def post(self):
name = self.get_argument('name')
url = self.get_argument('rss_url')
ftags = self.get_argument('tags').split('|')
fclasses = self.get_argument('classes').split('|')
ftext = self.get_argument('text')
urlmd5 = self.get_argument("urlmd5")
dominfo = eval(cache.get(urlmd5 + 'dominfo'))
res= '1'
if urlmd5:
crawl_info = dict(dominfo=dominfo,
filterdominfo=dict(filtertag=ftags,
filterclass=fclasses),
filterhtmlinfo=dict(ftext=ftext))
info = dict(url=url,
name=name,
crawl_info=json.dumps(crawl_info))
logger.info(info)
res = DButils.writeRssInfo(info)
self.finish(res)
def post(self):
name = self.get_argument('name')
url_example = self.get_argument('url')
domain = self.get_argument('domain', "")
url_regular = self.get_argument('url_regular', "")
paging = self.get_argument('optionsRadios')
nextpagename = self.get_argument('nextpagename')
ftags = self.get_argument('tags').split('|')
fclasses = self.get_argument('classes').split('|')
fimgurl = self.get_argument('imgurl')
ftext1start = self.get_argument('text1start')
ftext1end = self.get_argument('text1end')
ftext2start = self.get_argument('text2start')
ftext2end = self.get_argument('text2end')
imgreplace= self.get_argument('imgreplace', '')
dominfo = self.get_argument("dominfo", "")
filtertext = [[ftext1start, ftext1end], [ftext2start, ftext2end]]
crawl_info = dict(crawl_mode=1,
paging_mode=int(paging),
dominfo=dominfo,
nextpageinfo=dict(tagname='a',
attr='text',
con=nextpagename),
filterdominfo=dict(filterimg=fimgurl,
filtertag=ftags,
filterclass=fclasses),
filterhtmlinfo=dict(filtertext=filtertext,
imgreplace=imgreplace),
sourceinfo=dict())
info = dict(url_example=url_example,
url_regular=url_regular,
name=name,
domain=domain,
crawl_info=json.dumps(crawl_info))
res = DButils.writeRuleInfo(info)
print res
self.finish(res)
def get(self):
string = self.get_argument('string', None)
result = DButils.readRssInfo(string)
logger.info(result)
return self.render('rssadmin.html', data=result)
