新片场视频下载

仅作练习，侵权联系删除

代码

7页视频信息.py

获取前7页的视频信息

import json
import os
import re
import time
import requests
from DrissionPage import ChromiumPage

# 打开浏览器，手动登录账号，取cookie
def get_ck():
    page = ChromiumPage()
    page.get("https://www.xinpianchang.com/discover/article-27-180-all-all-0-0-score-pp4")
    time.sleep(10)
    cookies = page.cookies()
    cookies = ', '.join([f"\'{cookie['name']}\':\'{cookie['value']}\'" for cookie in cookies])
    cookies = json.dumps(cookies)
    # 使用正则表达式提取键值对
    pattern = re.compile(r"'([^']+)':'([^']+)'")
    matches = pattern.findall(cookies)
    # 转换为字典
    cookies = {key: value for key, value in matches}
    print('cookies', cookies)
    return cookies


cookies = get_ck()
for i in range(1, 8):
    headers = {
        'accept': '*/*',
        'accept-language': 'zh-CN,zh;q=0.9',
        # Requests sorts cookies= alphabetically
        # 'cookie': 'Device_ID=8ot5e2cg6lzl4q2m6; Authorization=B1B9682CB8F69EB9FB8F694F80B8F69AEB6B8F69D97762B2E237; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%2214882668%22%2C%22first_id%22%3A%221913182f98f36b-041ddc99b17b4a-26001e51-2359296-1913182f990612%22%2C%22props%22%3A%7B%22%24latest_traffic_source_type%22%3A%22%E7%9B%B4%E6%8E%A5%E6%B5%81%E9%87%8F%22%2C%22%24latest_search_keyword%22%3A%22%E6%9C%AA%E5%8F%96%E5%88%B0%E5%80%BC_%E7%9B%B4%E6%8E%A5%E6%89%93%E5%BC%80%22%2C%22%24latest_referrer%22%3A%22%22%7D%2C%22%24device_id%22%3A%221913182f98f36b-041ddc99b17b4a-26001e51-2359296-1913182f990612%22%7D; sl-session=yKGIM3WUwGY5O8voLLclMQ==; Hm_lvt_446567e1546b322b726d54ed9b5ad346=1723115438,1723115460,1723120731,1723810557; HMACCOUNT=3C402195F4DFF3E8; Hm_lpvt_446567e1546b322b726d54ed9b5ad346=1723810955',
        'if-none-match': 'W/"7iqcws87zm3vnu"',
        'priority': 'u=1, i',
        'referer': 'https://www.xinpianchang.com/discover/article-27-180-all-all-0-0-score-pp4',
        'sec-ch-ua': '"Not)A;Brand";v="99", "Google Chrome";v="127", "Chromium";v="127"',
        'sec-ch-ua-mobile': '?0',
        'sec-ch-ua-platform': '"Windows"',
        'sec-fetch-dest': 'empty',
        'sec-fetch-mode': 'cors',
        'sec-fetch-site': 'same-origin',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
        'x-nextjs-data': '1',
        'x-user-hash': '14882668:4074873819',
    }

    params = {
        'param': f'27-180-all-all-0-0-score-pp{i}',
    }
    if i == 1:
        response = requests.get(
            f'https://www.xinpianchang.com/_next/data/gJx7P4y6Bi_PvEysygeJE/discover/article/27-180.json',
            params=params, cookies=cookies, headers=headers)
        # print(response.json())
    else:
        response = requests.get(
            # data/xxxxxxxxxxxxxxxx/discover,中间的xxxxxx从网页上抓包，找链接，会变，仅修改中间位置就行
            f'https://www.xinpianchang.com/_next/data/gJx7P4y6Bi_PvEysygeJE/discover/article/27-180-all-all-0-0-score-pp{i}.json',
            params=params, cookies=cookies, headers=headers)
    print(response)
    print(response.json())
    lists = response.json()['pageProps']['discoverArticleData']['list']
    for list in lists:
        title = list['title']
        print(title)
        cate = []
        categories = list['categories']
        for category in categories:
            category_name1 = category['category_name']
            cate.append(category_name1)
            category_name2 = category['sub']['category_name']
            cate.append(category_name2)
        print(cate)
        url = list['web_url']
        print(url)
        # 创建一个字典来存储所有信息
        movie_info = {
            # 标题
            'title': title,
            # 分类
            'cate': cate,
            # 链接
            'url': url,
        }

