Backup_Repos/FanFicFare
1
0
Fork 0
mirror of https://github.com/JimmXinu/FanFicFare.git synced 2025-12-06 08:52:55 +01:00
Code Issues Projects Releases Wiki Activity

Brought fimfiction.net published date parsing into line with new site layout

Browse source
This commit is contained in:
althaine 2011-11-06 18:59:33 +11:00
parent a3402170ad
commit 2cd89b2e55
1 changed files with 9 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
fanficdownloader/adapters/adapter_fimfictionnet.py
View file

@ -94,7 +94,11 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
self.story.setMetadata("authorId", author) # The author's name will be unique self.story.setMetadata("authorId", author) # The author's name will be unique
self.story.setMetadata("authorUrl", "http://%s/user/%s" % (self.getSiteDomain(),author)) self.story.setMetadata("authorUrl", "http://%s/user/%s" % (self.getSiteDomain(),author))
self.chapterUrls = [(chapter.text, "http://"+self.getSiteDomain() + chapter['href']) for chapter in soup.findAll("a", {"class":"chapter_link"})] chapterDates = []
for chapter in soup.findAll("a", {"class":"chapter_link"}):
chapterDates.append(chapter.span.extract().text.strip("()"))
self.chapterUrls.append((chapter.text.strip(), "http://"+self.getSiteDomain() + chapter['href']))
self.story.setMetadata('numChapters',len(self.chapterUrls)) self.story.setMetadata('numChapters',len(self.chapterUrls))
@ -138,9 +142,10 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
# than miss an update, we hardcode the year of creation and update to be 2011. # than miss an update, we hardcode the year of creation and update to be 2011.
# Get the date of creation from the first chapter # Get the date of creation from the first chapter
datePublished_soup = bs.BeautifulSoup(self._fetchUrl(self.chapterUrls[0][1])).find("div", {"class":"calendar"}) datePublished_text = chapterDates[0]
datePublished_soup.find('span').extract() day, month = datePublished_text.split()
datePublished = makeDate("2011"+datePublished_soup.text, "%Y%b%d") day = re.sub(r"[^\d.]+", '', day)
datePublished = makeDate("2011"+month+day, "%Y%b%d")
self.story.setMetadata("datePublished", datePublished) self.story.setMetadata("datePublished", datePublished)
dateUpdated_soup = bs.BeautifulSoup(data).find("div", {"class":"calendar"}) dateUpdated_soup = bs.BeautifulSoup(data).find("div", {"class":"calendar"})
dateUpdated_soup.find('span').extract() dateUpdated_soup.find('span').extract()