). 8ae1ac569fdbd90148431560afbdebb3fa0e252b Phil Gyford phil@gyford.com