urllib通过Post请求爬去数据并解析JSON（Python）

1.   封装的请求post函数：

def downloadPostPage(url, dictdata, headers, charset='utf-8', reqnum=5):
    data = bytes(parse.urlencode(dictdata), encoding=charset)
    req = request.Request(url, data, headers=headers,method='POST')
    info= None
    try:
        response = request.urlopen(req)
        info = response.read().decode(charset)
    except error.HTTPError as e:
        # 服务器错误
        print(e.code)
        if reqnum > 0:
            if hasattr(e, 'code') and 500 <= e.code <= 600:
                time.sleep(random.randint(5, 11))
                downloadPostPage(url,dictdata,headers, charset=charset, reqnum=reqnum-1)
    except error.URLError:
        print("url error")
    return info

2.   主函数的实现：

if __name__ == '__main__':
    url = 'http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule&smartresult=ugc&sessionFrom=null'
    headers = {
        "Accept": "application/json, text/javascript, */*; q=0.01",
        "X-Requested-With": "XMLHttpRequest",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:45.0) Gecko/20100101 Firefox/45.0",
        "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
    }
    while True:
        key = input('输入搜索词：')
        if not key:
            break
        dictdata = {
            "i": key,
            "from": "auto",
            "to": "auto",
            "smartresult": "dict",
            "client": "fanyideskweb",
            "salt": "1511219405946",
            "sign": "f8965f67a1d3eee8a69ddf8ccc5f582b",
            "doctype": "json",
            "version": "2.1",
            "keyfrom": "fanyi.web",
            "action": "FY_BY_REALTIME",
            "typoResult": "false"
        }
        info = downloadPostPage(url, dictdata, headers=headers,reqnum=1)
        jsonLoads = json.loads(info)
        print(jsonLoads)
        print(jsonLoads['translateResult'][0][0]['tgt'])