def get_target(self,url,target_prefix=""): content, ts = self.get_html(url) if content == -1: return -1 data = json.loads(content)['data'] if data: try: ps = parser(data) return ps except Exception, e: print e return -1
def get_target(self,url,target_prefix=""): content, ts = self.get_html(url) if content == -1: return -1 data = json.loads(content)['data'] if data: try: ps = parser(data) return ps except Exception, e: print e return -1
def get_target(self,url,target_prefix=""):
content, ts = self.get_html(url)
if content == -1:
return -1
lines = content.splitlines()
for line in lines:
if line.startswith(target_prefix):
n = line.find('html":"')
target = line[n+7:-12]
target = target.replace("\\t","")
target = target.replace("\\n","")
target = target.replace("\\r",'')
target = target.replace("\\",'')
ps = parser(target)
if ps == None:
#logger.logger_error("bad content")
print "why here..."
return -1
return ps
#logger.logger_error("bad content, please check the resource")
print "bad content, please check the resource"
save_to_disk("tmp.html",content)
return -1
def get_target(self, url, target_prefix=""):
content, ts = self.get_html(url)
if content == -1:
return -1
lines = content.splitlines()
for line in lines:
if line.startswith(target_prefix):
n = line.find('html":"')
target = line[n + 7:-12]
target = target.replace("\\t", "")
target = target.replace("\\n", "")
target = target.replace("\\r", '')
target = target.replace("\\", '')
ps = parser(target)
if ps == None:
#logger.logger_error("bad content")
print "why here..."
return -1
return ps
#logger.logger_error("bad content, please check the resource")
print "bad content, please check the resource"
save_to_disk("tmp.html", content)
return -1
