Python爬取某拍短视频

# eplace()方法用于在字符串中用一些字符替换另一些字符
    # parseInt 数据转换成对应的整型
    # base64.atob   对base64编码过的字符串进行解码
    # substring 方法可在字符串中抽取从 start 下标开始的指定数目的字符

import base64

def decode(data):
    def getHex(a):
        return {
            'str': a[4:],
            'hex': ''.join(list(a[:4])[::-1]),
        }

    def getDec(a):
        b = str(int(a, 16))
        return {
            'pre': list(b[:2]),
            'tail': list(b[2:]),
        }

    def substr(a, b):
        c = a[0: int(b[0])]
        d = a[int(b[0]): int(b[0]) + int(b[1])]
        return c + a[int(b[0]):].replace(d, "")

    def getPos(a, b):
        b[0] = len(a) - int(b[0]) - int(b[1])
        return b

    b = getHex(data)
    c = getDec(b['hex'])
    d = substr(b['str'], c['pre'])
    return base64.b64decode(substr(d, getPos(d, c['tail'])))

print(decode("e121Ly9tBrI84RdnZpZGVvMTAubWVpdHVkYXRhLmNvbS82MGJjZDcwNTE3NGZieXBueG5udnRwMTA5N19IMjY0XzFfNWY3YThmM2U0MTEwNy5tc2JVjAu3EDQ="))

import requests
from lxml import etree
import base64

def decode_mp4(data):
    def getHex(a):
        return {
            'str': a[4:],
            'hex': ''.join(list(a[:4])[::-1]),
        }

    def getDec(a):
        b = str(int(a, 16))
        return {
            'pre': list(b[:2]),
            'tail': list(b[2:]),
        }

    def substr(a, b):
        c = a[0: int(b[0])]
        d = a[int(b[0]): int(b[0]) + int(b[1])]
        return c + a[int(b[0]):].replace(d, "")

    def getPos(a, b):
        b[0] = len(a) - int(b[0]) - int(b[1])
        return b

    b = getHex(data)
    c = getDec(b['hex'])
    d = substr(b['str'], c['pre'])
    return base64.b64decode(substr(d, getPos(d, c['tail'])))
# 运行主函数
def main():
    url = 'https://www.meipai.com'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36',
    }
    response = requests.get(url=url, headers=headers)
    html_data = etree.HTML(response.text)
    href_list = html_data.xpath('//div/a/@href')
    # print(href_list)
    for href in href_list:
        res = requests.get('https://www.meipai.com' + href, headers=headers)
        html = etree.HTML(res.text)
        name = html.xpath('//div[@id="detailVideo"]/img/@alt')[0]
        mp4_data = html.xpath('//div[@id="detailVideo"]/@data-video')[0]
        # print(name, mp4_data)
        mp4_url = decode_mp4(mp4_data).decode('utf-8')
        print(mp4_url)
        result = requests.get("http:" + mp4_url)
        with open(name + ".mp4", 'wb') as f:
            f.write(result.content)
            f.close()


if __name__ == '__main__':
    main()