first commit

README.md

@@ -1,6 +1,6 @@
-音乐相册小程序爬虫:https://git.yishihui.com/Server/crawler_music_album
+音乐相册小程序爬虫: https://git.yishihui.com/Server/crawler_music_album
 
-云文档:https://w42nne6hzg.feishu.cn/sheets/shtcnT6zvmfsYe1g0iv4pt7855g?sheet=f5a76e
+云文档: https://w42nne6hzg.feishu.cn/sheets/shtcnT6zvmfsYe1g0iv4pt7855g?sheet=f5a76e
 
 ffmpeg==1.4
 ffmpeg_python==0.2.0
@@ -19,7 +19,7 @@ python3 main/run_recommend.py
 
 #**********2022/7/13**********#
 
-1. 基础筛选门槛 
+1.基础筛选门槛 
 
 - 播放量≥20000
 
@@ -28,7 +28,7 @@ python3 main/run_recommend.py
 - 视频时长≥1分钟
 
 
-2. 视频下载门槛
+2.视频下载门槛
 
 - 标题为空的视频，不进行下载。
 
@@ -39,7 +39,7 @@ python3 main/run_recommend.py
 - 标题中含有以下词汇的视频，直接过滤掉，不进行下载。
 
 
-3. 视频上传
+3.视频上传
 
 - 渠道号：YINYUEXIANGCE
 

logs/__init__.py

@@ -0,0 +1,3 @@
+# -*- coding: utf-8 -*-
+# @Author: wangkun
+# @Time: 2022/7/12

main/__init__.py

@@ -0,0 +1,3 @@
+# -*- coding: utf-8 -*-
+# @Author: wangkun
+# @Time: 2022/7/12

main/common.py

@@ -0,0 +1,136 @@
+# -*- coding: utf-8 -*-
+# @Author: wangkun
+# @Time: 2022/7/12
+"""
+公共方法，包含：生成log / 删除log / 获取session  / 下载方法 / 读取文件 / 统计下载数
+"""
+import json
+from datetime import date, timedelta
+import datetime
+import os
+import time
+import requests
+import urllib3
+from loguru import logger
+
+proxies = {"http": None, "https": None}
+
+
+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(log_type):
+        """
+        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
+        if log_type == "recommend":
+            log_name = time.strftime("%Y-%m-%d", time.localtime(time.time())) + '-music-album-recommend.log'
+        elif log_type == "follow":
+            log_name = time.strftime("%Y-%m-%d", time.localtime(time.time())) + '-music-album-follow.log'
+        else:
+            log_name = time.strftime("%Y-%m-%d", time.localtime(time.time())) + '-music-album.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, log_type):
+        """
+        清除冗余日志文件
+        :return: 保留最近 7 个日志
+        """
+        log_dir = "./logs/"
+        all_files = sorted(os.listdir(log_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(log_dir + file)
+        cls.logger(log_type).info("清除冗余日志成功")
+
+        # 删除 charles 缓存文件，只保留最近的两个文件
+
+    # 封装下载视频或封面的方法
+    @classmethod
+    def download_method(cls, log_type, 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 + "/"
+        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"
+
+            # 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)
+                cls.logger(log_type).info("==========视频下载完成==========")
+            except Exception as e:
+                cls.logger(log_type).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"
+
+            # 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)
+                cls.logger(log_type).info("==========封面下载完成==========")
+            except Exception as e:
+                cls.logger(log_type).exception("封面下载失败：{}", e)
+
+
+if __name__ == "__main__":
+    common = Common()

