Python: 封装版本爬取虎扑篮球图片

本文是上一篇的续后期将进行封装，以提高可用性。

虎扑在展示图片的时候偷懒了，直接给出了原图链接，直接获取这个链接，下载到本地即可。

这里使用PhantomJS来打开浏览器。

使用urllib2下载图片

# download one picture by urllib2
def downloadPicture(pic_url, pic_path):
    f = urllib2.urlopen(pic_url)
    with open(pic_path, "wb") as img_file:
        img_file.write(f.read())

逐个获取每个图片

def getPictures(elem_url, nums, path):
    try:
        count = 1
        t = elem_url.find(r'.html')
        while (count <= nums):
            html_url = elem_url[:t-2] + '-' + str(count) + '.html'
            # Set proxy
            proxy_support = urllib2.ProxyHandler({"http": "http://yout_proxy:8080/"})
            opener = urllib2.build_opener(proxy_support)
            urllib2.install_opener(opener)
            driver.get(html_url)
            elem = driver.find_element_by_xpath("//div[@class='pic_bg']/div/img")
            url = elem.get_attribute("src")
            file_name = os.path.basename(url).replace('*','')
            fname = path + "\\" + file_name
            downloadPicture(url, fname)
            count += 1
    except Exception, e:
        print "Error: ", e
    finally:
        print "Download " + str(count-1) + ' pictures\n'

主程序

if __name__ == "__main__":
    elem_url = "http://photo.hupu.com/nba/p29556-1.html"
    nums = 15
    # Create folder for store picture
    sub_folder = os.path.join(os.getcwd(), "hupupic")
    if not os.path.exists(sub_folder):
        os.mkdir(sub_folder)
    # os.chdir(sub_folder)
    pic_path = sub_folder
    getPictures(elem_url, nums, pic_path)