from urllib import request
import urllib
import re
#网页版有道翻译是ajax的post请求。
#浏览器请求地址http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule
#但是在抓取时,路径有所变化,具体原因不明。后续要了解下 translate_o -》 translate
url = "http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule"
#搜狗浏览器的 模拟浏览器
header = {"user-agent":
"mozilla/5.0 (windows nt 10.0; wow64) applewebkit/537.36 (khtml, like gecko) chrome/58.0.3029.110 safari/537.36 se 2.x metasr 1.0"
}
key = str(input("请输入要翻译的词语:"))
#key = "中国"
#这个formdata是浏览器发送请求copy过来的
formdata = {
"i":key,
"from":"auto",
"to":"auto",
"smartresult":"dict",
"client":"fanyideskweb",
"salt":"15536694414373",
"sign":"cddcc6c6092b57a04c546a2e075e2218",
"ts":"1553669441437",
"bv":"f355c521b6e13c15aa35c72a097b7786",
"doctype":"json",
"version":"2.1",
"keyfrom":"fanyi.web",
"action":"fy_by_realtlme",
"typoresult":"false"
}
data = urllib.parse.urlencode(formdata).encode(encoding = 'utf-8')
#当请求中存在data时就属于post请求
req = request.request(url, data = data , headers= header)
result = request.urlopen(req).read().decode()
print(result)
#用正则取出有用数
pattern = r'"tgt":"(.*?)"}'
va = re.findall(pattern, result)
print(va)
如对本文有疑问, 点击进行留言回复!!
Anaconda(python3.7)+pytorch(1.5.1)急速安装(2020.7.11日安装教程)
网友评论