python 爬虫求助

tcd700

debug 显示 {"errorCode":50}

import urllib.request    #这一行未高亮
import  urllib.parse

url = "http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule&sessionFrom=dict2.index"
data = {}
data['type'] = 'AUTO'
data['i'] = 'I love Fishc.com'
data['doctype'] = 'json'
data['XMLHttpRequest'] = '2.1'
data['keyfrom'] = 'fanyi.web'
data['ue'] = 'UTF-8'
data['typoResult'] = 'true'
data = urllib.parse.urlencode(data).encode('utf-8')
response = urllib.request.urlopen(url, data)
html = response.read().decode('utf-8')
print(html)

yongxi

求助之前请在论坛搜索相同问题的帖子。

这个问题在求助区出现已经不下10次了

ba21

接口已变。看代码的URL

1. import urllib.request    #这一行未高亮
   
2. import  urllib.parse
   
3. 
   
4. url = "http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule&sessionFrom=https://www.baidu.com/link"
   
5. data = {}
   
6. data['type'] = 'AUTO'
   
7. data['i'] = 'I love Fishc.com'
   
8. data['doctype'] = 'json'
   
9. data['XMLHttpRequest'] = '2.1'
   
10. data['keyfrom'] = 'fanyi.web'
    
11. data['ue'] = 'UTF-8'
    
12. data['typoResult'] = 'true'
    
13. data = urllib.parse.urlencode(data).encode('utf-8')
    
14. response = urllib.request.urlopen(url, data)
    
15. html = response.read().decode('utf-8')
    
16. print(html)
    

复制代码

ooxx7788

http://bbs.fishc.com/thread-88062-1-1.html

看这个吧

tcd700

ooxx7788 发表于 2017-7-28 10:33
http://bbs.fishc.com/thread-88062-1-1.html

看这个吧

非常感谢

tcd700

yongxi 发表于 2017-7-27 21:56
求助之前请在论坛搜索相同问题的帖子。

这个问题在求助区出现已经不下10次了

不太会描述这个问题

基尔

1. import urllib.request
   
2. import urllib.parse
   
3. import json
   
4. import time
   
5. import hashlib
   
6. 
   
7. while True:
   
8. 
   
9.     #sign登录准备阶段  获取content--------------------------------------
   
10.     content = input("请输入要翻译的内容，0退出：")
    
11.     if content == '0':
    
12.         break
    
13.    
    
14.     #sign登录准备阶段  获取url------------------------------------------
    
15.     url = 'http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule&sessionFrom=dict2.top'
    
16. 
    
17.     #sign登录准备阶段  获取client---------------------------------------
    
18.     client = 'fanyideskweb'
    
19. 
    
20.     #sign登录准备阶段  获取salt-----------------------------------------
    
21.     salt = str(int(time.time()*1000))
    
22. 
    
23.     #sign登录准备阶段  获取mkey-----------------------------------------
    
24.     mkey = "rY0D^0'nM0}g5Mm1z%1G4"
    
25. 
    
26.     #制作sign信息-------------------------------------------------------
    
27.     sign = hashlib.md5()
    
28.     sign.update((client + content + salt + mkey).encode('utf-8'))
    
29.    
    
30.     #data表单填写-------------------------------------------------------
    
31.     data = {}
    
32.     data['i'] = content
    
33.     data['from'] = 'AUTO'
    
34.     data['to'] = 'AUTO'
    
35.     data['smartresult'] = 'dict'
    
36.     data['client'] = client
    
37.     data['salt'] = salt
    
38.     data['sign'] = sign.hexdigest()
    
39.     data['doctype'] = 'json'
    
40.     data['version'] = '2.1'
    
41.     data['keyfrom'] = 'fanyi.web'
    
42.     data['action'] = 'FY_BY_CLlCKBUTTON'
    
43.     data['typoResult'] = 'true'
    
44.     data = urllib.parse.urlencode(data).encode('utf-8')
    
45.     #encode 硬性编码：将uicode换成其他格式（utf-8）
    
46.    
    
47.     #headers填写--------------------------------------------------------
    
48.     head = {}
    
49.     head['User-Agent'] = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.87 Safari/537.36 QQBrowser/9.2.5583.400'
    
50.     #另一种方法
    
51.     #res.add_headers('key','value')urlopen不能已经指定headers
    
52.     #head['Host'] = 'fanyi.youdao.com'#未知 这句可以不要
    
53.     head['Referer'] = 'http://fanyi.youdao.com/'#未知
    
54. 
    
55.     #访问网页-----------------------------------------------------------
    
56.     req = urllib.request.Request(url,data,head)
    
57.     res = urllib.request.urlopen(req)
    
58.     #不能写成下面的缩略版 原因应该是无法自动转换
    
59.     #res = urllib.request.urlopen(url,data,head)
    
60.     html = res.read().decode('utf-8')
    
61.     #decode 将 utf-8 转换成 unicode
    
62. 
    
63.     #输出结果-----------------------------------------------------------
    
64.     target = json.loads(html)
    
65.     print("翻译结果：%s\n" % (target['translateResult'][0][0]['tgt']))
    

复制代码