main/demo.py

@@ -0,0 +1,61 @@
+# -*- coding: utf-8 -*-
+# @Author: wangkun
+# @Time: 2022/7/12
+import shutil
+import ffmpeg
+
+
+class Demo:
+    # 获取已下载视频宽高、时长等信息
+    @classmethod
+    def get_video_info_from_local(cls, video_path):
+        probe = ffmpeg.probe(video_path)
+        # print('video_path: {}'.format(video_path))
+        # format1 = probe['format']
+        # bit_rate = int(format1['bit_rate']) / 1000
+        # duration = format['duration']
+        # size = int(format1['size']) / 1024 / 1024
+        video_stream = next((stream for stream in probe['streams'] if stream['codec_type'] == 'video'), None)
+        if video_stream is None:
+            print('No video stream found!')
+            return
+        width = int(video_stream['width'])
+        height = int(video_stream['height'])
+        # num_frames = int(video_stream['nb_frames'])
+        # fps = int(video_stream['r_frame_rate'].split('/')[0]) / int(video_stream['r_frame_rate'].split('/')[1])
+        duration = float(video_stream['duration'])
+        # print('width: {}'.format(width))
+        # print('height: {}'.format(height))
+        # print('num_frames: {}'.format(num_frames))
+        # print('bit_rate: {}k'.format(bit_rate))
+        # print('fps: {}'.format(fps))
+        # print('size: {}MB'.format(size))
+        # print('duration: {}'.format(duration))
+        return width, height, duration
+
+    # 判断视频时长是否大于 60s
+    @classmethod
+    def check_duration(cls):
+        # 获取视频时长
+        video_info = cls.get_video_info_from_local("../videos/11111/video.mp4")
+        video_duration = video_info[2]
+        if int(video_duration) < 60:
+            shutil.rmtree("../videos/11111/")
+        else:
+            print(f"video_duration:{video_duration}")
+
+    # 判断 title 长度
+    @classmethod
+    def check_title_len(cls):
+        title = "🌸这首《老公赚钱给老婆花》🌸被唱的太肉麻了🌸好听好看🌸这首《老公赚钱给老婆花》🌸被唱的太肉麻了🌸好听好看"[:30]
+        # print(len(title))
+        # if len(title) > 30:
+        #     title = title[:30]
+        print(title)
+        print(len(title))
+
+
+if __name__ == "__main__":
+    demo = Demo()
+    # demo.check_duration()
+    demo.check_title_len()

