网站视频爬取

import json
import pandas as pd

with open("1.json", "r", encoding="utf-8") as f:
    data = json.load(f)

result = []

class_sections = data["data"]["classSection"]

for section in class_sections:  
    for year, chapters in section.items():
        for chapter in chapters:
            children = chapter.get("children", [])
            if children:
                for child in children:
                    title = child.get("title", "")
                    video = child.get("videoModel")
                    if video:
                        url = video.get("vGUrl") or video.get("vBUrl") or video.get("vCUrl")
                        if url:
                            result.append({"标题": title, "链接": url})

df = pd.DataFrame(result)
df.to_excel("2.xlsx", index=False)

import os
import requests
from tqdm import tqdm
import pandas as pd

SAVE_DIR = "videos"
os.makedirs(SAVE_DIR, exist_ok=True)

# 读取 Excel 文件
df = pd.read_excel("1.xlsx")

print(f"共 {len(df)} 条视频链接，开始下载...")

for idx, row in df.iterrows():
    title = str(row["标题"]).replace("/", "-").replace("\\", "-")
    url = row["下载链接"]
    filename = os.path.join(SAVE_DIR, f"{title}.mp4")
    print(f"正在下载: {title}")
    try:
        with requests.get(url, stream=True) as r:
            r.raise_for_status()
            total_size = int(r.headers.get('content-length', 0))
            with open(filename, 'wb') as f:
                for chunk in tqdm(r.iter_content(1024 * 1024), total=total_size // (1024 * 1024), unit='MB'):
                    if chunk:
                        f.write(chunk)
    except Exception as e:
        print(f"下载失败: {title}，错误: {e}")

print("下载完成")