crawler_kanyikan/main/download_play.py

# -*- coding: utf-8 -*-
# @Author: wangkun
# @Time: 2022/4/18

"""
下载并上传：播放量视频
"""
import os
import sys

sys.path.append(os.getcwd())
from main.common import Common
from main.get_feeds import get_feeds
from main.publish import Publish


class DownloadPlay:

    @staticmethod
    def play_rule(play_width, play_height, play_duration, play_play_cnt):
        """
        1.分辨率，宽或者高 >= 720 or ==0
        2.600s >= 时长 >= 60s
        3.视频播放量 >= 150000
        """
        if int(play_width) >= 720 or int(play_height) >= 720 or play_width == "0" or play_height == "0":
            if 600 >= int(play_duration) >= 60:
                if int(play_play_cnt) >= 150000:
                    return True
                else:
                    return False
            else:
                return False
        else:
            return False

    @classmethod
    def download_play_video(cls, env):
        """
        下载播放量视频
        测试环境:env == dev
        正式环境:env == prod
        """
        videos = Common.read_txt("kanyikan_feeds.txt")
        for video in videos:
            download_video_id = video.strip().split(" + ")[1]
            try:
                # download_video_id = video.strip().split(" + ")[1]
                download_video_title = video.strip().split(" + ")[3]
                download_video_duration = video.strip().split(" + ")[4]
                download_video_play_cnt = video.strip().split(" + ")[2]
                download_video_comment_cnt = video.strip().split(" + ")[5]
                download_video_like_cnt = video.strip().split(" + ")[6]
                download_video_share_cnt = video.strip().split(" + ")[7]
                download_video_resolution = video.strip().split(" + ")[8]
                download_video_width = download_video_resolution.split("*")[0]
                download_video_height = download_video_resolution.split("*")[-1]
                download_video_send_time = video.strip().split(" + ")[9]
                download_user_name = video.strip().split(" + ")[10]
                download_head_url = video.strip().split(" + ")[11]
                download_cover_url = video.strip().split(" + ")[12]
                download_video_url = video.strip().split(" + ")[13]
                download_video_session = video.strip().split(" + ")[-1]

                if cls.play_rule(download_video_width,
                                 download_video_height,
                                 download_video_duration,
                                 download_video_play_cnt) is True:
                    Common.crawler_log().info("开始下载视频:{}".format(download_video_title))
                    # 下载封面
                    Common.download_method(text="cover", d_name=download_video_title, d_url=download_cover_url)
                    # 下载视频
                    Common.download_method(text="video", d_name=download_video_title, d_url=download_video_url)

                    # 保存视频 ID 到 "./txt/kanyikan_videoid.txt"
                    with open("./txt/kanyikan_videoid.txt", "a", encoding="utf8") as f_a:
                        f_a.write(download_video_id + "\n")

                    # 保存视频信息至 "./videos/{download_video_title}/info.txt"
                    with open("./videos/" + download_video_title + "/info.txt", "a", encoding="utf8") as f_a:
                        f_a.write(str(download_video_id) + "\n" +
                                  str(download_video_title) + "\n" +
                                  str(download_video_duration) + "\n" +
                                  str(download_video_play_cnt) + "\n" +
                                  str(download_video_comment_cnt) + "\n" +
                                  str(download_video_like_cnt) + "\n" +
                                  str(download_video_share_cnt) + "\n" +
                                  str(download_video_resolution) + "\n" +
                                  str(download_video_send_time) + "\n" +
                                  str(download_user_name) + "\n" +
                                  str(download_head_url) + "\n" +
                                  str(download_video_url) + "\n" +
                                  str(download_cover_url) + "\n" +
                                  str(download_video_session))

                    # 上传视频
                    Common.crawler_log().info("开始上传视频:{}".format(download_video_title))
                    Publish.upload_and_publish(env, "play")

                    # 删除该视频在kanyikan_feeds.txt中的信息
                    Common.crawler_log().info("删除该视频在kanyikan_feeds.txt中的信息:{}".format(download_video_title))
                    with open("./txt/kanyikan_feeds.txt", "r", encoding="utf8") as f_r:
                        lines = f_r.readlines()
                    with open("./txt/kanyikan_feeds.txt", "w", encoding="utf-8") as f_w:
                        for line in lines:
                            if download_video_id in line.split(" + ")[1]:
                                continue
                            f_w.write(line)
                else:
                    # 删除该视频在 recommend.txt中的信息
                    Common.crawler_log().info("该视频不满足下载规则，删除在kanyikan_feeds.txt中的信息:{}".format(download_video_title))
                    with open("./txt/kanyikan_feeds.txt", "r", encoding="utf8") as f_r:
                        lines = f_r.readlines()
                    with open("./txt/kanyikan_feeds.txt", "w", encoding="utf-8") as f_w:
                        for line in lines:
                            if download_video_id in line.split(" + ")[1]:
                                continue
                            f_w.write(line)
            except Exception as e:
                Common.crawler_log().info("视频 info 异常".format(e))
                with open("./txt/kanyikan_feeds.txt", "r", encoding="utf8") as f_r:
                    lines = f_r.readlines()
                with open("./txt/kanyikan_feeds.txt", "w", encoding="utf-8") as f_w:
                    for line in lines:
                        if download_video_id in line.split(" + ")[1]:
                            continue
                        f_w.write(line)


if __name__ == "__main__":
    download_play = DownloadPlay()
    get_feeds()
    download_play.download_play_video("dev")