基于社交网络爬虫的人物兴趣属性分析（四）

def translate(content, fromLang='en', toLang='zh'):

salt = str(random.randint(32768, 65536))

sign = appid + content + salt + secretKey  #appid+q+salt+密钥 的MD5值

sign = hashlib.md5(sign.encode("utf-8")).hexdigest() #对sign做md5，得到32位小写的sign

#print(content)

try:

      #根据技术手册中的接入方式进行设定

paramas = {

'appid': appid,

'q': content,

'from': fromLang,

'to': toLang,

'salt': salt,

'sign': sign

}

response = requests.get(apiurl, paramas)

jsonResponse = response.json()  # 获得返回的结果，结果为json格式

      #print(jsonResponse)

dst = str(jsonResponse["trans_result"][0]["dst"])  # 取得翻译后的文本结果

return dst

except Exception as e:

print(e)

#!/usr/bin/env python

# -*- coding: utf-8 -*-

from __future__ import division

import jieba.analyse

from math import sqrt

from functools import reduce

import hashlib

import random

import openpyxl

from openpyxl import Workbook

import requests

apiurl = 'http://api.fanyi.baidu.com/api/trans/vip/translate'

appid = '20191231000371318'

secretKey = 'wMXgSdRsUI_XmGtf8JC2'

class Similarity():

def __init__(self, target1, target2, topK=10):

self.target1 = target1

self.target2 = target2

self.topK = topK

def vector(self):

self.vdict1 = {}

self.vdict2 = {}

      top_keywords1 = jieba.analyse.extract_tags(self.target1, topK=self.topK, withWeight=True)

      top_keywords2 = jieba.analyse.extract_tags(self.target2, topK=self.topK, withWeight=True)

for k, v in top_keywords1:

          self.vdict1[k] = v

for k, v in top_keywords2:

          self.vdict2[k] = v

def mix(self):

for key in self.vdict1:

          self.vdict2[key] = self.vdict2.get(key, 0)

for key in self.vdict2:

          self.vdict1[key] = self.vdict1.get(key, 0)

def mapminmax(vdict):

          """计算相对词频"""

_min = min(vdict.values())

_max = max(vdict.values())

_mid = _max - _min

#print _min, _max, _mid

for key in vdict:

              vdict[key] = (vdict[key] - _min)/_mid

return vdict

self.vdict1 = mapminmax(self.vdict1)

self.vdict2 = mapminmax(self.vdict2)

def similar(self):

      self.vector()

self.mix()

sum = 0

for key in self.vdict1:

sum += self.vdict1[key] * self.vdict2[key]

A = sqrt(reduce(lambda x,y: x+y, map(lambda x: x*x, self.vdict1.values())))

B = sqrt(reduce(lambda x,y: x+y, map(lambda x: x*x, self.vdict2.values())))

return sum/(A*B)

def translate(content, fromLang='en', toLang='zh'):

salt = str(random.randint(32768, 65536))

sign = appid + content + salt + secretKey  #appid+q+salt+密钥 的MD5值

sign = hashlib.md5(sign.encode("utf-8")).hexdigest() #对sign做md5，得到32位小写的sign

#print(content)

try:

      #根据技术手册中的接入方式进行设定

paramas = {

'appid': appid,

'q': content,

'from': fromLang,

'to': toLang,

'salt': salt,

'sign': sign

}

response = requests.get(apiurl, paramas)

jsonResponse = response.json()  # 获得返回的结果，结果为json格式

      #print(jsonResponse)

dst = str(jsonResponse["trans_result"][0]["dst"])  # 取得翻译后的文本结果

return dst

except Exception as e:

print(e)

def confir(str):

for i in range(0,32):

str = str.replace(chr(i),'')

for i in range(1000,200000):

str = str.replace(chr(i),'')

return  str

if __name__ == '__main__':

with open('weibo/孙燕姿.txt','r',encoding='utf-8') as f:

t1 = f.read().replace('[','').replace(']','').replace('\'','')

#t1=t1.split(',')

#print(list(t1))

with open('twitter/Stefsunyanzi.txt','r',encoding='utf-8') as f:

t2 = f.read().replace('[','').replace(']','').replace('\'','')

t2=confir(t2)

t2=translate(t2)

print(t2)

#t2=t2.split(',')

#print(list(t2))

topK = 100

s = Similarity(t1, t2, topK)

print(s.similar())