python.beatifulsoup入门

python.beatifulsoup入门

最先想试试python的爬虫功能，于是用easy_install安装了beautifulsoup，下面是我写的demo代码，可以简单看看

#coding=utf-8

import urllib2
from BeautifulSoup import BeautifulSoup as bs

url_addr = 'http://car.autohome.com.cn/baoyang/detail_74_442_0_0_0_57.html'

def save_to_file(content, fileName):
	with open(fileName, 'w+') as f:
		if not f:
			return False
		f.write(content)
		f.close()

def parse_content(content):
	soup = bs(content)
	tds = soup.findAll('td')
	for i in tds:
		print i.text
	
		
def is_unicode(c):
	if isinstance(c, unicode):
		return True
	return False

def is_asii(c):
	if isinstance(c, str):
		return True
	return False
	
if __name__ == '__main__':
	
	content = urllib2.urlopen(url_addr).read()
	
	#对于任何格式的str先转换为中间编码unicode
	#调用decode转换为unicode编码【根据自身的编码】
	#然后再调用encode将unicode转换为指定的编码
	
	#将content【编码为gb2312】转换为unicode编码
	c = content.decode('gb2312')
	
	print('c is unicode:', is_unicode(c))
	#print(c)
	save_to_file(c.encode('gb2312'), 'd:/content.html')
	parse_content(content)