main/feishu_lib.py

@@ -0,0 +1,309 @@
+# -*- coding: utf-8 -*-
+# @Author: wangkun
+# @Time: 2022/7/12
+import json
+
+import requests
+import urllib3
+
+from main.common import Common
+
+proxies = {"http": None, "https": None}
+
+
+class Feishu:
+    """
+    编辑飞书云文档
+    """
+    # 看一看爬虫数据表
+    kanyikan_url = "https://w42nne6hzg.feishu.cn/sheets/shtcngRPoDYAi24x52j2nDuHMih?"
+    # 快手爬虫数据表
+    kuaishou_url = "https://w42nne6hzg.feishu.cn/sheets/shtcnp4SaJt37q6OOOrYzPMjQkg?"
+    # 微视爬虫数据表
+    weishi_url = "https://w42nne6hzg.feishu.cn/sheets/shtcn5YSWg91JfVGzj0SFZIRRPh?"
+    # 小年糕爬虫数据表
+    xiaoniangao_url = "https://w42nne6hzg.feishu.cn/sheets/shtcnYxiyQ1wLklo1W5Kdqc9cGh?"
+    # 音乐相册
+    music_album = "https://w42nne6hzg.feishu.cn/sheets/shtcnT6zvmfsYe1g0iv4pt7855g?"
+    # 数据监控表
+    crawler_monitor = "https://w42nne6hzg.feishu.cn/sheets/shtcnlZWYazInhf7Z60jkbLRJyd?"
+
+    # 飞书路径token
+    @classmethod
+    def spreadsheettoken(cls, crawler):
+        """
+        :param crawler: 哪个爬虫
+        """
+        if crawler == "kanyikan":
+            return "shtcngRPoDYAi24x52j2nDuHMih"
+        elif crawler == "kuaishou":
+            return "shtcnp4SaJt37q6OOOrYzPMjQkg"
+        elif crawler == "weishi":
+            return "shtcn5YSWg91JfVGzj0SFZIRRPh"
+        elif crawler == "xiaoniangao":
+            return "shtcnYxiyQ1wLklo1W5Kdqc9cGh"
+        elif crawler == "monitor":
+            return "shtcnlZWYazInhf7Z60jkbLRJyd"
+        elif crawler == "music_album":
+            return "shtcnT6zvmfsYe1g0iv4pt7855g"
+
+    # 获取飞书api token
+    @classmethod
+    def get_token(cls, log_type):
+        """
+        获取飞书api token
+        :return:
+        """
+        url = "https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal/"
+        post_data = {"app_id": "cli_a13ad2afa438d00b",  # 这里账号密码是发布应用的后台账号及密码
+                     "app_secret": "4tK9LY9VbiQlY5umhE42dclBFo6t4p5O"}
+
+        try:
+            urllib3.disable_warnings()
+            response = requests.post(url=url, data=post_data, proxies=proxies, verify=False)
+            tenant_access_token = response.json()["tenant_access_token"]
+            return tenant_access_token
+        except Exception as e:
+            Common.logger(log_type).error("获取飞书 api token 异常:{}", e)
+
+    # 获取表格元数据
+    @classmethod
+    def get_metainfo(cls, log_type, crawler):
+        """
+        获取表格元数据
+        :return:
+        """
+        get_metainfo_url = "https://open.feishu.cn/open-apis/sheets/v2/spreadsheets/" \
+                           + cls.spreadsheettoken(crawler) + "/metainfo"
+
+        headers = {
+            "Authorization": "Bearer " + cls.get_token(log_type),
+            "Content-Type": "application/json; charset=utf-8"
+        }
+        params = {
+            "extFields": "protectedRange",  # 额外返回的字段，extFields=protectedRange时返回保护行列信息
+            "user_id_type": "open_id"  # 返回的用户id类型，可选open_id,union_id
+        }
+        try:
+            urllib3.disable_warnings()
+            r = requests.get(url=get_metainfo_url, headers=headers, params=params, proxies=proxies, verify=False)
+            response = json.loads(r.content.decode("utf8"))
+            return response
+        except Exception as e:
+            Common.logger(log_type).error("获取表格元数据异常:{}", e)
+
+    # 读取工作表中所有数据
+    @classmethod
+    def get_values_batch(cls, log_type, crawler, sheetid):
+        """
+        读取工作表中所有数据
+        :param log_type: 启用哪个 log
+        :param crawler: 哪个爬虫
+        :param sheetid: 哪张表
+        :return: 所有数据
+        """
+        get_values_batch_url = "https://open.feishu.cn/open-apis/sheets/v2/spreadsheets/" \
+                               + cls.spreadsheettoken(crawler) + "/values_batch_get"
+        headers = {
+            "Authorization": "Bearer " + cls.get_token(log_type),
+            "Content-Type": "application/json; charset=utf-8"
+        }
+        params = {
+            # 多个查询范围 如 url?ranges=range1,range2 ，其中 range 包含 sheetId 与单元格范围两部分
+            "ranges": sheetid,
+
