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

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

url = "http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule&sessionFrom=https://www.baidu.com/link"
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)

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

import urllib.request
import urllib.parse
import json
import time
import hashlib

while True:

    #sign登录准备阶段  获取content--------------------------------------
    content = input("请输入要翻译的内容，0退出：")
    if content == '0':
        break
    
    #sign登录准备阶段  获取url------------------------------------------
    url = 'http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule&sessionFrom=dict2.top'

    #sign登录准备阶段  获取client---------------------------------------
    client = 'fanyideskweb'

    #sign登录准备阶段  获取salt-----------------------------------------
    salt = str(int(time.time()*1000))

    #sign登录准备阶段  获取mkey-----------------------------------------
    mkey = "rY0D^0'nM0}g5Mm1z%1G4"

    #制作sign信息-------------------------------------------------------
    sign = hashlib.md5()
    sign.update((client + content + salt + mkey).encode('utf-8'))
    
    #data表单填写-------------------------------------------------------
    data = {}
    data['i'] = content
    data['from'] = 'AUTO'
    data['to'] = 'AUTO'
    data['smartresult'] = 'dict'
    data['client'] = client
    data['salt'] = salt
    data['sign'] = sign.hexdigest()
    data['doctype'] = 'json'
    data['version'] = '2.1'
    data['keyfrom'] = 'fanyi.web'
    data['action'] = 'FY_BY_CLlCKBUTTON'
    data['typoResult'] = 'true'
    data = urllib.parse.urlencode(data).encode('utf-8')
    #encode 硬性编码：将uicode换成其他格式（utf-8）
    
    #headers填写--------------------------------------------------------
    head = {}
    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'
    #另一种方法
    #res.add_headers('key','value')urlopen不能已经指定headers
    #head['Host'] = 'fanyi.youdao.com'#未知 这句可以不要
    head['Referer'] = 'http://fanyi.youdao.com/'#未知

    #访问网页-----------------------------------------------------------
    req = urllib.request.Request(url,data,head)
    res = urllib.request.urlopen(req)
    #不能写成下面的缩略版 原因应该是无法自动转换
    #res = urllib.request.urlopen(url,data,head)
    html = res.read().decode('utf-8')
    #decode 将 utf-8 转换成 unicode

    #输出结果-----------------------------------------------------------
    target = json.loads(html)
    print("翻译结果：%s\n" % (target['translateResult'][0][0]['tgt']))