Python爬虫实现使用beautifulSoup4爬取名言网功能案例

柔情只为你懂 2023-07-16 03:50 26阅读 0赞

本文实例讲述了Python爬虫实现使用beautifulSoup4爬取名言网功能。分享给大家供大家参考，具体如下：

爬取名言网top10标签对应的名言，并存储到mysql中，字段（名言，作者，标签）

#! /usr/bin/python3
    # -*- coding:utf-8 -*-
    from urllib.request import urlopen as open
    from bs4 import BeautifulSoup
    import re
    import pymysql
    def find_top_ten(url):
      response = open(url)
      bs = BeautifulSoup(response,'html.parser')
      tags = bs.select('span.tag-item a')
      top_ten_href = [tag.get('href') for tag in tags]
      top_ten_tag = [tag.text for tag in tags]
      # print(top_ten_href)
      # print(top_ten_tag)
      return top_ten_href
    def insert_into_mysql(records):
      con = pymysql.connect(host='localhost',user='root',password='root',database='quotes',charset='utf8',port=3306)
      cursor = con.cursor()
      sql = "insert into quotes(content,author,tags) values(%s,%s,%s)"
      for record in records:
        cursor.execute(sql, record)
      con.commit()
      cursor.close()
      con.close()
    # http://quotes.toscrape.com/tag/love/
    #要获取对应标签中所有的名言 所以这里要考虑分页的情况
    #经过在网页上查看知道分页查询的url
    #http://quotes.toscrape.com/tag/love/page/1/
    #判断到那一页没有数据 div.container div.row [1]
    def find_link_content(link):
      page = 1
      while True:
        new_link = "http://quotes.toscrape.com" + link + "page/"
        # print(new_link)
        new_link = new_link + str(page)
        print(new_link)
        sub_bs = open(new_link)
        sub_bs = BeautifulSoup(sub_bs,'html.parser')
        quotes = sub_bs.select('div.row div.col-md-8 span.text')
        # 如果没有数据就退出
        if len(quotes) == 0:
          break
        #名言
        quotes = [quote.text.strip('“”') for quote in quotes]
        #作者
        authors = sub_bs.select('small.author')
        authors = [author.text for author in authors]
        # 标签
        tags_list = sub_bs.select('meta.keywords')
        tags_list = [tags.get('content') for tags in tags_list]
        # print(authors)
        # print(quotes)
        #print(tags_list)
        record_list = []
        for i in range(len(quotes)):
          tags = tags_list[i]
          tags = tags.replace(',','，')
          print(tags)
          record = [quotes[i],authors[i],tags]
          record_list.append(record)
        insert_into_mysql(record_list)
        page += 1
    #
    def main():
      url = "http://quotes.toscrape.com/"
      parent_link = find_top_ten(url)
      for link in parent_link:
        print(link)
        find_link_content(link)
    if __name__ == '__main__':
      main()

最后给大家推荐一个口碑不错的python聚集地【[点击进入][Link 1]】，这里有很多的老前辈学习技巧，学习心得，面试技巧，职场经历等分享，更为大家精心准备了零基础入门资料，实战项目资料，每天都有程序员定时讲解Python技术，分享一些学习的方法和需要留意的小细节

[Link 1]: https://jq.qq.com/?_wv=1027&k=5JIjRvv