        # 读取已有的 JSON 文件内容
        file_path = 'movie_info1.json'
        if os.path.exists(file_path):
            with open(file_path, 'r', encoding='utf-8') as f:
                existing_data = json.load(f)
        else:
            existing_data = []

        # 添加新的电影信息到现有数据中
        existing_data.append(movie_info)

        # 将更新后的数据写回到 JSON 文件
        with open(file_path, 'w', encoding='utf-8') as f:
            json.dump(existing_data, f, ensure_ascii=False, indent=4)

        print(f"{title}已追加到 movie_info1.json 文件中。")

 成果展示

视频链接.py

视频链接在html中，使用request请求没加载出来，没数据，这里使用自动化工具

import json
import re
import time
from DrissionPage import ChromiumPage


def get_ck(url):
    # 使用ChromiumPage获取网页内容
    page = ChromiumPage()
    page.get(url)
    time.sleep(10)  # 等待页面加载
    html = page.html

    clean_url = None
    # 正则表达式匹配视频链接
    match = re.search(r'src="([^"]+\.mp4\?[^"]+)"', html)
    if match:
        video_url = match.group(1)
        # 使用正则表达式提取基本 URL
        match = re.match(r'([^?]+)', video_url)
        if match:
            clean_url = match.group(1)
            print('================', clean_url)
        else:
            print("URL 不匹配")
    else:
        print("视频链接未找到")

    return clean_url


def get_urls_from_json(json_file, count=60):
    # 从本地JSON文件中读取URL列表
    url_list = []
    with open(json_file, 'r', encoding='utf-8') as file:
        datas = json.load(file)
    for data in datas:
        url = data['url']
        url_list.append(url)
    # 取出前count个URL
    urls = url_list[:count]
    print(urls)
    return urls


def save_urls_to_json(urls, output_file):
    # 将URL列表保存到JSON文件中
    with open(output_file, 'w', encoding='utf-8') as file:
        json.dump(urls, file, ensure_ascii=False, indent=4)
    print(f"Clean URLs 已保存到 {output_file}")


# 从JSON文件中读取URL
json_file_path = 'movie_info1.json'  # 替换为你的文件路径
urls = get_urls_from_json(json_file_path, 60)

# 用于存储 clean_url 的列表
clean_urls = []

# 对每个URL执行 get_ck 函数，并将得到的 clean_url 添加到列表中
for url in urls:
    clean_url = get_ck(url)
    if clean_url:
        clean_urls.append({'clean_url': clean_url})

# 将得到的 clean_url 列表保存到一个新的 JSON 文件中
output_file_path = 'clean_urls.json'  # 设置输出文件路径
save_urls_to_json(clean_urls, output_file_path)

 成果展示

 视频下载.py

使用多线程，快速下载视频

import json
import requests
import os
import re
import time
from concurrent.futures import ThreadPoolExecutor

def video(video_url, thread_name):
    headers = {
        'sec-ch-ua': '"Not)A;Brand";v="99", "Google Chrome";v="127", "Chromium";v="127"',
        'Referer': 'https://www.xinpianchang.com/',
        'sec-ch-ua-mobile': '?0',
        'Range': 'bytes=0-',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
        'sec-ch-ua-platform': '"Windows"',
    }

    params = {
        'j': '{"userId":14882668,"deviceId":"66b4975aaf0658528","ip":"42.235.14.44,61.163.51.58"}',
    }

    try:
        response = requests.get(video_url, params=params, headers=headers, stream=True)
        print(f"{thread_name}: {response}")
        if response.status_code == 206:
            with open(f'{thread_name}.mp4', 'wb') as f:
                for chunk in response.iter_content(chunk_size=8192):
                    f.write(chunk)
            print(f"{thread_name}: 视频下载完成")
        else:
            print(f"{thread_name}: 下载失败，状态码：{response.status_code}")
    except Exception as e:
        print(f"{thread_name}: 下载出错: {e}")

# 读取已有的 JSON 文件内容
with open('clean_urls.json', 'r', encoding='utf-8') as f:
    datas = json.load(f)

# 多线程下载视频
def download_videos_multithreaded(urls):
    with ThreadPoolExecutor(max_workers=10) as executor:  # 设置最大线程数
        for i, data in enumerate(urls):
            video_url = data.get('clean_url')
            if video_url:
                thread_name = f'视频{i+1}'
                executor.submit(video, video_url, thread_name)

download_videos_multithreaded(datas)

成果展示