图片爬虫（代理ip）

# -*- coding: utf-8 -*-
"""
Created on Sat Nov 19 22:44:37 2022

@author: fch
"""

import random
from pyquery import PyQuery as pq
import requests
import os
import time
import json


proxies=[
         {'HTTP':'http://122.140.5.115:9999'},
         {'HTTP':'http://113.101.96.66:8080'},
         {'HTTP':'http://113.124.86.24:9999'},
         {'HTTP':'http://121.13.252.58:41564'},
         {'HTTP':'http://61.216.185.88:60808'},
         {'HTTP':'http://58.20.184.187:9091'},
         {'HTTP':'http://183.236.123.242:8060'},
         {'HTTP':'http://116.9.163.205:58080'},
         {'HTTP':'http://222.74.73.202:42055'},
         {'HTTP':'http://183.247.202.208:30001'},
         {'HTTP':'http://39.108.101.55:1080'},
         {'HTTP':'http://47.105.91.226:8118'},
         ]
proxie=random.choice(proxies)
user_agent_list = ['Chrome/86.0.4240.198',
                   'Chrome/101.0.4951.64',
                   'Chrome/96.0.4664.45',
                   'Chrome/94.0.4606.41'
                   ]
headers = {'User-Agent': random.choice(user_agent_list)}
list1 = [
        "Chrome/68.0.3440.106",
        "Chrome/67.0.3396.99",
        "Chrome/64.0.3282.186",
        "Chrome/62.0.3202.62",
        "Chrome/45.0.2454.101"
    ]


header={'User-Agent': random.choice(list1),
        'Referer':'http://81.68.202.74/',
        'sec-ch-ua': 'Google Chrome',
        'sec-ch-ua-platform':'Windows'
        }
base_url = 'http://81.68.202.74/datu/page/'

# verify=False忽略SSL警告
def Base_page(Page_num):
    url = base_url + str(Page_num)
    try:
        r = requests.get(url, headers=headers,proxies=proxie)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        print('ERROR!!!')


def Page_url(fir_html):
    doc = pq(fir_html)
    items = doc('.posts-wrapper .entry-media').items()
    num = 1
    for item in items:
        page_url=item('a').attr('href')
        fil_name=item('.lazyload').attr('alt').replace(":","")
        # print(fil_name,page_url)
        print('------ 个数：',num,'------')
        Parse_img(page_url, fil_name)
        num+=1


def Parse_img(page_url,fil_name):
    time.sleep(0.25)
    i=1
    r = requests.get(page_url, headers=headers,proxies=proxie)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    sec_html=r.text
    doc=pq(sec_html)
    items=doc('.entry-content p img').items()
    for item in items:
        dict={
            'url':item.attr('src'),
            'name':item.attr('title')
        }
        print("保存第",i,'张图')
        i+=1
        time.sleep(1.25)
        Save_img(dict,fil_name)

def Save_img(dic,fil_name):
    url=dic['url']
    # time.sleep(0.25)
    data = requests.get(url,headers=header,proxies=proxie).content
    name=dic['name']
    houzui=url.split('.')[-1]
    addr='./images_2/'+fil_name
    if not os.path.isdir(addr):
        os.makedirs(addr)
    with open('./images_2/{}/{}.{}'.format(fil_name,name,houzui),'wb') as f:
        f.write(data)

def main():
    #左闭右开，到21页
    for Page_num in range(1,22):
        print("*************第",Page_num,'页*************')
        fir_html = Base_page(Page_num)
        Page_url(fir_html)
    print("结束！")

main()