# -*- coding: utf-8 -*-
import requests
import os

# API URL
# https://www.douyu.com/gapi/rknc/directory/yzRec/1

def get_html(url):
    header = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36'
    }
    response = requests.get(url=url, headers=header)
    html = response.json()
    return html

def parse_html(html):
    rl_list = html['data']['rl']
    img_info_list = []
    
    for rl in rl_list:
        img_info = {}
        img_info['img_url'] = rl['rs1']  # 头像URL
        img_info['nickname'] = rl['nn']   # 主播昵称
        img_info['room_id'] = rl['rid']    # 房间号
        img_info['title'] = rl['rn']       # 房间标题
        img_info['viewers'] = rl['ol']     # 在线人数
        img_info_list.append(img_info)
    
    return img_info_list

def save_to_images(img_info_list):
    dir_path = 'douyu_streamers'
    if not os.path.exists(dir_path):
        os.makedirs(dir_path)
    
    for img_info in img_info_list:
        img_path = os.path.join(dir_path, f"{img_info['nickname']}.jpg")
        res = requests.get(img_info['img_url'])
        with open(img_path, 'wb') as f:
            f.write(res.content)

def save_to_csv(img_info_list):
    import csv
    
    with open('douyu_streamers.csv', 'w', encoding='utf-8', newline='') as f:
        writer = csv.DictWriter(f, fieldnames=['room_id', 'nickname', 'title', 'viewers'])
        writer.writeheader()
        for info in img_info_list:
            writer.writerow(info)

if __name__ == '__main__':
    # 颜值主播分类
    url = 'https://www.douyu.com/gapi/rknc/directory/yzRec/1'
    
    html = get_html(url)
    img_info_list = parse_html(html)
    
    # 保存头像
    save_to_images(img_info_list)
    
    # 保存CSV
    save_to_csv(img_info_list)
    
    print(f"采集完成，共 {len(img_info_list)} 位主播")
    for info in img_info_list:
        print(f"{info['nickname']} - {info['title']} - {info['viewers']}在线")