Python爬取《创造营2020》小姐姐数据并用腾讯云人脸识别做

最近 创造营2020好多小姐姐吸引到我了，于是就有这这个

以下是代码，需要你在申请腾讯云有关参数替换哦

# -*- coding: utf-8 -*-
"""
Created on Sun May 24 20:45:13 2020

@author: Gdc
"""

import requests
from fake_useragent import UserAgent
import pandas as pd
import json
from lxml import etree

from tencentcloud.common import credential
from tencentcloud.common.profile.client_profile import ClientProfile
from tencentcloud.common.profile.http_profile import HttpProfile
from tencentcloud.common.exception.tencent_cloud_sdk_exception import TencentCloudSDKException 
from tencentcloud.iai.v20180301 import iai_client, models 

#腾讯云人脸检测与分析
#检测给定图片中的人脸（Face）的位置、相应的面部属性和人脸质量信息
#位置包括 (x，y，w，h)
#面部属性包括性别（gender）、年龄（age）、表情（expression）、魅力（beauty）、眼镜（glass）、发型（hair）、口罩（mask）和姿态 (pitch，roll，yaw)
#人脸质量信息包括整体质量分（score）、模糊分（sharpness）、光照分（brightness）和五官遮挡分（completeness）

def faceScore(url):
    try: 
        cred = credential.Credential("你的腾讯云key", "你的腾讯云id") 
        httpProfile = HttpProfile()
        httpProfile.endpoint = "iai.tencentcloudapi.com"
    
        clientProfile = ClientProfile()
        clientProfile.httpProfile = httpProfile
        client = iai_client.IaiClient(cred, "ap-beijing", clientProfile) 
    
        req = models.DetectFaceRequest()
        param = {"Url":url,"NeedFaceAttributes":1}
        params = json.dumps(param)
        req.from_json_string(params)
    
        resp = client.DetectFace(req) 
        respstr = resp.to_json_string().replace('false','0').replace('true','1')
        respdic = eval(respstr)
        
        age = respdic['FaceInfos'][0]['FaceAttributesInfo']['Age']
        beauty = respdic['FaceInfos'][0]['FaceAttributesInfo']['Beauty']
        
    except TencentCloudSDKException as err: 
        print(err)
    
    return age,beauty


url = 'https://zbaccess.video.qq.com/fcgi/getVoteActityRankList?'

headers = {"User-Agent": UserAgent(verify_ssl=False).random}

params = {'raw': 1,
           'vappid': 51902973,
           'vsecret': '14816bd3d3bb7c03d6fd123b47541a77d0c7ff859fb85f21',
           'actityId': 107015,
           'pageSize': 101,
           'vplatform': 3,
           'listFlag': 0,
           'pageContext':'' ,
           'ver': 1,
           '_t': 1590324974706,
           '_': 1590324974708
    }
re = requests.get(url,headers = headers,params = params)

data = json.loads(re.text)

Li_list = data['data']['itemList']
rank = 0
data_list = []

#获取每个选手的基础信息
for li in Li_list:
    rank += 1
    item = {}
    #获取基础信息
    item['当前排名'] = rank
    item['选手编号'] = li['itemInfo']['id']
    item['选手姓名'] = li['itemInfo']['name']
    item['选手照片'] = li['itemInfo']['mapData']['poster_pic']
    item['选手状态'] = li['statusInfo']['voteBtnTxt']
    #获取选手doki粉丝数

    id_ = item['选手编号']
    url_ = f'https://v.qq.com/x/star/{id_}?tabid=2'
    re_ = requests.get(url_,headers = headers)
    re_.encoding='utf-8'
    html = etree.HTML(re_.text)
    item['粉丝数'] = html.xpath('.//div[@class="followers_count"]/text()')[0]
    info = html.xpath('.//div[@class="wiki_info_1"]//span[@class="content"]/text()')
    item['星座'] = info[-5]
    item['身高'] = info[-3]
    item['体重'] = info[-2]
    item['出生地'] = info[-1]
    info2 = html.xpath('.//div[@class="wiki_info_2"]//span[@class="content"]/text()')
    item['生日'] = info2[0]
    url_ai = item['选手照片']
    age,beauty = faceScore(url_ai) 
    item['AI预测年龄'] = age
    item['AI颜值评分'] = beauty
    data_list.append(item)


df = pd.DataFrame(data_list)
df.to_excel(r'D:\python\创造营\创造营2020名单.xlsx',sheet_name='名单',index=0)