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

Change to allow a chapter url to be passed in, yet still get the information it needs from the story index page. This will get the chapter links from the passed in url.

Browse source
This commit is contained in:
wsuetholz 2010-11-10 12:36:21 -06:00
parent 7c252e83a1
commit 3f40df82dd
1 changed files with 51 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

54
hpfiction.py
View file

@ -40,10 +40,23 @@ class HPFiction(FanfictionSiteAdapter):
self.opener = u2.build_opener(u2.HTTPCookieProcessor())
self.chapurl = False
self.storyId = '0'
sss = self.url.split('?')
logging.debug('sss=%s' % sss)
if sss is not None and len(sss) > 1:
sc = sss[1].split('=')
logging.debug('sc=%s' % sc)
if sc is not None and len(sc) > 1:
if sc[0] == 'chapterid':
self.chapurl = True
elif sc[0] == 'psid' or sc[0] == 'sid':
self.storyId = sc[1]
self.storyDescription = 'Fanfiction Story'
self.authorId = '0'
self.authorURL = ''
(u1, self.storyId) = self.url.split('=')
self.storyPublished = datetime.date(1970, 01, 31)
self.storyCreated = datetime.datetime.now()
self.storyUpdated = datetime.date(1970, 01, 31)
@ -93,6 +106,7 @@ class HPFiction(FanfictionSiteAdapter):
return True
def extractIndividualUrls(self):
data = self.opener.open(self.url).read()
soup = bs.BeautifulSoup(data)
@ -100,10 +114,42 @@ class HPFiction(FanfictionSiteAdapter):
def_chapurl = ''
def_chaptitle = ''
if self.chapurl:
foundid = False
for a in links:
if a['href'].find('psid') != -1:
sp = a['href'].split('?')
if sp is not None and len(sp) > 1:
for sp1 in sp:
if sp1.find('psid') != -1:
ps = sp1.split('=')
if ps is not None and len(ps) > 1:
self.storyId = ps[1].replace('\'','')
foundid = True
self.storyName = a.string
logging.debug('self.storyId=%s, self.storyName=%s' % (self.storyId, self.storyName))
break
if foundid:
self.url = "http://" + self.host + "/viewstory.php?psid=" + self.storyId
logging.debug('Title Page URL=%s' % self.url)
data1 = self.opener.open(self.url).read()
hdrsoup = bs.BeautifulSoup(data1)
else:
hdrsoup = soup
else:
hdrsoup = soup
for a in links:
if a['href'].find('psid') != -1:
if not self.chapurl and a['href'].find('psid') != -1:
sp = a['href'].split('?')
if sp is not None and len(sp) > 1:
for sp1 in sp:
if sp1.find('psid') != -1:
ps = sp1.split('=')
if ps is not None and len(ps) > 1:
self.storyId = ps[1].replace('\'','')
self.storyName = a.string
logging.debug('self.storyName=%s' % self.storyName)
logging.debug('self.storyId=%s, self.storyName=%s' % (self.storyId, self.storyName))
elif a['href'].find('viewuser.php') != -1:
self.authorName = a.string
self.authorURL = 'http://' + self.host + '/' + a['href']
@ -114,7 +160,7 @@ class HPFiction(FanfictionSiteAdapter):
def_chaptitle = a.string
logging.debug('def_chapurl=%s, def_chaptitle=%s' % (def_chapurl, def_chaptitle))
centers = soup.findAll('center')
centers = hdrsoup.findAll('center')
for center in centers:
tds = center.findAll ('td')
if tds is not None and len(tds) > 0: