# -*- coding: utf-8 -*-
# @Time : 2018/03/30 15:20
# @Author : cxa
# @File : liuuchnagtu.py
# @Software: PyCharm
import requests
from fake_useragent import UserAgent as UA
from lxml import html
import os
import threading
import traceback
import time
import random
class GetImage():
def __init__(self):
self.url="http://www.s6tu.com/explore/popular/?list=images&sort=likes_desc&page={}"
self.imgpath = "//div[@class='list-item-image fixed-size']/a/img/@src"
self.headers = {
'Accept': 'text/html, application/xhtml+xml, image/jxr, */*',
'Accept - Encoding': 'gzip, deflate',
'Accept-Language': 'zh-Hans-CN, zh-Hans; q=0.5',
'Connection': 'Keep-Alive',
'User-Agent': UA().random,
'Host': 'www.s6tu.com',}
def get_oen_page(self):
try:
os.makedirs("setu",exist_ok=True)
for i in range(1,999):
url=self.url.format(i)
Session=requests.session()
#Session.proxies.update(self.proxies)
req=Session.get(url,headers=self.headers)
if req.status_code==requests.codes.ok:
root=html.fromstring(req.text)
imglist=root.xpath(self.imgpath)
newlist=[i.replace(".md.",".")for i in imglist]
downloadThreads=[]
for i in range(0,len(newlist),int(len(newlist)/3)):
downloadThread = threading.Thread(target=self.getimglist, args=(newlist,i, i + int(len(newlist)/3)))
downloadThreads.append(downloadThread)
downloadThread.start()
for item in downloadThreads:
item.join()
print("get one page over")
else:
print("errro")
time.sleep(random.randint(1,5))
except:
print("error,here is details:{}".format(traceback.format_exc()))
def getimglist(self,newlist,start,end):
if end>len(newlist):
end=len(newlist)
for i in range(start,end):
imgurl=newlist[i]
downloadThreads = []
print(imgurl)
req=requests.get(imgurl,headers=self.headers)
with open(os.path.join("setu",os.path.basename(imgurl)),"wb") as fs:
fs.write(req.content)
if __name__=="__main__":
GetImage().get_oen_page()
转载于:https://www.cnblogs.com/c-x-a/p/8676669.html
