古诗爬取

IP代理爬取

直接代码

import re
import requests
import time
# url = 'https://www.gushiwen.org/default_1.aspx'


def parse_page(url):
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.92 Safari/537.36'
    }
    response = requests.get(url, headers)
    text = response.text
    # print(text)
    titles = re.findall(r'<div\sclass="cont">.*?<b>(.*?)</b>', text, re.DOTALL)
    # print(titles)
    dynasties = re.findall(r'<p\sclass="source".*?<a.*?>(.*?)</a>', text, re.DOTALL)
    # print(dynasties)
    authors = re.findall(r'<p\sclass="source".*?</a>.*?<a.*?>(.*?)</a>', text, re.DOTALL)
    # print(authors)
    contents = re.findall(r'<div\sclass="contson".*?>(.*?)</div>', text, re.DOTALL)
    # print(contents)
    poems = []
    for content in contents:
        # print(content)
        x = re.sub(r'<.*?>', "", content)
        # print(x)
        poems.append(x.strip())
        # print(poems)
        shis = []
    for value in zip(titles, dynasties, authors, poems):
        title, dynasty, author, poem = value
        f=open('main.txt','a')
        w=title+'@'+title+','+dynasty+','+author+','+poem
        w=w.replace('·','.').replace('/','-')
        print(w)
        time.sleep(2)


def main():
    base_url = 'https://www.gushiwen.org/default_{}.aspx'

    for x in range(1, 11):	# 利用正则表达式爬取1-10页的内容
        url = base_url.format(x)
        parse_page(url)


if __name__ == '__main__':
    main()