爬虫-Day5-登录和IP代理

爬虫-Day5-登录和IP代理

1.requests登录反爬

import requests

# 1. request登录反爬过程
"""
1）用谷歌浏览器打开需要爬取的网站，人工完成登录
2）获取这个网站登录后的cookie信息：
  检查 -> Network -> All -> 网站域名  -> Headers -> RequestHeader  -> cookie
3）在headers对应的字典中添加键值对： 'cookie': 获取到的cookie信息
"""

headers = {
    'cookie': '_zap=bccd72c4-94da-4aad-b6f4-c4a076540641; d_c0="APCfiebWwxSPTmf4t0eyATFtTgFHdTZJ_sk=|1649519947"; _xsrf=7RrxkbJCk4djlHfCY5NfKwhhm5IDMyOD; __snaker__id=ncPyNsuTImwpYs5U; gdxidpyhxdE=R63k63BTZgZmXMVXEoiGKqKXyt%5C%2Fwv%5CicGl9ILEMdLjgbXj7nk27VJCDgVByWgL2E9%5C81w5II3sRI%2BLlrU%5CNujzOp%2FwpBDxMoiUCttYM9TUr%5C%2BQqMfbqqZJBEnfpo9CWB%2FuKHMltgaSI1NYgTxXcR3WmZ5ZsoHtDeaKKogUenjN9E8Lv%3A1652758223246; _9755xjdesxxd_=32; 
}
response = requests.get('https://www.zhihu.com/', headers=headers)

print(response.text)

2.selenium登录反爬

from selenium.webdriver import Chrome
from json import dumps

# 1. 打开需要做自动登录的网站
b = Chrome()
b.get('https://www.taobao.com')

# 2. 提供足够长的时间让人工在这个页面中完成登录(登录后一定要保证b对应的窗口出现登录信息)
input('登录完成:')

# 3. 获取登录后的cookie信息保存到本地文件中(建议保存一个json)
cookies = b.get_cookies()

with open('files/taobao.json', 'w', encoding='utf-8') as f:
    f.write(dumps(cookies))

b.close()

# 1. 打开需要爬取的网站
b = Chrome()
b.get('https://www.taobao.com')

# 2.从cookie文件中获取cookie信息并且添加到浏览器对象中
with open('files/taobao.json', encoding='utf-8') as f:
    cookies = loads(f.read())

for x in cookies:
    b.add_cookie(x)

# 3.重新打开网页
b.get('https://www.taobao.com')

input('end:')
b.close()

3.requests使用代理

import requests

headers = {
    'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Safari/537.36'
}

# 创建代理对象
# proxies = {
#     'https': 'http://183.165.224.25:4554',
#     'http': 'http://183.165.224.25:4554'
# }
proxies = {
    'https': '183.165.224.25:4554',
    'http': '183.165.224.25:4554'
}
# 发送请求的时候使用代理
response = requests.get('https://www.maoyan.com/', headers=headers, proxies=proxies)
# 解决乱码问题
response.encoding = 'utf-8'
print(response.text)

4.使用代理的实际用法

import requests
import time
from bs4 import BeautifulSoup


def get_ip():
    """
    获取代理ip，如果获取失败过2秒再重新获取
    :return: 获取到的ip地址
    """
    while True:
        response = requests.get('http://d.jghttp.alicloudecs.com/getip?num=1&type=1&pro=510000&city=510600&yys=0&port=1&time=2&ts=0&ys=0&cs=0&lb=4&sb=0&pb=4&mr=1&regions=')
        result = response.text
        if result[0] == '{':
            print('ip获取失败')
            time.sleep(2)
        else:
            return result


def get_net_data():
    url = 'https://www.maoyan.com/'
    headers = {
        'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Safari/537.36'
    }

    # 使用代理ip发送请求，如果代理失败，重新获取新的ip重新再发送请求
    while True:
        ip = get_ip()
        print(ip)
        proxy = {
            'https': ip
        }
        response = requests.get(url, headers=headers, proxies=proxy)
        response.encoding = 'utf-8'
        print(response.text)

        soup = BeautifulSoup(response.text, 'lxml')
        movies_div = soup.select('.movie-list .movie-item')
        if len(movies_div) == 0:
            continue
        else:
            print('爬虫成功!做后续的解析操作')
            break


if __name__ == '__main__':
    get_net_data()

5.selenium使用代理

from selenium.webdriver import Chrome, ChromeOptions

options = ChromeOptions()
options.add_argument('--proxy-server=http://115.208.231.37:4545')

b = Chrome(options=options)
b.get('https://www.maoyan.com/')

print(b.page_source)

input('end:')
b.close()