single_video_crawler/single_video/xigua/xigua_video.py

import base64
import configparser
import os
import re
import sys
import time

import requests

from common import Common
from common.pq_utility import PQ

sys.path.append(os.getcwd())
from common.url_manage import urlManage
from common.aliyun_oss_uploading import Oss
from common.userAgent import get_random_user_agent

config = configparser.ConfigParser()
config.read('/root/single_video_crawler/config.ini')  # 替换为您的配置文件路径
class xiguaVideo():

    # 获取西瓜 标题+视频链接
    @classmethod
    def download_video(cls, video_url, video_path_url):
        for i in range(3):
            payload = {}
            headers = {
                'accept-language': 'zh-CN,zh;q=0.9',
                'cache-control': 'no-cache',
                'pragma': 'no-cache',
                'range': 'bytes=0-',
                'referer': 'https://www.ixigua.com/',
                'sec-ch-ua': '"Google Chrome";v="123", "Not:A-Brand";v="8", "Chromium";v="123"',
                'sec-ch-ua-mobile': '?0',
                'sec-ch-ua-platform': '"macOS"',
                'sec-fetch-dest': 'video',
                'sec-fetch-mode': 'no-cors',
                'sec-fetch-site': 'same-site',
                'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36',
            }

            response = requests.request("GET", video_url, headers=headers, data=payload)
            # 检查响应状态码是否为200
            if response.status_code == 206:
                # 以二进制写入模式打开文件
                with open(f"{video_path_url}", "wb") as file:
                    # 将响应内容写入文件
                    file.write(response.content)
                return True
        return False

    # 获取西瓜 标题+视频链接
    @classmethod
    def get_videoList(cls, vx_message, channel):
        try:
            data_link = vx_message[1]
            time.sleep(1)
            content_id = ''
            for i in range(3):
                content_id = urlManage.url_manage(data_link, channel)
                if content_id:
                    break
            if content_id == '':
                return "无法获取到视频ID"
            for i in range(3):
                headers = {
                    'Cookie': 'ttwid=1%7C7j8Kxe-NNRFurQ2qk8x48WH3FToSbPDi1_YAU1IC2ws%7C1711524169%7C845d7775e8226786557408dc77df0ba8a8f7b18bdba3c37b693438dc6049ad95;',
                    'Referer': f'https://www.ixigua.com/{content_id}',
                    'User-Agent': get_random_user_agent()
                }
                url = f'https://www.ixigua.com/{content_id}'

                response = requests.get(url, headers=headers)
                status_code = response.status_code
                if status_code != 200:
                    continue
                response.encoding = "utf-8"
                try:
                    html_data = response.text
                    title_match = re.search(r'<title[^>]*>(.*?)</title>', html_data)
                except Exception:
                    continue
                if title_match:
                    title_content = title_match.group(1)
                    title_content = title_content.split(" - ")[0]
                else:
                    title_content = ''
                print(title_content)
                try:
                    mainUrl = re.search(r'("main_url":")(.*?)"', html_data)[0]
                except Exception:
                    return '无法获取视频链接'
                mainUrl = mainUrl.split(":")[1]
                decoded_data = base64.b64decode(mainUrl)
                try:
                    # 尝试使用utf-8解码
                    video_url = decoded_data.decode('utf-8')
                except UnicodeDecodeError:
                    # 如果utf-8解码失败，尝试使用其他编码方式
                    video_url = decoded_data.decode('latin-1')
                # 随机生成视频oss_id
                video_id = urlManage.random_id()
                video_path_url = config['PATHS']['VIDEO_OSS_PATH'] + video_id+".mp4"
                status = cls.download_video(video_url, video_path_url)
                if status == False:
                    return "视频下载失败"
                oss_object_key = Oss.video_sync_upload_oss(video_path_url, video_id)
                # 获取 oss 视频地址
                oss_object_key = oss_object_key.get("oss_object_key")
                Common.logger().info(f'准备发送站内参数:{oss_object_key},{title_content},{vx_message[3]}')
                piaoquantv = PQ.insert_piaoquantv(oss_object_key, title_content, vx_message[3])
                if piaoquantv == False:
                    return "视频发送到站内失败"
                if os.path.isfile(video_path_url):
                    os.remove(video_path_url)
                return
        except Exception as e:
            Common.logger().info(f'报错信息:{e}')
            return f"处理报错，报错信息{e}"