使用python3爬取数据至mysql

最新推荐文章于 2024-04-22 11:23:15 发布

原创最新推荐文章于 2024-04-22 11:23:15 发布 · 1.3k 阅读

3 ·

CC 4.0 BY-SA版权

python 专栏收录该内容

16 篇文章

订阅专栏

本文介绍了一个使用Python编写的简单爬虫程序，该程序能够从维基百科抓取页面标题和内容，并将其存储到MySQL数据库中。爬虫通过Beautiful Soup解析网页，遵循随机链接进行抓取。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

直接贴代码

#!/usr/local/bin/python3.5
# -*- coding:UTF-8 -*-
from urllib.request import urlopen
from bs4 import BeautifulSoup
import re
import datetime
import random
import pymysql

connect = pymysql.connect(host='192.168.10.142', unix_socket='/tmp/mysql.sock', user='root', passwd='1234', db='scraping', charset='utf8')
cursor = connect.cursor()
cursor.execute('USE scraping')

random.seed(datetime.datetime.now())


def store(title, content):

    execute = cursor.execute("select * from pages WHERE `title` = %s", title)
    if execute <= 0:
        cursor.execute("insert into pages(`title`, `content`) VALUES(%s, %s)", (title, content))
        cursor.connection.commit()
    else:
        print('This content is already exist.')


def get_links(acticle_url):
    html = urlopen('http://en.wikipedia.org' + acticle_url)
    soup = BeautifulSoup(html, 'html.parser')
    title = soup.h1.get_text()
    content = soup.find('div', {'id': 'mw-content-text'}).find('p').get_text()
    store(title, content)
    return soup.find('div', {'id': 'bodyContent'}).findAll('a', href=re.compile("^(/wiki/)(.)*$"))

links = get_links('')

try:
    while len(links) > 0:
        newActicle = links[random.randint(0, len(links) - 1)].attrs['href']
        links = get_links(newActicle)
        print(links)
finally:
    cursor.close()
    connect.close()