pyton 爬虫-图片

emptyimport urllib.request
import urllib.response
import os
import re

baseDir = os.path.dirname(os.path.abspath(__file__))#os.path.abspath(__file__)当前绝对路径os.path.dirname(path) 返回path的目录
imgDir = os.path.join(baseDir,"img")# os.path.join 将多个路径组合后返回
url = "http://www.sccnn.com"
user_agent = ''
def getHtmlContent(url):
    page = urllib.request.Request(url)
    response = urllib.request.urlopen(page)
    content = response.read().decode("gbk")
    #print(content)
    return content

def getImg(html):
    imglist = re.findall('src="(.+?\.jpg)', html)#正则匹配图片路径
    i = 10
    for imgurl in imglist:#遍历url
        #imghttplist = "https:%s" % imgurl
        imghttplist = "%s" % imgurl
        urllib.request.urlretrieve( imghttplist, '%s/%s.jpg'%(imgDir,i))
        print("\033[32;1m -------第%s张----\033[0m"%i)
        i+=1
htmlconent = getHtmlContent(url)
getImg(htmlconent)