crawler_kanyikan/main/download_sendtime.py

# -*- coding: utf-8 -*-
# @Author: wangkun
# @Time: 2022/4/18
"""
下载并上传：发布时间榜
规则：
    1.基本规则：send_time_rule()
    2.视频发布3日内，播放量大于2万（当前时间 - 发布时间 <= 3 天）
"""
import json
import os
import random
import sys
import time
import requests
import urllib3

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

proxies = {"http": None, "https": None}


class DownloadSendtime:

    @staticmethod
    def send_time_rule(send_time_width, send_time_height, send_time_duration, send_time_share_cnt):
        """
        1.分辨率，宽或者高 >= 720 or == 0
        2.600s >= 时长 >= 60s
        3.视频播放量 >= 0
        """
        if int(send_time_width) >= 720 or int(send_time_height) >= 720 \
                or send_time_width == "0" or send_time_height == "0":
            if 600 >= int(send_time_duration) >= 60:
                if int(send_time_share_cnt) > 0:
                    return True
                else:
                    return False
            else:
                return False
        else:
            return False

    @classmethod
    def download_sendtime_video(cls, env):
        """
        视频发布3日内，播放量大于2万（当前时间 - 发布时间 <= 3 天）
        :param env: 测试环境：dev；正式环境：prod
        :return: 下载并上传视频
        """
        if len(Feishu.get_values_batch("Y8N3Vl")) == 1:
            pass
        else:
            for i in range(len(Feishu.get_values_batch("Y8N3Vl"))):
                try:
                    sendtime_session = Common.get_session()
                    Common.crawler_log().info("获取视频info时，session：{}".format(sendtime_session))
                    download_video_id = Feishu.get_values_batch("Y8N3Vl")[i+1][1]
                    download_video_title = Feishu.get_values_batch("Y8N3Vl")[i+1][3]
                    url = "https://search.weixin.qq.com/cgi-bin/recwxa/recwxagetonevideoinfo?"
                    param = {
                        "session": sendtime_session,
                        "vid": download_video_id,
                        "wxaVersion": "3.9.2",
                        "channelid": "208201",
                        "scene": "32",
                        "subscene": "1089",
                        "model": "iPhone 11<iPhone12,1>14.7.1",
                        "clientVersion": "8.0.18",
                        "sharesearchid": "447665862521758270",
                        "sharesource": "-1"
                    }
                    urllib3.disable_warnings()
                    r = requests.get(url=url, params=param, proxies=proxies, verify=False)
                    response = json.loads(r.content.decode("utf8"))
                    if "data" not in response:
                        Common.crawler_log().error("获取视频info时错误，删除该视频:{}".format(download_video_title))
                        # 删除行或列，可选 ROWS、COLUMNS
                        Feishu.dimension_range("Y8N3Vl", "ROWS", i + 2, i + 2)
                    else:
                        data = response["data"]
                        v_duration = data["duration"]
                        v_play_cnt_sendtime = data["played_cnt"]
                        v_comment_cnt = data["comment_cnt"]
                        v_liked_cnt = data["liked_cnt"]
                        v_shared_cnt = data["shared_cnt"]
                        v_width = data["width"]
                        v_height = data["height"]
                        v_resolution = str(v_width) + "*" + str(v_height)
                        v_send_date = data["upload_time"]
                        v_username = data["user_info"]["nickname"].strip().replace("\n", "")
                        v_user_cover = data["user_info"]["headimg_url"]
                        v_video_cover = data["cover_url"]
                        if "items" not in data["play_info"]:
                            if len(data["play_info"]) > 2:
                                download_url_up = data["play_info"][2]["play_url"]
                                # Common.crawler_log().info('视频下载地址：{}'.format(download_url_up))
                            else:
                                download_url_up = data["play_info"][0]["play_url"]
                                # Common.crawler_log().info('视频下载地址：{}'.format(download_url_up))
                        else:
                            if len(data["play_info"]["items"]) > 2:
                                download_url_up = data["play_info"]["items"][2]["play_url"]
                                # Common.crawler_log().info('视频下载地址：{}'.format(download_url_up))
                            else:
                                download_url_up = data["play_info"]["items"][0]["play_url"]
                                # Common.crawler_log().info('视频下载地址：{}'.format(download_url_up))