+            # valueRenderOption=ToString 可返回纯文本的值(数值类型除外)；
+            # valueRenderOption=FormattedValue 计算并格式化单元格；
+            # valueRenderOption=Formula单元格中含有公式时返回公式本身；
+            # valueRenderOption=UnformattedValue计算但不对单元格进行格式化
+            "valueRenderOption": "ToString",
+
+            # dateTimeRenderOption=FormattedString 计算并将时间日期按照其格式进行格式化，但不会对数字进行格式化，返回格式化后的字符串。
+            "dateTimeRenderOption": "",
+
+            # 返回的用户id类型，可选open_id,union_id
+            "user_id_type": "open_id"
+        }
+        try:
+            urllib3.disable_warnings()
+            r = requests.get(url=get_values_batch_url, headers=headers, params=params, proxies=proxies, verify=False)
+            # print(r.text)
+            response = json.loads(r.content.decode("utf8"))
+            values = response["data"]["valueRanges"][0]["values"]
+            return values
+        except Exception as e:
+            Common.logger(log_type).error("读取工作表所有数据异常:{}", e)
+
+    # 工作表，插入行或列
+    @classmethod
+    def insert_columns(cls, log_type, crawler, sheetid, majordimension, startindex, endindex):
+        """
+        工作表插入行或列
+        :param log_type: 日志路径
+        :param crawler: 哪个爬虫的云文档
+        :param sheetid:哪张工作表
+        :param majordimension:行或者列, ROWS、COLUMNS
+        :param startindex:开始位置
+        :param endindex:结束位置
+        """
+        insert_columns_url = "https://open.feishu.cn/open-apis/sheets/v2/spreadsheets/" \
+                             + cls.spreadsheettoken(crawler) + "/insert_dimension_range"
+        headers = {
+            "Authorization": "Bearer " + cls.get_token(log_type),
+            "Content-Type": "application/json; charset=utf-8"
+        }
+        body = {
+            "dimension": {
+                "sheetId": sheetid,
+                "majorDimension": majordimension,  # 默认 ROWS ，可选 ROWS、COLUMNS
+                "startIndex": startindex,  # 开始的位置
+                "endIndex": endindex  # 结束的位置
+            },
+            "inheritStyle": "AFTER"  # BEFORE 或 AFTER，不填为不继承 style
+        }
+        try:
+            urllib3.disable_warnings()
+            r = requests.post(url=insert_columns_url, headers=headers, json=body, proxies=proxies, verify=False)
+            Common.logger(log_type).info("插入行或列:{}", r.json()["msg"])
+        except Exception as e:
+            Common.logger(log_type).error("插入行或列异常:{}", e)
+
+    # 写入数据
+    @classmethod
+    def update_values(cls, log_type, crawler, sheetid, ranges, values):
+        """
+        写入数据
+        :param log_type: 日志路径
+        :param crawler: 哪个爬虫的云文档
+        :param sheetid:哪张工作表
+        :param ranges:单元格范围
+        :param values:写入的具体数据，list
+        """
+        update_values_url = "https://open.feishu.cn/open-apis/sheets/v2/spreadsheets/" \
+                            + cls.spreadsheettoken(crawler) + "/values_batch_update"
+        headers = {
+            "Authorization": "Bearer " + cls.get_token(log_type),
+            "Content-Type": "application/json; charset=utf-8"
+        }
+        body = {
+            "valueRanges": [
+                {
+                    "range": sheetid + "!" + ranges,
+                    "values": values
+                },
+            ],
+        }
+
+        try:
+            urllib3.disable_warnings()
+            r = requests.post(url=update_values_url, headers=headers, json=body, proxies=proxies, verify=False)
+            Common.logger(log_type).info("写入数据:{}", r.json()["msg"])
+        except Exception as e:
+            Common.logger(log_type).error("写入数据异常:{}", e)
+
+    # 合并单元格
+    @classmethod
+    def merge_cells(cls, log_type, crawler, sheetid, ranges):
+        """
+        合并单元格
+        :param log_type: 日志路径
+        :param crawler: 哪个爬虫
+        :param sheetid:哪张工作表
+        :param ranges:需要合并的单元格范围
+        """
+        merge_cells_url = "https://open.feishu.cn/open-apis/sheets/v2/spreadsheets/" \
+                          + cls.spreadsheettoken(crawler) + "/merge_cells"
+        headers = {
+            "Authorization": "Bearer " + cls.get_token(log_type),
