Python---爬取糗事百科的数据

2019独角兽企业重金招聘Python工程师标准>>>

爬取糗事百科的数据

def getData(url):
    try:
        req = urllib.request.Request(url)
        req.add_header("User-Agent", "Moz+illa/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.87 Safari/537.36")
        data = urllib.request.urlopen(req).read().decode('utf-8')
        # 过滤用户头像、用户名称
        pattrn1 = '<img src="//(.*?)" alt="(.*?)">'
        result1 = re.compile(pattrn1).findall(data)
        # 过滤性别、年龄
        pattrn2 = '<div class="articleGender (.*?)">(\d+)</div>'
        result2 = re.compile(pattrn2).findall(data)
        print(result1)
        print(result2)
    except urllib.error.URLError as e:
        if hasattr(e, "code"):
            print(e.code)
        if hasattr(e, "reason"):
            print(e.reason)


for i in range(1, 2):
    url = "https://www.qiushibaike.com/8hr/page/"+str(i)
    getData(url)

 

转载于:https://my.oschina.net/quguangle/blog/1840499