xingtai - 学习爬取脑经急转弯的高级爬虫

import requests
idw = 0
idd = 0
for xyz in range(75):
    try:
        url = "http://www.2345.com/inner/jzw/%s.htm"%xyz
        jzw = requests.get(url).content.decode("GB2312")
        # print(jzw)
        import re
        nr = re.findall('<li><span class="table_left">(.*)点击显示答案</a></span></li>',jzw)

        for i in nr:
            print("--------------这是第%d道题题目---------------"%idw)
            idw = idw + 1
            question = re.findall("(.*)</span><span class=", i)
            print(question[0])
           # with open("脑经急转弯问题大全.txt", "a+") as f:
              #  f.write(question[0]+"\n")

        for i in nr:
            print("--------------这是第%d道题答案---------------"%idd)
            idd = idd + 1
            da = re.findall('MM_popupMsg(.*)">', i)
            print(da[0])
            with open("脑筋急转弯答案大全.txt","a+") as f:
                f.write(da[0]+"\n")
    except:
        print("第%d页报错了"%xyz)