简单爬虫进行拼音转汉字

论坛里面有人用想用搜索引擎进行拼音转汉字。

目前已经有了百度的代码，就是要修改为google。

很简单的东西，用urllib2+beautifulsoup就是分分钟的事情，但是考虑到这个哥们估计不会安装beautifulsoup，所以还是用re来解决：

#!/usr/bin/env python
# -*- coding: utf_8 -*-

import re
from urllib2 import Request, urlopen

headers = {
    'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
    'Accept-Language':'en-US,en;q=0.8,zh-TW;q=0.6,zh;q=0.4,ja;q=0.2',
    'Cache-Control':'max-age=0',
    'Connection':'keep-alive',
    'DNT':'1',
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.87 Safari/537.36',
}  
url_base = "https://www.google.co.jp/search?site=&source=hp&q=%s&oq=%s"

def getpage(url):
    response = urlopen(Request(url = url,headers = headers), timeout = 60) 
    return response.read()

def han(keyword):
    page = getpage(url_base % (keyword, keyword))
    result = re.findall('<a class="spell" href=.*?><em>(.*?)</em></a>', page) 
    ret = result[0] if len(result)>0 else ""
    return ret

def getwords(input_file):
    with open(input_file) as f:
        raw_text = f.readlines()
    return [i.strip() for i in raw_text]


if __name__ == "__main__":
    input_file  = '三拼四拼.txt'
    output_file = input_file.replace('.txt','_cn.txt')
    words = getwords(input_file)

    with open(output_file, 'w') as f:
        for word in words:
            cn = han(word)
            print '%s:%s\n'% (word, cn)
            f.write('%s:%s\n'% (word, cn))
    print '\n Done.'