python最简单爬虫入手例子:
爬取某网站书籍评论
import requests
from bs4 import BeautifulSoup
import pandas as pd
url = 'https://www.aliwx.com.cn/comment?bookid=7178107&authorid=2371187'
user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36'
headers = {"User-Agent": user_agent}
inform_list = []
respond = requests.get(url=url, headers=headers)
soup = BeautifulSoup(respond.text, 'lxml')
div_list = soup.find_all('div', class_="comment")
for node in div_list:
comment = node.find('p', class_='content js-textArea').text
print(comment)
inform_list.append(comment)