python练习代码12

# -*- coding:utf-8 -*-
import urllib
import requests
import re
import os
 
def getHtml(url):
    html = requests.get(url).text  
    #requests.get(url)  拿到这个网址的信息  .text  则是把网页信息以文本形式输出
    # urls = re.findall('"objURL":"(.*?jpg)|(.*?JPG)"',html, re.S)
    # urls = re.findall('"objURL":"(.*?jpg|JPG)"',html, re.S)
    
    # urls = re.findall('"objURL":"(.*?.jpg)"',html, re.S)
    urls = list()

    # urls = re.findall('"objURL":"(\S*?jpg)"',html, re.S)  


    # urls = re.findall('"objURL":"(\S*?jpg)"|"objURL":"(\S*?JPG)"',html, re.S)

    urls = re.findall('"objURL":"(\S*?jpg|\S*?JPG)"',html, re.S)  #能够识别jpg 和JPG

    # urls = re.findall('"objURL":"(\S*?jpg)"',html, re.S)
    
    # my_jpg = re.compile('"objURL":"(.*?jpg)"',re.I)
    # urls = re.findall(my_jpg.match,html, re.S)
     #匹配正则条件 / 匹配的目标文件 / 使用re.S参数以后，正则表达式会将这个字符串作为一个整体，在整体中进行匹配。
    return urls
    #urls的返回值就是一串串的字符串
    

a = getHtml('http://image.baidu.com/search/index?tn=baiduimage&ps=1&ct=201326592&lm=-1&cl=2&nc=1&ie=utf-8&word=动态壁纸')
print(a)
# pattern = re.compile(r'([a-z]+) ([a-z]+)', re.I)  # re.I 表示忽略大小写
# m = pattern.match('Hello World Wide Web')
# print(m)