爬取豆瓣前250本书籍信息

参考了这个哥们的思路:https://blog.csdn.net/qq_40123329/article/details/81807759

一共250本书，分10页展示，每页25本书。

每一个图书的信息：

豆瓣网每一个table中的源码格式：

 <table width="100%">
        <tr class="item">
          <td width="100" valign="top">
            <a class="nbg" href="https://book.douban.com/subject/1770782/"
              onclick="moreurl(this,{i:'0'})"
              >
              <img src="https://img3.doubanio.com/view/subject/m/public/s1727290.jpg" width="90" />
            </a>
          </td>
          <td valign="top">
            
            <div class="pl2">

              <a href="https://book.douban.com/subject/1770782/" onclick=&#34;moreurl(this,{i:&#39;0&#39;})&#34; title="追风筝的人"
                
              >
                追风筝的人
                
             </a>

                &nbsp; <img src="https://img3.doubanio.com/pics/read.gif" alt="可试读" title="可试读"/>
             
                <br/>
                <span style="font-size:12px;">The Kite Runner</span>
            </div>
              <p class="pl">[美] 卡勒德·胡赛尼 / 李继宏 / 上海人民出版社 / 2006-5 / 29.00元</p>
         
              
              <div class="star clearfix">
                  <span class="allstar45"></span>
                  <span class="rating_nums">8.9</span>

                <span class="pl">(
                    445012人评价
                )</span>
              </div>
           
              <p class="quote" style="margin: 10px 0; color: #666">
                  <span class="inq">为你，千千万万遍</span>
             </p>

          </td>
        </tr>
      </table>
        <p class="ul"></p>

代码实现：

from bs4 import BeautifulSoup
import re
import requests
import pandas as pd

def getHTMLText(url):
    try:
        kw = {'user-agent': 'chrome/10.0'}
        r = requests.get(url, params=kw)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        print('error')


def parseHTML(bookinfo, html):
    soup = BeautifulSoup(html, 'html.parser')
    tables = soup.findAll('table', {"width": "100%"})
    for table in tables:
        link = table.div.a['href']
        title = table.div.a.text.strip().replace('\n', '').replace(' ', '')
        people = table.find('span', {'class': 'pl'}).text.strip()
        people = re.findall(r'[0-9]+', people)[0]
        score = table.find('span', {'class': 'rating_nums'}).text.strip()
        detail = table.find('p', {"class": "pl"}).text
        if table.find('span', {"class": "inq"}):
            abstract = table.find('span', {"class": "inq"}).text.strip()
        else:
            abstract = 'no abstract'
        bookinfo.append([title, score, people, detail, abstract, link])
    return bookinfo


def saveInfo(bookinfo, path):
    a = pd.DataFrame(bookinfo, columns=['书籍名称', '豆瓣评分', '评价人数', '书籍信息', '书籍描述', '链接'])
    a.to_excel(path, index=False)


def main():
    book = []
    path = r'doubanbook2.xlsx'
    for i in range(10):
        bookinfo = []
        url = 'https://book.douban.com/top250?start='
        url = url + str(i * 25)
        print(url)
        html = getHTMLText(url)
        books = parseHTML(bookinfo, html)
        for i in range(len(books)):
            book.append(books[i])
    saveInfo(book, path)

main()

爬虫效果：