import re,json,os,sys,time,requests
from lxml import etree
from multiprocessing.dummy import Pool as ThreadPool
from urllib.parse import quote,unquote
def filterFName(FName):
rstr = r"[\/\\\:\*\?\"\<\>\|]"
new_name = re.sub(rstr, "_", FName)
return new_name
def mkdir(path):
path = path.strip()
isExists = os.path.exists(path)
if not isExists:
os.makedirs(path)
def gethtml(url,encode):
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8'}
r = requests.get(url,headers=headers)
r.encoding = encode
return r.text
def writehtml(path,str):
f = open(path,'w+',encoding='utf-8')
f.write(str)
f.close
def postdata(url,pdata):
headers = {'X-Requested-With': 'XMLHttpRequest'}
rep