通过代理爬mzitu

#导入库

import os
import requests
from bs4 import BeautifulSoup
import time
from config import *
import random
import re
from requests import ConnectionError

#生成mzitu请求headers

def res_headers():
    headers = {
        'User-Agent': random.choice(USER_AGENT_LIST),
        'Referer':random.choice(REFERER_LIST),
    }
    return headers

　　#生成单个user-agent

def get_header():
    headers = {
        'User-Agent':random.choice(USER_AGENT_LIST)
    }
    return headers

　　#获取list后checkip返回可用ip

def get_proxy_list():
    ip_list = []
    base_url = 'https://www.xicidaili.com/wt/'
    header = get_header()
    actual_url = base_url + str(random.randint(1,300))
    try:
        res = requests.get(url=actual_url, headers=header)
        if res.status_code == 200:
            html = res.text
            pattern = '(d+.d+.d+.d+)</td>s*<td>(d+)'
            re_list = re.findall(pattern, html)
            for ip_port in re_list:
                ip_port = ip_port[0] + ':' + ip_port[1]
                ip_list.append(ip_port)
            check_ip(ip_list)
        else:get_proxy_list()
    except ConnectionError:
        get_proxy_list()

　　#check 有效ip

def check_ip(ip_list):
    # print('check_ip')
    url_baidu = 'https://www.mzitu.com/'
    proxy_ip = 'http://' + random.choice(ip_list)
    proxy_ip_dic = {
        'http': proxy_ip
    }
    header = get_header()
    # print(proxy_ip_dic)
    try:
        res = requests.get(url_baidu, headers=header, proxies=proxy_ip_dic, timeout=8)
        if res.status_code == 200:
            # print(proxy_ip_dic)
            return proxy_ip_dic
    except ConnectionError:
        get_proxy_list()

　　#网站请求

def get_page(url):
    headers=res_headers()
    # 创建session
    s = requests.session()
    s.keep_alive = False
    # 获取页面
    res = s.get(url,headers=headers)
    html = res.text
    return html

　　#获取页面all girls的详情页url

def get_all_girls(url):
    html = get_page(url)
    # 构建soup页面
    soup = BeautifulSoup(html, 'html.parser')
    # 获取 class_='archives' 下的所有 'a'标签
    total_info = soup.find(class_='archives').find_all('a')
    # 遍历 'a' 标签，读取'href'值
    all_list=[]
    for girls_info in total_info:
        link_url = girls_info['href']
        all_list.append(link_url)
    # print(all_list)
    return all_list

　　#获取girl的所有图片url

def get_girl_all_page(url):
    print('获取girl的所有图片url')
    html=get_page(url)
    soup = BeautifulSoup(html,'html.parser')
    # 在 class_='pagenavi' 中的倒数第3个标签，读取 'span' 的值（图片数量）
    max_page = soup.find(class_='pagenavi',).find_all('a')[-2].find('span').string
    title = soup.find(class_='main-title').string
    # 循环读取详情页面中的'img'标签中的'src'值
    headers = res_headers()
    proxy = get_proxy_list()
    pic_url_list = []
    for i in range(int(max_page)):
        page_url = url + "/%s"  %(i+1)
        html = requests.get(page_url, headers=headers, proxies=proxy).text
        # print(html)
        soup = BeautifulSoup(html,'html.parser')
        # print(soup.text)
        # pic_url = soup.find('img').get('src')
        pic_url = soup.find('img').get('src')
        # print(pic_url)
        pic_url_list.append(pic_url)
        time.sleep(0.1)
    # print(pic_url_list)
    download_Pic(title,pic_url_list)

　　#下载图片，以标题为文件夹名

def download_Pic(title, pic_url_list):
    # 新建文件夹，路径
    os.mkdir(title)
    headers = res_headers()
    proxy = get_proxy_list()
    # 自定义序列号
    j = 1
    # 下载图片
    for item in pic_url_list:
        # 定义文件路径及名称
        filename = '%s/%s.jpg' % (title, str(j))
        print('downloading....%s : NO.%s' % (title, str(j)))
        with open(filename, 'wb') as f:
            img = requests.get(item, headers=headers,proxies=proxy).content
            f.write(img)
        j += 1
    time.sleep(10)

　　#主程序

if __name__ == '__main__':
    url = "https://www.mzitu.com/all"
    pic_list = get_all_girls(url)
    for i in pic_list:
        get_girl_all_page(i)

