python 简单爬取简书首页

基础简单的抓取

1.通过BeautifulSoup来解析网页获取到所有链接

2.通过正则判断链接的完整性是否追加域名

3.写入到txt文件

一.代码

import random
import re
import requests  # 网络请求模块
from bs4 import BeautifulSoup

if __name__ == '__main__':
    response = requests.get('https://www.jianshu.com', headers=getHeaders(), timeout=5)
    print(response)  # 打印请求结果的状态码
    print(response.content)  # 打印请求到的网页源码

    soup = BeautifulSoup(response.content, 'lxml')  # 将网页源码构造成BeautifulSoup对象，方便操作
    tags = soup.find_all('a')
    text = ''  # 创建一个空字符串

    for tag in tags:
        title = tag.get_text().replace(" ", "").replace("\r", "").replace("\n", "")
        href = tag["href"]
        none = str(re.match(r'(http|https)+:\/\/w{3}((.\w+){2})', href, flags=0))
        print("none：" + none)
        if none == 'None':
            href = "https://www.jianshu.com" + href

        if title.strip():
            text += title + "\n" + href + "\n"
        # print("获取到的标签：" + text)  # 打印a标签对象的href属性，即这个对象指向的链接地址
    with open("url.txt", "w") as f:
        f.write(text)
        
        
def getHeaders():
    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 6.2) 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"
    ]
    UserAgent = random.choice(user_agent_list)
    headers = {'User-Agent': UserAgent}
    return headers

二.结果

三.学习总结

正则表达式的学习

(http|https)+:\/\/w{3}((.\w+){2}) 

（http|https)+: 以http或https开头出现1次或多次的

   \/\/转义斜杠相当于匹配 //

   w{3} w至少出现三次

   (.\w+){2}  .xxx.xxx.xxx 这样以点结尾格式至少出现过三次

 

       正则测试网址：https://c.runoob.com/front-end/854