1.爬取百度首页

爬取百度首页：

案例仅用于学习，任何非法用途，与本人无关。

import random

import requests

# 封装请求头
user_agent = [
    '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 (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',
    'Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; 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',
    '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)'
]

# 随机 获取一个 agent
# print(random.choice(user_agent))
headers = {
    'User-Agent': random.choice(user_agent)
}
# 请求 百度页面
response = requests.get('https://www.baidu.com/', headers)

# 将页面内容 保存到本地
with open('baidu.html', 'w', encoding='utf-8') as f:
    f.write(response.content.decode('utf-8'))