python爬取图书信息_python爬虫之爬取豆瓣top250图书信息

先上代码：

import requests

from bs4 import BeautifulSoup

import time

class top250books():

def html(self, href):

max_span = 225

for page in range(0, int(max_span), 25):

page_url = href + '?start=' + str(page)

self.parse(page_url)

def parse(self, url):

html = self.request(url)

all_tables = BeautifulSoup(html.text, 'lxml').find('div', class_='indent').find_all('table')

for table in all_tables:

time.sleep(0.5)

title = table.find('div', class_='pl2').find('a').get_text()

info = table.find('p', class_='pl').get_text()

rating_nums = table.find('span', class_='rating_nums').get_text()

rating_people = table.find('span', class_='pl