[原创] 爬取笔趣阁小说带界面爬虫工具 附源码和成品

import re
import requests
from bs4 import BeautifulSoup
import json
from PIL import Image
from io import BytesIO
 
 
def xsh_video_image():
    try:
 
        headers = {
            "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.4098.3 Safari/537.36",
        }
        # 定义请求的URL
        url = "http://xhslink.com/PMbpHv"
        # 请替换你自己的cookie
        cookie = {
            'customerBeakerSessionId': '',
            'xsecappid': '',
            'x-user-id-creator.xiaohongshu.com': '',
            'websectiga': '',
            'galaxy_creator_session_id': '',
            'webBuild': '3.11.3',
            'galaxy.creator.beaker.session.id': '',
            'sec_poison_id': '',
            'web_session': '',
            'gid': '',
            'a1': '',
            'abRequestId': '',
            'access-token-creator.xiaohongshu.com': '',
            'cache_feeds': '[]',
            'customer-sso-sid': '',
            'customerClientId': '',
            'unread': '',
            'webId': ''}
 
        # 发送GET请求，并添加Cookie
        response = requests.get(url, headers=headers, cookies=cookie)
        response.raise_for_status()
        if response.text == '':
            print("解析失败")
            return
        soup = BeautifulSoup(response.text, 'html.parser')
 
        script = soup.find('script', string=re.compile('window\.__INITIAL_STATE__')).text
 
        newhtmlinfo = script.replace('window.__INITIAL_STATE__=', '').replace('undefined', 'null')
        # 转换成json数据
        result = json.loads(newhtmlinfo, strict=False)
        note = result.get('note')
        noteDetailMap = note.get('noteDetailMap')
 
        first_key, first_value = next(iter(noteDetailMap.items()))
        first_note = first_value.get('note')
        # 标题
        title = first_note.get('title')
        # 如果获取到的视频还是带水印那就是你的cookie获取有问题,推荐使用Cookie-Editor插件来获取
        if first_note.get('type') == 'video':
            print("类型为video")
            stream = first_note.get('video').get('media').get('stream')
 
            h264 = stream.get('h264')
            # 这是视频地址
            video_url = h264[-1].get('masterUrl')
            print(video_url)
        else:
            print("类型是图片")
            image_list = first_note.get('imageList')
            image_url_list_webp = []
            for image_obj in image_list:
                info_list = image_obj.get('infoList')
                for image_url in info_list:
                    if image_url.get('imageScene') == 'CRD_WM_JPG':
                        url = image_url.get('url')
                        # 这个url地址的图片是webp格式的需要自己转换一下
                        download_and_convert_webp_to_jpg(url, "c:/")
 
    except requests.exceptions.HTTPError as err:
        print(err)
        return "解析错误"
 
 
def download_and_convert_webp_to_jpg(url, save_path):
    """
    这个下载的自己改改吧,我的需求是做成接口的
    :param url: 图片网络地址
    :param save_path: 图片保存的位置
    :return:
    """
    response = requests.get(url)
    if response.status_code == 200:
        # 从响应内容创建PIL Image对象
        webp_image = Image.open(BytesIO(response.content))
        # 转换为JPEG格式
        webp_image = webp_image.convert("RGB")
        # 保存为JPEG文件
        webp_image.save(save_path, "JPEG")
        print(f"成功将WebP图片保存为JPEG格式：{save_path}")
    else:
        print(f"无法下载图片，状态码：{response.status_code}")