'):data.find('
')] +"
"
- soup = self.make_soup(data)
- for tag in soup.findAll('td',{'class':'ffh'}) + \
- soup.findAll('div',{'class':'acl'}) + \
- soup.findAll('div',{'class':'adWrap'}) + \
- soup.findAll('div',{'class':'footer smtxt'}) + \
- soup.findAll('table',{'class':'tbbrdr'}):
- tag.extract() # remove tag from soup.
+ m = re.match(r".*?Uploaded On: ([a-zA-Z]+ \d\d, \d\d\d\d \d\d:\d\d)",headerstr)
+ if m:
+ date = makeDate(m.group(1), self.dateformat)
+ if not self.story.getMetadataRaw('datePublished') or date < self.story.getMetadataRaw('datePublished'):
+ self.story.setMetadata('datePublished', date)
- return self.utf8FromSoup(url,soup)
+ chapter = soup.find('div',{'id':'fanfic-text'})
+
+ return self.utf8FromSoup(url,chapter)
+
+ # chapter=self.make_soup('
').find('div')
+
+ # if None == header:
+ # raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
+
+ # ## find divs with align=left, those are paragraphs in newer stories.
+ # divlist = header.findAllNext('div',{'align':'left'})
+ # if divlist:
+ # for div in divlist:
+ # div.name='p' # convert to
mediaminer uses div with
+ # # a margin for paragraphs.
+ # chapter.append(div)
+ # del div['style']
+ # del div['align']
+ # return self.utf8FromSoup(url,chapter)
+
+ # else:
+ # logger.debug('Using kludgey text find for older mediaminer story.')
+ # ## Some older mediaminer stories are unparsable with BeautifulSoup.
+ # ## Really nasty formatting. Sooo... Cheat! Parse it ourselves a bit first.
+ # ## Story stuff falls between:
+ # data = "
" + data[data.find('
'):data.find('
')] +"
"
+ # soup = self.make_soup(data)
+ # for tag in soup.findAll('td',{'class':'ffh'}) + \
+ # soup.findAll('div',{'class':'acl'}) + \
+ # soup.findAll('div',{'class':'adWrap'}) + \
+ # soup.findAll('div',{'class':'footer smtxt'}) + \
+ # soup.findAll('table',{'class':'tbbrdr'}):
+ # tag.extract() # remove tag from soup.
+
+ # return self.utf8FromSoup(url,soup)
def getClass():
diff --git a/fanficfare/defaults.ini b/fanficfare/defaults.ini
index 3659f75..16caca7 100644
--- a/fanficfare/defaults.ini
+++ b/fanficfare/defaults.ini
@@ -1856,6 +1856,15 @@ rating_titles: R=RESTRICTED (16+), E=EXEMPT (18+), I=ART HOUSE, T=To every, A=IN
adult_ratings: E,R
[www.mediaminer.org]
+dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S
+## Note that mediaminer doesn't give datePublished on the story's
+## index page--it's collected from the earliest uploaded chapter. So
+## it's not available when only fetching metadata.
+datePublished_format:%%Y-%%m-%%d %%H:%%M:%%S
+
+## some sites include images that we don't ever want becoming the
+## cover image. This lets you exclude them.
+cover_exclusion_regexp:/img/rss.png
[www.midnightwhispers.ca]
## Some sites do not require a login, but do require the user to