[已解决]爬虫

月魔同学

1. <div>import urllib.request
   
2. import urllib.parse
   
3. import json
   
4. import time</div><div>while True:
   
5.     </div><div>    content=input('请输入要翻译的内容（如果结束请输入q）：')
   
6.     if content=='q':
   
7.         break
   
8.     head={}
   
9.     head['User-Agent']='Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3706.400 SLBrowser/10.0.4040.400'</div><div>    url='http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'
   
10.     data={'i':content,
    
11.         'from':'AUTO',
    
12.         'to':'AUTO',
    
13.         'smartresult':'dict',
    
14.         'client':'fanyideskweb',
    
15.         'salt':'15966771704905',
    
16.         'sign': '8634c91db8413ef4cfbe684fd030d518',
    
17.         'ts': '1596677170490',
    
18.         'bv': 'd16528ec6ead722121051f646932f6ab',
    
19.         'doctype': 'json',
    
20.         'version': '2.1',
    
21.         'keyfrom': 'fanyi.web',
    
22.         'action':'FY_BY_REALTlME'}
    
23.     data=urllib.parse.urlencode(data).encode('utf-8')</div><div>    response=urllib.request.urlopen(url,data,head)
    
24.     html=response.read().decode('utf-8')</div><div>    target=json.loads(html)</div><div>    target=target['translateResult'][0][0]['tgt']</div><div>    print(target)
    
25.     time.sleep(5)
    
26. 
    
27. </div>

复制代码

结果：
======================= RESTART: E:\python\程序\54_有道翻译.py =======================
请输入要翻译的内容（如果结束请输入q）我爱你
Traceback (most recent call last):
  File "E:\python\程序\54_有道翻译.py", line 31, in <module>
    response=urllib.request.urlopen(url,data,head)
  File "D:\python\lib\urllib\request.py", line 222, in urlopen
    return opener.open(url, data, timeout)
  File "D:\python\lib\urllib\request.py", line 525, in open
    response = self._open(req, data)
  File "D:\python\lib\urllib\request.py", line 542, in _open
    result = self._call_chain(self.handle_open, protocol, protocol +
  File "D:\python\lib\urllib\request.py", line 502, in _call_chain
    result = func(*args)
  File "D:\python\lib\urllib\request.py", line 1348, in http_open
    return self.do_open(http.client.HTTPConnection, req)
  File "D:\python\lib\urllib\request.py", line 1319, in do_open
    h.request(req.get_method(), req.selector, req.data, headers,
  File "D:\python\lib\http\client.py", line 1230, in request
    self._send_request(method, url, body, headers, encode_chunked)
  File "D:\python\lib\http\client.py", line 1276, in _send_request
    self.endheaders(body, encode_chunked=encode_chunked)
  File "D:\python\lib\http\client.py", line 1225, in endheaders
    self._send_output(message_body, encode_chunked=encode_chunked)
  File "D:\python\lib\http\client.py", line 1004, in _send_output
    self.send(msg)
  File "D:\python\lib\http\client.py", line 944, in send
    self.connect()
  File "D:\python\lib\http\client.py", line 915, in connect
    self.sock = self._create_connection(
  File "D:\python\lib\socket.py", line 793, in create_connection
    sock.settimeout(timeout)
TypeError: an integer is required (got type dict)

小甲鱼视频的程序，不知道为什么会是类型错误？Data就是从Form Date 复制过来的
类型错误:需要一个整数(获取类型dict)

最佳答案

月排行榜 / 总排行榜

Twilight6

2020-8-6 10:54:33

月魔同学 发表于 2020-8-6 10:52

urlopen 不能直接加 headers ，你需要先 Request

还有url 中的 _o 需要去掉，否则会出现 error:50 的假网址内容

1. import urllib.request
   
2. import urllib.parse
   
3. import json
   
4. import time
   
5. while True:
   
6.     content=input('请输入要翻译的内容（如果结束请输入q）：')
   
7.     if content=='q':
   
8.         break
   
9.     head={}
   
10.     head['User-Agent']='Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3706.400 SLBrowser/10.0.4040.400'
    
11.     url='http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule'
    
