Download Baidu Haokan video

haokan_down.go

package main

import (
	"fmt"
	"io"
	"net/http"
	"net/url"
	"os"
	"strings"
)

func downloadVideo(urlStr string) error {
	headers := map[string]string{
		"User-Agent":    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 Edge/16.16299",
		"Cache-Control": "no-cache",
		"Pragma":        "no-cache",
		"Expires":       "0",
	}

	// Make GET request to the URL
	req, err := http.NewRequest("GET", urlStr, nil)
	if err != nil {
		return err
	}

	for key, value := range headers {
		req.Header.Set(key, value)
	}

	client := &http.Client{}
	resp, err := client.Do(req)
	if err != nil {
		return err
	}

	defer resp.Body.Close()

	// Read response body
	bodyBytes, err := io.ReadAll(resp.Body)
	if err != nil {
		return err
	}

	bodyStr := string(bodyBytes)

	// Find the "playurl" in the response body
	playurlStart := strings.Index(bodyStr, `"playurl":"`) + len(`"playurl":"`)
	playurlEnd := strings.Index(bodyStr[playurlStart:], `","`) + playurlStart
	playurl := strings.ReplaceAll(bodyStr[playurlStart:playurlEnd], `\/`, `/`)
	fmt.Println("playurl:", playurl)

	// Parse the playurl to get the filename
	u, err := url.Parse(playurl)
	if err != nil {
		return err
	}

	pathSegments := strings.Split(u.Path, "/")
	filename := pathSegments[len(pathSegments)-1]

	// Create the file and download the video
	out, err := os.Create(filename)
	if err != nil {
		return err
	}

	defer out.Close()

	resp, err = http.Get(playurl)
	if err != nil {
		return err
	}

	defer resp.Body.Close()

	_, err = io.Copy(out, resp.Body)
	if err != nil {
		return err
	}

	fmt.Println("Downloaded file:", filename)
	return nil
}

func main() {
	if len(os.Args) < 2 {
		fmt.Println("Please provide the URL as an argument.")
		os.Exit(1)
	}

	url := os.Args[1]
	err := downloadVideo(url)
	if err != nil {
		fmt.Println("Error:", err)
		os.Exit(1)
	}
}

haokan_down.py

import requests
import sys
from urllib.parse import urlparse

def download_video(url):
	headers = {
	    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 Edge/16.16299'
	}
	response = requests.get(url, headers=headers)

	playurl_start = response.text.find('"playurl":"') + len('"playurl":"')
	playurl_end = response.text.find('","', playurl_start)
	playurl = response.text[playurl_start:playurl_end]
	playurl = playurl.replace('\\/', '/')
	print("playurl", playurl)

	playurl_path = urlparse(playurl).path
	filename = playurl_path.split('/')[-1]

	with open(filename, 'wb') as f:
	    video = requests.get(playurl)
	    print("begin to download to file", filename)
	    f.write(video.content)


if __name__ == '__main__':
    if len(sys.argv) < 2:
        print('Please provide the URL as an argument.')
        sys.exit(1)
    url = sys.argv[1]
    download_video(url)