百度AI认为最漂亮的中国女星是----范冰冰

import time
import json
import logging
import sqlite3
import requests
from lxml import etree
from urllib.parse import quote
from BaiduFaceIdentify import BaiduFaceIdentify


class BeautyRank():
    def __init__(self):
        self.db_conn = sqlite3.connect(‘beauty_rank.db‘)
        self.db_cursor = self.db_conn.cursor()
        self.model_count = 0
        self.bfi = BaiduFaceIdentify()
        pass

    def request_name_list_url(self,name_list_url):
        headers = {
            ‘Host‘: ‘123fans.cn‘,
            ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:60.0) Gecko/20100101 Firefox/60.0‘,
            ‘Accept‘: ‘text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8‘,
            ‘Accept-Language‘: ‘zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2‘,
            ‘Accept-Encoding‘: ‘gzip, deflate, br‘,
            ‘Referer‘: ‘https://www.ugirls.com/Models/‘,
        }
        # 访问明星名单url
        response = requests.get(name_list_url,headers=headers,timeout=10)
        if response.status_code != 200:
            logging.warning(f"请求失败：{response.status_code}")
            return False
        sel = etree.HTML(response.text)
        # 获取明星名单列表
        name_lists = sel.xpath(‘//div[@id="main"]//div[@class="ranking"]//td[@class="name"]//a/text()‘)
        star_counts = len(name_lists)
        count = 0
        # 遍历明星名单
        for star_name in name_lists:
            count += 1
            try:
                logging.warning(f‘\r\n开始采集{count}/{star_counts}：{star_name}‘)
                # 通过搜狗获取明星图片
                self.request_and_parse_star_img(star_name,‘sougou‘)
                # 通过360获取明星图片
                self.request_and_parse_star_img(star_name,‘360‘)
            except:
                logging.warning(f‘\r\n{count}/{star_counts}：{star_name}出现错误‘)
                continue

    def request_and_parse_star_img(self, star_name, search_engine):
        headers = {
            ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:60.0) Gecko/20100101 Firefox/60.0‘,
            ‘Accept‘: ‘application/json, text/javascript, */*; q=0.01‘,
            ‘Accept-Language‘: ‘zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2‘,
            ‘X-Requested-With‘: ‘XMLHttpRequest‘,
            ‘Connection‘: ‘close‘,
        }
        # 根据要求使用的搜索引擎构建请求的url和完善头部信息
        if search_engine == ‘sougou‘:
            star_img_ajax_request_url = f‘http://pic.sogou.com/pics?query={quote(star_name)}&mode=1&start=96&reqType=ajax&reqFrom=result&tn=0‘
            headers[‘Host‘] = ‘pic.sogou.com‘
            headers[‘Referer‘] = ‘http://pic.sogou.com/pics?ie=utf8&p=40230504&interV=kKIOkrELjboMmLkEk7kTkKILlLELjboLmLkEkrgTkKIMkrELjboImLkEk74TkKILmrELjb8TkKIKmrELjbkI_1093829215&query=%E8%B5%B5%E4%B8%BD%E9%A2%96&‘
            # 下边从json_results中抽取明星图片列表的key name
            img_frames_key = ‘items‘
            # 下边从明星图片中抽取图片具体url的key name
            img_url_key = ‘pic_url‘
        elif search_engine == ‘360‘:
            star_img_ajax_request_url = f‘http://image.so.com/j?q={quote(star_name)}&src=tab_www&correct={quote(star_name)}&pn=60&ch=&sn=120&sid=af5aac1212d41c3b5cd6a96a0c311ba2&ran=0&ras=0&cn=0&gn=10&kn=50‘
            headers[‘Host‘] = ‘image.so.com‘
            headers[‘Referer‘] = ‘http://image.so.com/i?q=%E8%B5%B5%E4%B8%BD%E9%A2%96&src=tab_www‘
            img_frames_key = ‘list‘
            img_url_key = ‘img‘
        # 访问搜索引擎，获取明星图片url
        try:
            response = requests.get(star_img_ajax_request_url, headers=headers, timeout=10)
            if response.status_code != 200:
                logging.warning(‘请求出错：%s‘ % response.status_code)
                return False
            json_results = json.loads(response.text)
        except:
            return False
        # 遍历图片列表，调用百度AI接口并接收图片颜值
        for img_frame in json_results[img_frames_key]:
            img_url = img_frame[img_url_key]
            logging.warning(f‘{time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())}开始识别:{img_url}‘)
            try:
                beauty_value = self.bfi.parse_face_pic(img_url)
            except:
                logging.warning(‘百度识别出现错误‘)
                continue
            # 如果颜值没有问题则插入数据库
            if beauty_value > 1.0:
                logging.warning(
                    f‘{time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())}即将插入数据库（{search_engine}）：{star_name}-{beauty_value}-{img_url}‘)
                self.insert_into_database(star_name, beauty_value, img_url,search_engine)
        return True

    # 此函数用于将结果插入数据库
    def insert_into_database(self,star_name,beauty_value,img_url,search_engine):
        # 如果表star_beauty_value不存在则先创建
        sql = ‘‘‘create table if not exists star_beauty_value(star_name text,beauty_value int,img_url text,search_engine text)‘‘‘
        self.db_cursor.execute(sql)
        self.db_conn.commit()
        # 将结果插入数据库
        sql = f‘‘‘insert into star_beauty_valuex values(‘{star_name}‘,‘{beauty_value}‘,‘{img_url}‘,‘{search_engine}‘)‘‘‘
        self.db_cursor.execute(sql)
        self.db_conn.commit()


    def __del__(self):
        self.db_cursor.close()
        self.db_conn.close()
        pass


if __name__ == ‘__main__‘:
    # 明星名单url
    name_list_url = ‘https://123fans.cn/rank.php?c=2‘
    # 实例化
    beauty_rank = BeautyRank()
    beauty_rank.request_name_list_url(name_list_url)