爬取csdn博主文章

#!/usr/bin/env python
import re
import requests
import os
import sys
from lxml import etree
headers = {
    "User-Agent":
    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.106 Safari/537.36"
}
# 傳遞的非單個博客地址，而是博客列表
url = "https://blog.csdn.net/maqingqing1992"
html = requests.get(url, headers=headers, verify=False).text
nodes = etree.HTML(html)
tag_a = nodes.xpath('//p//a')
#文章摘要
digest_dic = []
url_dic1 = []
url_dic = []
for i in tag_a:
    res = etree.tostring(i, method='text', encoding='utf-8').decode('utf-8')
    digest_dic.append(res)
    url_dic1.append(str(i.attrib))
for i in url_dic1:
    url_dic.append(re.findall(u'https://.*\d', i))
fo = open("a.txt", "w")
for i in url_dic:
    fo.write(i[0] + "\n")
fo.close()

只是爬取了文章的url，沒有進一步利用。