问题描述: 从试试一张图片的下载,到单页的图片下载,到单个栏目的下载(代码如下)
基本简单,最粗糙的代码
# 1: 引包
import time
import urllib.request
import re
import os
# 2: 请求得到响应
rootURL = "http://www.netbian.com"
url = "http://www.netbian.com/fengjing/"
response = urllib.request.urlopen(url)
# 3: 获得状态码
print(response.getcode())
# 4: 获取内容并编码
content = response.read().decode("GBK")
imgUrlList = re.finditer('(?<=(<li><a href=")).*?(?=")', content)
urlArr = []
insertStr = "-1920x1080.htm"
for url in imgUrlList: # 把每张图片的 1920 * 1080 的链接放进数组
url = url.group()
if url.find("desk") > 0:
url = rootURL + url
tempUrl = url.split(".htm")
tempUrl.insert(1, insertStr