Python爬虫系列之某个人站点信息爬取

Python爬虫系列之某个人站点信息爬取

代码仅供学习交流，请勿用于非法用途

小程序爬虫接单、app爬虫接单、网页爬虫接单、接口定制、网站开发、小程序开发 > 点击这里联系我们 <

微信请扫描下方二维码

• 以下为代码部分

import requests
import re

'''
    @Author:王磊
    @Time  :2018/11/15 15:29:06
'''


def getHTML(url):
    '''
    返回页面响应数据
    :param url:
    :return:
    '''
    res = requests.get(url)
    return res.content.decode(res.apparent_encoding, 'ignore')


def getImages(html):
    '''
    通过html获取图片地址，并处理拼接完整地址
    :param html:
    :return:
    '''
    pat = re.compile(r'')
    hostUrl = 'http://www.eastmountyxz.com/'
    urls = re.findall(pat, html)
    index = 0
    for url in urls:
        urls[index] = hostUrl + url[2:]
        index += 1
    return urls


def getArticals(html):
    '''
    通过html获取文章内容
    :param html:
    :return:
    '''
    pat_title_url = re.compile(r'
(.*?)
')
    res_tuple = re.findall(pat_title_url, html)
    pat_content = re.compile(r'
(.*?)
', re.S)
    res_contents = re.findall(pat_content, html)
    index = 0
    res = []
    for _ in res_tuple:
        res.append([res_tuple[index][0], res_tuple[index][1], res_contents[index]])
        index += 1
    return res


def getUserInfo(html):
    '''
    通过html获取个人信息
    :param hmtl:
    :return:
    '''
    pat = re.compile(r'
(.*?)
')
    info = re.findall(pat, html)
    return info


def run():
    '''
    主函数
    :return:
    '''
    url = 'http://www.eastmountyxz.com'
    html = getHTML(url)
    '''获取数据部分'''
    imgURLs = getImages(html)
    articalContent = getArticals(html)
    info = getUserInfo(html)
    '''打印数据部分'''
    for _ in range(len(articalContent)):
        print("第%d篇文章：" % (_ + 1))
        print("文章标题：%s" % articalContent[_][1])
        print("文章内容：%s" % articalContent[_][2])
        print("Url地址：%s" % articalContent[_][0])
        print("\r\n")

    print("用户个人信息：")
    for _ in info:
        print(_)
    '''图片下载部分'''
    index = 0
    for _ in imgURLs:
        resp = requests.get(_)
        with open("c:Users/asus/Desktop/pc/img/" + str(index) + ".gif", "wb") as f:
            f.write(resp.content)
            f.close()
        index += 1


if __name__ == '__main__':
    run()