python爬虫+IP代理

"""
Created on Wed Nov 23 00:03:30 2022

@author: fch
"""
import time

'''
网站网址：https://m.7160.top/rentiyishu/
'''
import random
from pyquery import PyQuery as pq
import requests
import os
from joblib import Parallel, delayed
import socket
socket.setdefaulttimeout(10)


# 忽略requests证书警告
from requests.packages.urllib3.exceptions import InsecureRequestWarning
requests.packages.urllib3.disable_warnings(InsecureRequestWarning)

requests.DEFAULT_RETRIES = 5  # 增加重试连接次数

IP_list=[]
with open('./IP代理池.txt','r') as f:
    for line in f:
        line = line.strip('\n')  # 删除换行符
        IP_list.append(line)
f.close()

'''
random随机读取到后为字符串类型，用eval转回字典
'''
# proxie = eval(random.choice(IP_list))

user_agent_list = [
        'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
        'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
        'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0',
        'Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko',
        'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)',
        'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)',
        'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)',
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
        'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
        'Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11',
        'Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11',
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)',
        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)',
        'Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5',
        'Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5',
        'Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5',
        'Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1',
        'MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1',
        'Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10',
        'Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13',
        'Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+',
        'Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0',
        'Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124',
        'Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)',
        'UCWEB7.0.2.37/28/999',
        'NOKIA5700/ UCWEB7.0.2.37/28/999',
        'Openwave/ UCWEB7.0.2.37/28/999',
        'Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999',
        'Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25',
    ]

def Res_url(url):
    requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
    headers = {'User-Agent': random.choice(user_agent_list),
               'Referer': 'https://m.7160.top/rentiyishu/',
               "Connection": "close"}

    try:
        s=requests.session()
        s.keep_alive = False
        r = s.get(url, headers=headers, proxies=eval(random.choice(IP_list)), timeout=(5, 10),verify=False,allow_redirects=False)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        print(url)
        return 'over'

'''
爬取首页中所有伪图片的链接地址和名称，返回成列表
'''
def Parse_page(html):
    page_url_list,fil_name_list=[],[]
    doc = pq(html)
    items = doc('.listUll2 li').items()
    for item in items:
        page_url_list.append(item('div a').attr('href'))
        fil_name_list.append(item('p').text())
    return page_url_list,fil_name_list


def Get_img(page_url, file_name):
    num = 1
    base_url = page_url.split('.')
    while True:
        if num == 1:
            url = page_url
        else:
            url = base_url[0] + '.' + base_url[1] + '.' + base_url[2] + '_' + str(num) + '.' + base_url[3]
        time.sleep(1)
        html = Res_url(url)
        if html != 'over':
            doc = pq(html)
            img_url = doc('.ArticleBox img').attr('src')
            img_basename = doc('.ArticleBox img').attr('alt')
            if img_basename==None:
                img_name=img_basename
            else:
                img_name=img_basename.replace('/','')
            if img_url == None:
                num += 1
            else:
                Save_img(img_url, file_name, img_name)
                num += 1
        else:
            break   #跳出while循环


def Save_img(img_url, file_name, img_name):
    time.sleep(1)
    requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
    headers = {'User-Agent': random.choice(user_agent_list),
               'Referer': 'https://m.7160.top/rentiyishu/',
               "Connection": "close"}
    houzui = img_url.split('.')[-1]
    addr = './images_3/' + file_name
    if not os.path.isdir(addr):
        os.makedirs(addr)
    r=requests.get(img_url, headers=headers, proxies=eval(random.choice(IP_list)), verify=False).content
    if r.status_code==200:
        with open('./images_3/{}/{}.{}'.format(file_name, img_name, houzui), 'wb') as f:
            f.write(r.content)
            f.close()
    else:
        print('图片地址不存在')


def main():
    page_num = 1
    base_url = 'https://m.7160.top/rentiyishu/index'
    while True:
        if page_num == 1:
            url = base_url + '.html'
        else:
            url = base_url + '_' + str(page_num) + '.html'
        html = Res_url(url)
        if html != 'over':
            print('保存第', page_num, '页')
            page_url_list, file_name_list=Parse_page(html)
            '''
            多线程：n_jobs=30即同时30个线程
            '''
            Parallel(n_jobs=5)(delayed(Get_img)(page_url,file_name) for page_url,file_name in zip(page_url_list,file_name_list))
        else:
            print('程序结束')
            return '程序结束'
        page_num += 1
main()