本帖最后由 949825667@qq.co 于 2016-8-25 10:23 编辑
自己用正则匹配了一下,没有得到完美的效果,有木有更好的正则匹配
我这个写法会连<a href="javascript:void(0);"class="century21" title="来源于21世纪大英汉词典"> </a>也匹配到 | import urllib.request | | | | import bs4 | | import re | | | | | | def trans(f): | | searchUrl = "http://dict.youdao.com/search?q=" + f + "&keyfrom=dict.index" | | web = urllib.request.urlopen(searchUrl) | | soup = bs4.BeautifulSoup(web, "html.parser") | | homegrids = soup.find(id='wordGroup') | | a = homegrids.find_all('a') | | print(homegrids.find_all('a')) | | for i in a: | | print(i.string) | | for j in homegrids: | | results = re.findall(r'.*</span>(.*)</p>', str(j), re.S) | | | | for result in results: | | print(result) | | def main(): | | f = input('') | | trans(f) | | | | if __name__ == '__main__': | | main()COPY |
|