12.     data={'i':content,
    
13.         'from':'AUTO',
    
14.         'to':'AUTO',
    
15.         'smartresult':'dict',
    
16.         'client':'fanyideskweb',
    
17.         'salt':'15966771704905',
    
18.         'sign': '8634c91db8413ef4cfbe684fd030d518',
    
19.         'ts': '1596677170490',
    
20.         'bv': 'd16528ec6ead722121051f646932f6ab',
    
21.         'doctype': 'json',
    
22.         'version': '2.1',
    
23.         'keyfrom': 'fanyi.web',
    
24.         'action':'FY_BY_REALTlME'}
    
25.     data=urllib.parse.urlencode(data).encode('utf-8')
    
26.     req = urllib.request.Request(url,data=data,headers=head)
    
27.     response=urllib.request.urlopen(req)
    
28.     html=response.read().decode('utf-8')
    
29.     target=json.loads(html)
    
30.     target=target['translateResult'][0][0]['tgt']
    
31.     print(target)
    
32.     time.sleep(5)

复制代码

跳转到最佳答案楼层

zltzlt

乱码了

月魔同学

1. import urllib.request
   
2. import urllib.parse
   
3. import json
   
4. import time
   
5. 
   
6. while True:
   
7.    
   
8. 
   
9.     content=input('请输入要翻译的内容（如果结束请输入q）')
   
10.     if content=='q':
    
11.         break
    
12.     head={}
    
13.     head['User-Agent']='Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3706.400 SLBrowser/10.0.4040.400'
    
14. 
    
15.     url='http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'
    
16.     data={'i':content,
    
17.         'from':'AUTO',
    
18.         'to':'AUTO',
    
19.         'smartresult':'dict',
    
20.         'client':'fanyideskweb',
    
21.         'salt':'15966771704905',
    
22.         'sign': '8634c91db8413ef4cfbe684fd030d518',
    
23.         'ts': '1596677170490',
    
24.         'bv': 'd16528ec6ead722121051f646932f6ab',
    
25.         'doctype': 'json',
    
26.         'version': '2.1',
    
27.         'keyfrom': 'fanyi.web',
    
28.         'action':'FY_BY_REALTlME'}
    
29.     data=urllib.parse.urlencode(data).encode('utf-8')
    
30. 
    
31.     response=urllib.request.urlopen(url,data,head)
    
32.     html=response.read().decode('utf-8')
    
33. 
    
34.     target=json.loads(html)
    
35. 
    
36.     target=target['translateResult'][0][0]['tgt']
    
37. 
    
38.     print(target)
    
39.     time.sleep(5)
    

复制代码

Twilight6

月魔同学 发表于 2020-8-6 10:52

urlopen 不能直接加 headers ，你需要先 Request

还有url 中的 _o 需要去掉，否则会出现 error:50 的假网址内容

1. import urllib.request
   
2. import urllib.parse
   
3. import json
   
4. import time
   
5. while True:
   
6.     content=input('请输入要翻译的内容（如果结束请输入q）：')
   
7.     if content=='q':
   
8.         break
   
9.     head={}
   
10.     head['User-Agent']='Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3706.400 SLBrowser/10.0.4040.400'
    
11.     url='http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule'
    
12.     data={'i':content,
    
13.         'from':'AUTO',
    
14.         'to':'AUTO',
    
15.         'smartresult':'dict',
    
16.         'client':'fanyideskweb',
    
17.         'salt':'15966771704905',
    
18.         'sign': '8634c91db8413ef4cfbe684fd030d518',
    
19.         'ts': '1596677170490',
    
20.         'bv': 'd16528ec6ead722121051f646932f6ab',
    
21.         'doctype': 'json',
    
22.         'version': '2.1',
    
23.         'keyfrom': 'fanyi.web',
    
24.         'action':'FY_BY_REALTlME'}
    
25.     data=urllib.parse.urlencode(data).encode('utf-8')
    
26.     req = urllib.request.Request(url,data=data,headers=head)
    
27.     response=urllib.request.urlopen(req)
    
28.     html=response.read().decode('utf-8')
    
29.     target=json.loads(html)
    
30.     target=target['translateResult'][0][0]['tgt']
    
31.     print(target)
    
32.     time.sleep(5)

复制代码