python古诗代码案例_【Python爬虫】爬取古诗词，按类别采集

[Python] 纯文本查看 复制代码from bs4 import BeautifulSoup

import requests

import json

import re

import time

def get_one_page(url):

try:

headers = {

"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36"

}

response = requests.get(url, headers=headers)

if response.status_code == 200:

response.encoding = "UTF-8"

return response.text

except requests.ConnectionError:

return None

def choice_jiekou(): # 抓取每个风格的地址

URL = "https://www.gushiwen.org/shiju/xiejing.aspx"

html = requests.get(URL).text

soup = BeautifulSoup(html, 'lxml')

gushi_1 = soup.find_all("div", {"class":"cont"})

raws = []

for gushi in gushi_1:

gushi = gushi.fin