　　#config.py

USER_AGENT_LIST = [
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
    "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
    "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
    "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",
    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",
    "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",
    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
    "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/531.21.8 (KHTML, like Gecko) Version/4.0.4 Safari/531.21.10",
    "Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/533.17.8 (KHTML, like Gecko) Version/5.0.1 Safari/533.17.8",
    "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/533.19.4 (KHTML, like Gecko) Version/5.0.2 Safari/533.18.5",
    "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-GB; rv:1.9.1.17) Gecko/20110123 (like Firefox/3.x) SeaMonkey/2.0.12",
    "Mozilla/5.0 (Windows NT 5.2; rv:10.0.1) Gecko/20100101 Firefox/10.0.1 SeaMonkey/2.7.1",
    "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.8 (KHTML, like Gecko) Chrome/4.0.302.2 Safari/532.8",
    "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.464.0 Safari/534.3",
    "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_5; en-US) AppleWebKit/534.13 (KHTML, like Gecko) Chrome/9.0.597.15 Safari/534.13",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.186 Safari/535.1",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.54 Safari/535.2",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7",
    "Mozilla/5.0 (Macintosh; U; Mac OS X Mach-O; en-US; rv:2.0a) Gecko/20040614 Firefox/3.0.0 ",
    "Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.5; en-US; rv:1.9.0.3) Gecko/2008092414 Firefox/3.0.3",
    "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.5; en-US; rv:1.9.1) Gecko/20090624 Firefox/3.5",
    "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.6; en-US; rv:1.9.2.14) Gecko/20110218 AlexaToolbar/alxf-2.0 Firefox/3.6.14",
    "Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.5; en-US; rv:1.9.2.15) Gecko/20110303 Firefox/3.6.15",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1"
]

REFERER_LIST= [
'https://www.mzitu.com/215756', 
'https://www.mzitu.com/201236',
'https://www.mzitu.com/214521',
'https://www.mzitu.com/200253',
'https://www.mzitu.com/214751',
'https://www.mzitu.com/199934',
'https://www.mzitu.com/214404',
'https://www.mzitu.com/199190',
'https://www.mzitu.com/214261',
'https://www.mzitu.com/199970',
]　　

　　    爬了1个小时后，自己的ip被代理网站屏蔽了，哈哈哈哈

Traceback (most recent call last):
  File "D:Python38libsite-packagesurllib3connection.py", line 156, in _new_conn
    conn = connection.create_connection(
  File "D:Python38libsite-packagesurllib3utilconnection.py", line 84, in create_connection
    raise err
  File "D:Python38libsite-packagesurllib3utilconnection.py", line 74, in create_connection
    sock.connect(sa)
TimeoutError: [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应，连接尝试失败。

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "D:Python38libsite-packagesurllib3connectionpool.py", line 665, in urlopen
    httplib_response = self._make_request(
  File "D:Python38libsite-packagesurllib3connectionpool.py", line 376, in _make_request
    self._validate_conn(conn)
  File "D:Python38libsite-packagesurllib3connectionpool.py", line 994, in _validate_conn
    conn.connect()
  File "D:Python38libsite-packagesurllib3connection.py", line 334, in connect
    conn = self._new_conn()
  File "D:Python38libsite-packagesurllib3connection.py", line 168, in _new_conn
    raise NewConnectionError(
urllib3.exceptions.NewConnectionError: <urllib3.connection.VerifiedHTTPSConnection object at 0x000001E898850C40>: Failed to establish a new connection: [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应，连接尝试失败。

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "D:Python38libsite-packages
equestsadapters.py", line 439, in send
    resp = conn.urlopen(
  File "D:Python38libsite-packagesurllib3connectionpool.py", line 719, in urlopen
    retries = retries.increment(
  File "D:Python38libsite-packagesurllib3util
etry.py", line 436, in increment
    raise MaxRetryError(_pool, url, error or ResponseError(cause))
urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='www.mzitu.com', port=443): Max retries exceeded with url: /194229/30 (Caused by NewConnectionError('<urllib3.connection.VerifiedHTTPSConnection object at 0x000001E898850C40>: Failed to establish a new connection: [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应，连接尝试失败。'))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "D:/project/mzitu/spider.py", line 132, in <module>
    get_girl_all_page(i,proxy)
  File "D:/project/mzitu/spider.py", line 98, in get_girl_all_page
    html = requests.get(page_url,headers=res_headers(),proxies=proxy).text
  File "D:Python38libsite-packages
equestsapi.py", line 75, in get
    return request('get', url, params=params, **kwargs)
  File "D:Python38libsite-packages
equestsapi.py", line 60, in request
    return session.request(method=method, url=url, **kwargs)
  File "D:Python38libsite-packages
equestssessions.py", line 533, in request
    resp = self.send(prep, **send_kwargs)
  File "D:Python38libsite-packages
equestssessions.py", line 646, in send
    r = adapter.send(request, **kwargs)
  File "D:Python38libsite-packages
equestsadapters.py", line 516, in send
    raise ConnectionError(e, request=request)
requests.exceptions.ConnectionError: HTTPSConnectionPool(host='www.mzitu.com', port=443): Max retries exceeded with url: /194229/30 (Caused by NewConnectionError('<urllib3.connection.VerifiedHTTPSConnection object at 0x000001E898850C40>: Failed to establish a new connection: [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应，连接尝试失败。'))

　　

【推广】 免费学中医，健康全家人
原文地址：https://www.cnblogs.com/lijifei/p/12048437.html