复杂的网页爬虫，python获取网页指的格式数据

た入场券 2022-09-29 04:08 132阅读 0赞

通过python 爬虫从网页上获取多页数标题、内容、时间、等级、学习人数等信息；

# -*-coding:utf-8 -*-
    ''' Created on 2017年3月13日 @author: July_whj '''
    import requests
    import sys
    import re 
    #由于网页编码是UTF-8 故将此设置称UTF-8编码，防止中文乱码；
    reload(sys)
    sys.setdefaultencoding('utf-8')
    #创建类
    class spjikexuey(object):
        def __init__(self):
            print"开始爬取网页内容。。。"
        #传递网页URL,返回整个页面源码；
        def getsourct(self,url):
            html = requests.get(url)
            return html.text
        #通过re.search 获取指定网页页数；page = 20 ;获取20页数据；返回20条URL;
        def chanegpage(self,url,page):
            now_page = int(re.search('pageNum=(\d+)', url, re.S).group(1))
            page_group = []
            for i in range(now_page,page):
                link = re.sub('pageNum=\d+', 'pageNum=%s'%i, url, re.S)
                page_group.append(link)
            return page_group
        #由getsourct()获取网页源码，通过geteveryclass()进行初步数据节选；缩小数据范围；返回筛选后的html
        def geteveryclass(self,source):
            everyclass = re.findall('li id="(.*?)</li>', source, re.S)
            return everyclass
        #获取标题、内容、时间、等级、学习人数等数据信息；并赋值到info集合
        def getinfo(self,eachclass):
            info = {}
            info['title'] = re.search('class="lessonimg" title="(.*?)" alt="', each, re.S).group(1)      
            info['content'] = re.search('display: none;">(.*?)</p>', each, re.S).group(1)
            timeandlevel = re.findall('<em>(.*?)</em>', each, re.S)
            info['classTime'] = timeandlevel[0]
            info['classlevel'] = timeandlevel[1]
            info['learnnum'] = re.search('"learn-number">(.*?)</em>', each, re.S).group(1)
            return info
        #将抓取数据出储存到info.txt中；
        def saveinfo(self,classinfo):
            f = open('info.txt','a')
            for each in classinfo:
                f.writelines('title:'+each['title']+'\n')
                f.writelines('content'+each['content']+'\n')
                f.writelines('classTime'+each['classTime']+'\n')
                f.writelines('classlevel'+each['classlevel']+'\n')
                f.writelines('learnnum'+each['learnnum']+'\n\n')
            f.close()
    
    if __name__ == "__main__":
        classinfo = []
        url = 'http://www.jikexueyuan.com/course/?pageNum=1'
        jikespider = spjikexuey()
        all_links = jikespider.chanegpage(url, 20)
        for link in all_links:
            print '正在处理页面：'+link
            html = jikespider.getsourct(link)
            print html
            everyclass = jikespider.geteveryclass(html)
            print everyclass
            for each in everyclass:
                info = jikespider.getinfo(each)
                classinfo.append(info)
            jikespider.saveinfo(classinfo)

![抓取后结果][SouthEast]

[SouthEast]: /images/20220708/529a44f2785743429a1c4998a4f4bfae.png