爬虫中ip代理、selenium\session和cookie的使用

1. ip代理

1. 什么是代理ip？它的作用？
2. HTTP和HTTPS的区别
3. 获取ip地址并验证代理IP地址的有效性

A1: 我们知道IP是上网需要唯一的身份地址，身份凭证，代理IP是我们上网过程中的一个中间平台，是由自己的电脑先访问代理IP，之后由代理IP访问点开的页面。所以在这次访问记录里留下的是代理IP的地址，而不少自己电脑本机IP。
使用代理IP的好处有：1.加快访问速度 2. 保护隐私信息 3. 提高下载速度 4.可以当防火墙。

A2:

A3:


从该网站获取代理IP地址：

代码如下:

from bs4 import BeautifulSoup
import requests
import re
import json


def open_proxy_url(url):
    user_agent = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
    headers = {'User-Agent': user_agent}
    try:
        r = requests.get(url, headers = headers, timeout = 10)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        print('无法访问网页' + url)


def get_proxy_ip(response):
    proxy_ip_list = []
    soup = BeautifulSoup(response, 'html.parser')
    proxy_ips = soup.find(id = 'ip_list').find_all('tr')
    for proxy_ip in proxy_ips:
        if len(proxy_ip.select('td')) >=8:
            ip = proxy_ip.select('td')[1].text
            port = proxy_ip.select('td')[2].text
            protocol = proxy_ip.select('td')[5].text
            if protocol in ('HTTP','HTTPS','http','https'):
                proxy_ip_list.append(f'{protocol}://{ip}:{port}')
    return proxy_ip_list

def open_url_using_proxy(url, proxy):
    user_agent = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
    headers = {'User-Agent': user_agent}
    proxies = {}
    if proxy.startswith(('HTTPS','https')):
        proxies['https'] = proxy
    else:
        proxies['http'] = proxy

    try:
        r = requests.get(url, headers = headers, proxies = proxies, timeout = 10)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return (r.text, r.status_code)
    except:
        print('无法访问网页' + url)
        print('无效代理IP: ' + proxy)
        return False

def check_proxy_avaliability(proxy):
    url = 'http://www.baidu.com'
    result = open_url_using_proxy(url, proxy)
    VALID_PROXY = False
    if result:
        text, status_code = result
        if status_code == 200:
            r_title = re.findall('<title>.*</title>', text)
            if r_title:
                if r_title[0] == '<title>百度一下，你就知道</title>':
                    VALID_PROXY = True
        if VALID_PROXY:
            check_ip_url = 'https://jsonip.com/'
            try:
                text, status_code = open_url_using_proxy(check_ip_url, proxy)
            except:
                return

            print('有效代理IP: ' + proxy)
            with open('valid_proxy_ip.txt','a') as f:
                f.writelines(proxy)
            try:
                source_ip = json.loads(text).get('ip')
                print(f'源IP地址为：{source_ip}')
                print('='*40)
            except:
                print('返回的非json,无法解析')
                print(text)
    else:
        print('无效代理IP: ' + proxy)

if __name__ == '__main__':
    proxy_url = 'https://www.xicidaili.com/'
    text = open_proxy_url(proxy_url)
    proxy_ip_filename = 'proxy_ip.txt'
    with open(proxy_ip_filename, 'w') as f:
        f.write(text)
    text = open(proxy_ip_filename, 'r').read()
    proxy_ip_list = get_proxy_ip(text)
    for proxy in proxy_ip_list:
        check_proxy_avaliability(proxy)

运行结果：

2.session 和 cookie

1. 静态网页和动态网页
   
   
   
   
   
   
   
2. 模拟登陆163

import time

from selenium import webdriver
from selenium.webdriver.common.by import By

"""
使用selenium进行模拟登陆
1.初始化ChromDriver
2.打开163登陆页面
3.找到用户名的输入框，输入用户名
4.找到密码框，输入密码
5.提交用户信息
"""
name = '*'
passwd = '*'
driver = webdriver.Chrome()
driver.get('https://mail.163.com/')
# 将窗口调整最大
driver.maximize_window()
# 休息5s
time.sleep(5)
current_window_1 = driver.current_window_handle
print(current_window_1)

button = driver.find_element_by_id('lbNormal')
button.click()

driver.switch_to.frame(driver.find_element_by_xpath("//iframe[starts-with(@id, 'x-URS-iframe')]"))

email = driver.find_element_by_name('email')
#email = driver.find_element_by_xpath('//input[@name="email"]')
email.send_keys(name)
password = driver.find_element_by_name('password')
#password = driver.find_element_by_xpath("//input[@name='password']")
password.send_keys(passwd)
submit = driver.find_element_by_id("dologin")
time.sleep(15)
submit.click()
time.sleep(10)
print(driver.page_source)
driver.quit()

3. 总结及作业