爬取西瓜視頻

有水印視頻

 

 上面那個鏈接在瀏覽器打開就是播放地址 ，可以直接請求並保存視頻

無水印視頻

沒有水印的視頻是音頻和視頻分離的，在network下選擇xhr

 

 

 

 無水印的有一些加密參數暫時沒有找到是怎么加密的

 

有水印的視頻還有一種下載方式 代碼如下

 

# -*- coding: utf-8 -*-
# __author__ = "maple"


from base64 import b64decode
from lxml import etree
import requests
import json
import re
import os


class XiGuaSpider:

    def __init__(self):
        self.headers = {
            'Referer': 'https://www.ixigua.com',
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
            'cookie': 'wafid=8b91d940-81ec-4620-af0f-f45d479a62c2; wafid.sig=BZgx1eD0aFGn25mL-y-SEh17cng; ttwid=6841106955945346564; ttwid.sig=glkPgElc0Yh0OEDyNL0P91fmbZg; xiguavideopcwebid=6841106955945346564; xiguavideopcwebid.sig=avM_v_QTwC7VqM26Yqde9eer3xA; _ga=GA1.2.1235075053.1592819342; SLARDAR_WEB_ID=fa1eb835-d608-4ade-850d-bc0409bd541f; _gid=GA1.2.303152420.1593089518; ixigua-a-s=1; Hm_lvt_db8ae92f7b33b6596893cdf8c004a1a2=1593094562,1593095154,1593098009,1593147688; Hm_lpvt_db8ae92f7b33b6596893cdf8c004a1a2=1593153331',
        }

        self.video_dirs = './video'

    def download_file(self, file_path, download_url):
        print('*' * 100)
        print(f"保存路徑：{file_path}")
        print(f'下載URL：{download_url}')
        response = requests.get(url=download_url, headers=self.headers, stream=True)
        content_size = int(response.headers["content-length"])  # 視頻內容的總大小
        size = 0
        with open(file_path, "wb") as file:  # 非純文本都以字節的方式寫入
            for data in response.iter_content(chunk_size=1024):  # 循環寫入
                file.write(data)  # 寫入視頻文件
                file.flush()  # 刷新緩存
                size += len(data)  # 疊加每次寫入的大小
                # 打印下載進度
                print("\r文件下載進度:%d%%(%0.2fMB/%0.2fMB)" % (
                    float(size / content_size * 100), (size / 1024 / 1024),
                    (content_size / 1024 / 1024)),
                      end=" ")
        print()

    def get_response(self, url):
        response = None
        try:
            response = requests.get(url, headers=self.headers)
        except Exception as e:
            print(e)
        return response

    def parse_detail(self, url):
        response = self.get_response(url)
        if not response:
            return
        html = response.text
        document = etree.HTML(html)
        title = ''.join(document.xpath('//*[@class="hasSource"]/text()'))
        if not title:
            title = ''.join(document.xpath('//*[@class="teleplayPage__Description__header"]/h1/text()'))

        title = re.sub(u"([^\u4e00-\u9fa5\u0030-\u0039\u0041-\u005a\u0061-\u007a])", "-", title)
        pattern = r'\<script.*?\>window\._SSR_HYDRATED_DATA=(.*?)\</script\>'
        result = re.findall(pattern, html)
        if len(result) < 1:
            print('沒有找到下載鏈接。。。')
            return None
        result = result[0]
        data = json.loads(result)
        with open('video.json', 'w', encoding='utf-8') as f:
            json.dump(data, f)

        try:
            video_list = data['Projection']['video']['videoResource']['normal']['video_list']
        except Exception as e:
            print('異常信息：', e)
            video_list = data['Teleplay']['videoResource']['normal']['video_list']

        video_3 = video_list.get('video_3')
        if not video_3:
            video_3 = video_list.get('video_2')
        video_url = video_3['main_url']
        video_url = b64decode(video_url).decode('utf-8')

        if not os.path.exists(self.video_dirs):
            os.mkdir(self.video_dirs)
        file_path = f"{self.video_dirs}/{title}.mp4"
        self.download_file(file_path, video_url)

    def start_requests(self):
        url = 'https://www.ixigua.com/i6618828724525597192'
        self.parse_detail(url)

    def run(self):
        self.start_requests()


if __name__ == '__main__':
    XiGuaSpider().run()