[python爬虫]爬取贴吧某页美女图片+爬取糗百美女图片

#coding:utf-8
import requests,pyquery,urllib
import re

def get_html(url):
	html=urllib.urlopen(url).read()
	return html


def get_image(html):
	reg=r'src="(.*?.jpg)"'
	#html=requests.get(url).read()
	result=re.compile(reg)
	aim=result.findall(html)
	i=0
	for imgurl in aim:
		urllib.urlretrieve(imgurl,'%s.jpg'%i)
		i+=1
html=get_html('http://tieba.baidu.com/p/2166231880')
print get_image(html)


#coding:UTF-8
from bs4 import BeautifulSoup
import requests
import urllib
import re
import os
url='http://www.qiubaichengren.com/'
def get_html(url):
	html=requests.get(url).text
	return html

def get_image(url):
	result=re.compile(r'src="(.*.jpg)"')
	i=0
	for n in range(1,679):
		page_url=url+'%d.html'%n
		html=get_html(page_url)
		aim=result.findall(html)
		for img_url in aim:
			urllib.urlretrieve(img_url,"/home/vincebye/Pictures/%s.jpg"%i)
			print '33[0;36;40m'
			print "正在下载第"+str(i)+"张图片,请稍等......."
			i+=1
			print '33[0m'
	
	


if __name__ == '__main__':
              get_image(url)
              

 耗时:1小时30分钟

错误原因:  IndentationError: unexpected indent  --Python及其要求代码格式对齐

                   request对象没有read()方法

                   是将read之后的网页拿去正则匹配

                   正则文法中()里面是我们匹配的目的,括号之外是描述词