crawler-twitter/main/common.py

# -*- coding: utf-8 -*-
# @Author: wangkun
# @Time: 2022/5/27
from datetime import date, timedelta
from loguru import logger
import datetime
import os
import time
import requests
import urllib3

proxies = {"http": None, "https": None}
# proxies = {"http": "127.0.0.1:19180", "https": "127.0.0.1:19180"}


class Common:
    # 统一获取当前时间 <class 'datetime.datetime'>  2022-04-14 20:13:51.244472
    now = datetime.datetime.now()
    # 昨天 <class 'str'>  2022-04-13
    yesterday = (date.today() + timedelta(days=-1)).strftime("%Y-%m-%d")
    # 今天 <class 'datetime.date'>  2022-04-14
    today = date.today()
    # 明天 <class 'str'>  2022-04-15
    tomorrow = (date.today() + timedelta(days=1)).strftime("%Y-%m-%d")

    # 使用 logger 模块生成日志
    @staticmethod
    def logger():
        """
        使用 logger 模块生成日志
        """
        # 日志路径
        log_dir = "./logs/"
        log_path = os.getcwd() + os.sep + log_dir
        if not os.path.isdir(log_path):
            os.makedirs(log_path)

        # 日志文件名
        log_name = time.strftime("%Y-%m-%d", time.localtime(time.time())) + '.log'

        # 日志不打印到控制台
        logger.remove(handler_id=None)

        # rotation="500 MB"，实现每 500MB 存储一个文件
        # rotation="12:00"，实现每天 12:00 创建一个文件
        # rotation="1 week"，每周创建一个文件
        # retention="10 days"，每隔10天之后就会清理旧的日志
        # 初始化日志
        logger.add(log_dir + log_name, level="INFO", rotation='00:00')

        return logger

    # 清除日志，保留最近 7 个文件
    @classmethod
    def del_logs(cls, d_dir):
        """
        清除冗余日志文件
        :d_dir: 需要删除的 log 地址
        :return: 保留最近 7 个日志
        """
        if d_dir == "logs":
            logs_dir = "./logs/"
            all_files = sorted(os.listdir(logs_dir))
            all_logs = []
            for log in all_files:
                name = os.path.splitext(log)[-1]
                if name == ".log":
                    all_logs.append(log)

            if len(all_logs) <= 7:
                pass
            else:
                for file in all_logs[:len(all_logs) - 7]:
                    os.remove(logs_dir + file)
            cls.logger().info("清除冗余日志成功")

    # 封装下载视频或封面的方法
    @classmethod
    def download_method(cls, log_path, text, d_name, d_url):
        """
        下载封面：text == "cover" ； 下载视频：text == "video"
        需要下载的视频标题：d_title
        视频封面，或视频播放地址：d_url
        下载保存路径："./files/{d_title}/"
        """
        # 首先创建一个保存该视频相关信息的文件夹
        video_dir = "./videos/" + d_name + "/"
        # video_dir = "./videos/"
        if not os.path.exists(video_dir):
            os.mkdir(video_dir)

        # 下载视频
        if text == "video":
            # 需要下载的视频地址
            video_url = d_url
            # 视频名
            video_name = "video.mp4"
            # # 视频名
            # video_name = d_name + ".mp4"

            # 下载视频
            urllib3.disable_warnings()
            response = requests.get(video_url, stream=True, proxies=proxies, verify=False)
            try:
                with open(video_dir + video_name, "wb") as f:
                    for chunk in response.iter_content(chunk_size=10240):
                        f.write(chunk)
                if log_path == "logs":
                    cls.logger().info("==========视频下载完成==========")
            except Exception as e:
                if log_path == "logs":
                    cls.logger().exception("视频下载失败：{}", e)

        # 下载封面
        elif text == "cover":
            # 需要下载的封面地址
            cover_url = d_url
            # 封面名
            cover_name = "image.jpg"
            # # 封面名
            # cover_name = d_name + ".jpg"

            # 下载封面
            urllib3.disable_warnings()
            response = requests.get(cover_url, proxies=proxies, verify=False)
            try:
                with open(video_dir + cover_name, "wb") as f:
                    f.write(response.content)
                if log_path == "logs":
                    cls.logger().info("==========封面下载完成==========")
            except Exception as e:
                if log_path == "logs":
                    cls.logger().exception("封面下载失败：{}", e)


if __name__ == "__main__":
    common = Common()