堆糖爬虫
因为，本人能力问题爬图片不能怕全。而且，也没有多线程。from urllib.request import *
import random
import os
from urllib.error import *
import re
import time
f_img = []
url = input('请输入网址')
head ={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.5112.48 Safari/537.36 Edg/104.0.1293.25'}
html = None
def get_html(url):
global html
url =url
head ={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.5112.48 Safari/537.36 Edg/104.0.1293.25'}
req = Request(url,None,head)
response = urlopen(req)
html = response.read().decode('utf-8')
def find_img():
global html
global f_img
while True:
xx = re.search(r'data-iid="" src="*"',html)
yy = re.search(r'thumb\.400_0\.jpg" height',html)
if yy == None:
break;
else:
xxx = str(yy)
xxx = xxx
yyy = str(xx)
yyy = yyy
yyy = int(yyy)
xxx = int(xxx)
xxx = xxx+15
y = html
print(y)
savemm(y,y)
html = html
def savemm(url,y):
y = url
y = y+str(time.time())
y = y+'.jpg'
try:
url = url
iplist = ['58.221.154.46:9091','112.14.40.137:9091','223.94.85.131:9091','120.237.144.200:9091','183.222.217.168:9091','123.180.189.135:9091','222.179.155.90:9091','183.239.62.251:9091','221.181.238.59:9091','112.14.40.137:9091','59.56.142.185:9091','222.77.85.15:9091']
head ={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.5112.48 Safari/537.36 Edg/104.0.1293.25'}
x = random.choice(iplist)
proxy_support = ProxyHandler({'http':x})
opener = build_opener(proxy_support)
opener.addheaders = [('User-Agent', 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.65 Safari/537.36')]
install_opener(opener)
response = urlopen(url)
html = response.read()
with open(y,'wb') as f:
f.write(html)
f.close()
except:
savemm(url,y)
get_html(url)
find_img()
页:
[1]