Python爬虫之requests

python爬虫之requests

在python中使用requests简化了网络请求，在使用requests之前需要pip install requests来安装requests,requests中文手册是一个很好的入门资料。
制作爬虫需要对html的结构有一定的了解，同时使用正则表达式原生匹配的爬虫也会随网页结构的改变而失效，所以若使下述代码无效，请分析网页的结构是否发生了改变。
抓取网页：极客学院视频库网页
爬取效果：

# -*-coding:utf-8 -*-
import requests
import re
import sys

''' 1.先获取整个网页 2.获取整个网页中的课程块 3.通过正则表达使获取想要的特定内容 '''


class spider(object):
    def __init__(self):
        print(u'开始爬取内容...')


    # 用于获取网页的源代码
    def getsource(self, url):
        html = requests.get(url)
        html.encoding = 'utf-8'
        return html.text

    # 改变链接中的页码数
    def changepage(self, url, total_page):
        now_page = int(re.search('pageNum=(\d+)', url, re.S).group(1))  # 返回页码数
        page_group = []
        for i in range(now_page, total_page + 1):
            link = re.sub('pageNum=\d+', 'pageNum=%s' % i, url, re.S)  # 替换url中的页码数
            page_group.append(link)
        return page_group

    # 抓取每个课程块消息
    def geteveryclass(self, source):
        everyclass = re.findall('(<li id=".*?</li>)', source, re.S)
        return everyclass

    # 从课程块中得到我们想要的信息
    def getinfo(self, eachclass):
        info = {}
        info['title'] = re.search('.*>(.*?)</a></h2>', eachclass, re.S).group(1)
        info['content'] = re.search('.*>(.*?)</p>', eachclass, re.S).group(1).strip()
        timeandlevel = re.findall('<em>(.*?)</em>', eachclass, re.S)
        classtime = timeandlevel[0].split()  # 截取字符中的空格
        info['classtime'] = classtime[0] + classtime[1]
        info['classlevel'] = timeandlevel[1]
        info['learnnum'] = re.search('"learn-number">(.*?)</em>', eachclass, re.S).group(1)
        return info

    def saveinfo(self, classinfo):
        f = open('info.txt', 'a', encoding='utf-8')
        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=2'
    jikespider = spider()
    all_links = jikespider.changepage(url, 20)
    print(all_links)
    for link in all_links:
        print(u'正在处理页面：' + link)
        html = jikespider.getsource(link)
        everyclass = jikespider.geteveryclass(html)
        for each in everyclass:
            info = jikespider.getinfo(each)
            classinfo.append(info)
    jikespider.saveinfo(classinfo)

转载于:https://my.oschina.net/u/3592080/blog/1236272