                        # 判断基本规则
                        if cls.send_time_rule(v_width, v_height, v_duration, v_play_cnt_sendtime) is True \
                                and download_video_id != "" and download_video_title != "" and v_duration != "" \
                                and v_play_cnt_sendtime != "" and v_comment_cnt != "" and v_liked_cnt != "" \
                                and v_shared_cnt != "" and v_width != "" and v_height != "" \
                                and v_send_date != "" and v_username != "" and v_user_cover != "" \
                                and v_video_cover != "" and download_url_up != "":
                            # 满足下载条件：当前时间 - 发布时间 <= 3天，播放量大于1万
                            if int(time.time()) - int(v_send_date) <= 604800:
                                if int(v_play_cnt_sendtime) >= 10000:
                                    Common.crawler_log().info("该视频:{}".format(
                                        download_video_title) + " " + "在7天内的播放量{}>=10000".format(v_play_cnt_sendtime))

                                    # 下载封面
                                    Common.download_method("cover", download_video_title, v_video_cover)
                                    # 下载视频
                                    Common.download_method("video", download_video_title, download_url_up)
                                    # 保存视频信息到 "./files/{视频标题}/videoinfo.txt"
                                    with open(r"./videos/" + download_video_title +
                                              "/" + "info.txt", "a", encoding="utf8") as f_a2:
                                        f_a2.write(str(download_video_id) + "\n" +
                                                   str(download_video_title) + "\n" +
                                                   str(v_duration) + "\n" +
                                                   str(v_play_cnt_sendtime) + "\n" +
                                                   str(v_comment_cnt) + "\n" +
                                                   str(v_liked_cnt) + "\n" +
                                                   str(v_shared_cnt) + "\n" +
                                                   str(v_resolution) + "\n" +
                                                   str(v_send_date) + "\n" +
                                                   str(v_username) + "\n" +
                                                   str(v_user_cover) + "\n" +
                                                   str(download_url_up) + "\n" +
                                                   str(v_video_cover) + "\n" +
                                                   str(sendtime_session))

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

                                    # 保存视频 ID 到云文档:
                                    # https://w42nne6hzg.feishu.cn/sheets/shtcngRPoDYAi24x52j2nDuHMih?sheet=20ce0c
                                    Common.crawler_log().info("保存视频ID至云文档:{}".format(download_video_title))
                                    # 看一看+ ，视频ID工作表，插入首行
                                    Feishu.insert_columns("20ce0c")
                                    # 看一看+ ，视频ID工作表，首行写入数据
                                    Feishu.update_values("20ce0c", download_video_id, "", "", "",
                                                         "", "", "", "", "", "", "", "", "", "", "")

                                    # 从云文档删除该视频信息:https://w42nne6hzg.feishu.cn/sheets/shtcngRPoDYAi24x52j2nDuHMih?sheet=Y8N3Vl
                                    Common.crawler_log().info("从云文档删除该视频信息:{}".format(download_video_title))
                                    # 删除行或列，可选 ROWS、COLUMNS
                                    Feishu.dimension_range("Y8N3Vl", "ROWS", i + 2, i + 2)

                                else:
                                    # 从云文档删除该视频信息:https://w42nne6hzg.feishu.cn/sheets/shtcngRPoDYAi24x52j2nDuHMih?sheet=Y8N3Vl
                                    Common.crawler_log().info("该视频7天播放量：{}<10000".format(
                                        int(v_play_cnt_sendtime)) + "；" + "不满足下载规则:{}".format(download_video_title))
                                    # 删除行或列，可选 ROWS、COLUMNS
                                    Feishu.dimension_range("Y8N3Vl", "ROWS", i + 2, i + 2)
                            else:
                                # 从云文档删除该视频信息:https://w42nne6hzg.feishu.cn/sheets/shtcngRPoDYAi24x52j2nDuHMih?sheet=Y8N3Vl
                                Common.crawler_log().info("视频发布时间大于7天：{}天".format(
                                    int((int(time.time()) - int(v_send_date)) / 86400))
                                                          + "；" + "标题：{}".format(download_video_title))
                                # 删除行或列，可选 ROWS、COLUMNS
                                Feishu.dimension_range("Y8N3Vl", "ROWS", i + 2, i + 2)
                        else:
                            # 从云文档删除该视频信息:https://w42nne6hzg.feishu.cn/sheets/shtcngRPoDYAi24x52j2nDuHMih?sheet=Y8N3Vl
                            Common.crawler_log().info("不满足下载规则：{}".format(download_video_title))
                            # 删除行或列，可选 ROWS、COLUMNS
                            Feishu.dimension_range("Y8N3Vl", "ROWS", i + 2, i + 2)

                except Exception as e:
                    Common.crawler_log().error("获取视频info异常：{}，删除该视频".format(e))
                    # 删除行或列，可选 ROWS、COLUMNS
                    Feishu.dimension_range("Y8N3Vl", "ROWS", i + 2, i + 2)

            cls.download_sendtime_video("prod")


if __name__ == "__main__":
    download_sendtime = DownloadSendtime()
    get_feeds()
    download_sendtime.download_sendtime_video("dev")