|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
本帖最后由 jiacce 于 2017-6-1 18:04 编辑
- import urllib.request
- import urllib.parse
- import re
- from bs4 import BeautifulSoup
- def main():
- keyword = input("请输入关键词:")
- keyword = urllib.parse.urlencode({"word":keyword})
- response = urllib.request.urlopen("http://baike.baidu.com/search/word?%s" % keyword)
- html = response.read()
- soup = BeautifulSoup(html,"html.parser")
- for each in soup.find_all(href = re.compile("item")):
- content = ''.join([each.text])
- url2 = ''.join(["http://baike.baidu.com",each["href"]])
- response2 = urllib.request.urlopen(url2)
- html2 = response2.read()
- soup2 = BeautifulSoup(html2,"html.parser")
- if soup2.h2:
- content = ''.join([content,soup2.h2.text])
- content = ''.join([content,"-->",url2])
- print(content)
- if __name__ == "__main__":
- [code]Traceback (most recent call last):
- File "F:\python34\libs\pl4_92.py", line 30, in <module>
- main()
- File "F:\python34\libs\pl4_92.py", line 20, in main
- response2 = urllib.request.urlopen(url2)
- File "F:\python34\lib\urllib\request.py", line 161, in urlopen
- return opener.open(url, data, timeout)
- File "F:\python34\lib\urllib\request.py", line 464, in open
- response = self._open(req, data)
- File "F:\python34\lib\urllib\request.py", line 482, in _open
- '_open', req)
- File "F:\python34\lib\urllib\request.py", line 442, in _call_chain
- result = func(*args)
- File "F:\python34\lib\urllib\request.py", line 1211, in http_open
- return self.do_open(http.client.HTTPConnection, req)
- File "F:\python34\lib\urllib\request.py", line 1183, in do_open
- h.request(req.get_method(), req.selector, req.data, headers)
- File "F:\python34\lib\http\client.py", line 1137, in request
- self._send_request(method, url, body, headers)
- File "F:\python34\lib\http\client.py", line 1172, in _send_request
- self.putrequest(method, url, **skips)
- File "F:\python34\lib\http\client.py", line 1014, in putrequest
- self._output(request.encode('ascii'))
- UnicodeEncodeError: 'ascii' codec can't encode characters in position 10-12: ordinal not in range(128)
复制代码
main()
[/code]
遇到特殊符号了,用try-except语句遍历跳过。
|
|