爬虫实例十：探索神秘的原神世界（二）

https://bbs-api.mihoyo.com/post/wapi/forumGoodPostFullList?

# -*- coding: UTF-8 -*-
"""
@Author  ：远方的星
@Time   : 2021/3/8 19:25
@CSDN    ：https://blog.csdn.net/qq_44921056
@腾讯云   ： https://cloud.tencent.com/developer/column/91164
"""
import requests
import os
import json

# 创建一个文件夹
path = 'D:/原神同人画'
if not os.path.exists(path):
    os.mkdir(path)
# 构造一个请求头
header = {
    'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 11_1_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'
}
# 用户输入想要爬取的页数
page = input('请输入您想要爬取的页数：')
page = int(page) + 1
n = 0
# image_id 代表图片从第几张开始爬取，默认一次滑动，加载出来20张
image_id = 0
for m in range(1, page):
    url = 'https://bbs-api.mihoyo.com/post/wapi/forumGoodPostFullList?'
    param = {
        'forum_id': '29',
        'gids': '2',
        'last_id': image_id,
        'page_size': '20'
    }
    # 定义一个空列表，用于存放图片的URL
    image_url = list()
    # 将编码形式转换为utf-8
    response = requests.get(url=url, headers=header, params=param)
    response.encoding = 'utf-8'
    response = response.text
    # 把字符串转换成json数据
    data_s = json.loads(response, strict=False)
    a = data_s["data"]["posts"]  # 提取data里的数据
    for i in range(len(a)):
        data = a[i].get("post").get("cover")
        image_url.append(data)
    for image_src in image_url:
        # 提取图片内容
        image_data = requests.get(url=image_src, headers=header).content
        # 图片名
        image_name = '{}'.format(n+1) + '.jpg'
        # 图片保存路径
        image_path = path + '/' + image_name
        # 保存数据
        with open(image_path, 'wb') as f:
            f.write(image_data)
            print(image_name, '==================>下载完毕！！！')
            f.close()
        n += 1
    image_id += 20