# -*- coding: utf-8 -*-
#!/usr/bin/env python
import urllib
import base64
import json
#client_id 为官网获取的AK, client_secret 为官网获取的SK
client_id ='43pyLfhEyu5kyxD7Pc3abo6G'
client_secret ='HTvjgzFQFX8LVPUE1VdGgcwfGg1cTRec'
#获取token
def get_token():
host = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=' + client_id + '&client_secret=' + client_secret
request = urllib.request.Request(host)
request.add_header('Content-Type', 'application/json; charset=UTF-8')
response = urllib.request.urlopen(request)
token_content = response.read()
if token_content:
token_info = json.loads(token_content)
token_key = token_info['access_token']
return token_key
#地标识别
def landmark(filename):
filename= 'guangzhouta.jpg'
request_url = "https://aip.baidubce.com/rest/2.0/image-classify/v1/landmark"
f = open(filename, 'rb')
img = base64.b64encode(f.read())
params = dict()
params['image'] = img
params['show'] = 'true'
params = urllib.parse.urlencode(params).encode("utf-8")
#params = json.dumps(params).encode('utf-8')
access_token = get_token()
request_url = request_url + "?access_token=" + access_token
request = urllib.request.Request(url=request_url, data=params)
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
response = urllib.request.urlopen(request)
content = response.read()
landmark=''
if content:
#print(content)
content=content.decode('utf-8')
#print(content)
data = json.loads(content)
#print(data)
words_result=data['result']
landmark=words_result['landmark']
print ('地标:',landmark)
return landmark
from bs4 import BeautifulSoup
#通过百度百科获取地标的详细说明
def get_baike_summary(itemname):
url='https://baike.baidu.com/item/'+urllib.parse.quote(itemname)
# 构建请求对象
headers = {"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36"}
request = urllib.request.Request(url, headers=headers)
# 发送请求
response = urllib.request.urlopen(request)
# 读取文件
content = response.read().decode('utf8')
# 先构建一个soup对象
soup = BeautifulSoup(content, "lxml")
#获取描述
summary = soup.find("div", attrs={"class": "lemma-summary"}).get_text()
print (summary)
def get_landmark_more(filename):
result=landmark(filename)
get_baike_summary(result)
get_landmark_more('landmark1.jpg')
输出
网友评论