+            "Content-Type": "application/json; charset=utf-8"
+        }
+
+        body = {
+            "range": sheetid + "!" + ranges,
+            "mergeType": "MERGE_ROWS"
+        }
+
+        try:
+            urllib3.disable_warnings()
+            r = requests.post(url=merge_cells_url, headers=headers, json=body, proxies=proxies, verify=False)
+            Common.logger(log_type).info("合并单元格:{}", r.json()["msg"])
+        except Exception as e:
+            Common.logger(log_type).error("合并单元格异常:{}", e)
+
+    # 读取单元格数据
+    @classmethod
+    def get_range_value(cls, log_type, crawler, sheetid, cell):
+        """
+        读取单元格内容
+        :param log_type: 日志路径
+        :param crawler: 哪个爬虫
+        :param sheetid: 哪张工作表
+        :param cell: 哪个单元格
+        :return: 单元格内容
+        """
+        get_range_value_url = "https://open.feishu.cn/open-apis/sheets/v2/spreadsheets/" \
+                              + cls.spreadsheettoken(crawler) + "/values/" + sheetid + "!" + cell
+        headers = {
+            "Authorization": "Bearer " + cls.get_token(log_type),
+            "Content-Type": "application/json; charset=utf-8"
+        }
+        params = {
+            # valueRenderOption=ToString 可返回纯文本的值(数值类型除外)；
+            # valueRenderOption=FormattedValue 计算并格式化单元格；
+            # valueRenderOption=Formula 单元格中含有公式时返回公式本身；
+            # valueRenderOption=UnformattedValue 计算但不对单元格进行格式化。
+            "valueRenderOption": "FormattedValue",
+
+            # dateTimeRenderOption=FormattedString 计算并对时间日期按照其格式进行格式化，但不会对数字进行格式化，返回格式化后的字符串。
+            "dateTimeRenderOption": "",
+
+            # 返回的用户id类型，可选open_id,union_id
+            "user_id_type": "open_id"
+        }
+        try:
+            urllib3.disable_warnings()
+            r = requests.get(url=get_range_value_url, headers=headers, params=params, proxies=proxies, verify=False)
+            # print(r.text)
+            return r.json()["data"]["valueRange"]["values"][0]
+        except Exception as e:
+            Common.logger(log_type).error("读取单元格数据异常:{}", e)
+
+    # 删除行或列，可选 ROWS、COLUMNS
+    @classmethod
+    def dimension_range(cls, log_type, crawler, sheetid, major_dimension, startindex, endindex):
+        """
+        删除行或列
+        :param log_type: 日志路径
+        :param crawler: 哪个爬虫
+        :param sheetid:工作表
+        :param major_dimension:默认 ROWS ，可选 ROWS、COLUMNS
+        :param startindex:开始的位置
+        :param endindex:结束的位置
+        :return:
+        """
+        dimension_range_url = "https://open.feishu.cn/open-apis/sheets/v2/spreadsheets/" \
+                              + cls.spreadsheettoken(crawler) + "/dimension_range"
+        headers = {
+            "Authorization": "Bearer " + cls.get_token(log_type),
+            "Content-Type": "application/json; charset=utf-8"
+        }
+        body = {
+            "dimension": {
+                "sheetId": sheetid,
+                "majorDimension": major_dimension,
+                "startIndex": startindex,
+                "endIndex": endindex
+                }
+            }
+        try:
+            urllib3.disable_warnings()
+            r = requests.delete(url=dimension_range_url, headers=headers, json=body, proxies=proxies, verify=False)
+            Common.logger(log_type).info("删除视频数据:{}", r.json()["msg"])
+        except Exception as e:
+            Common.logger(log_type).error("删除视频数据异常:{}", e)
+
+
+if __name__ == "__main__":
+    feishu = Feishu()
+
+    pass

main/publish.py

@@ -0,0 +1,259 @@
+# -*- coding: utf-8 -*-
+# @Author: wangkun
+# @Time: 2022/7/12
+"""
+上传视频到阿里云 OSS
+上传视频到管理后台
+"""
+import json
+import os
+import random
+import time
+import oss2
+import requests
+import urllib3
+from main.common import Common
+
+proxies = {"http": None, "https": None}
+
+
+class Publish:
+    @classmethod
+    def publish_video_dev(cls, log_type, request_data):
+        """
+        loginUid  站内uid (随机)
+        appType  默认：888888
+        crawlerSrcId   站外视频ID
+        crawlerSrcCode   渠道（自定义 KYK）
+        crawlerSrcPublishTimestamp  视频原发布时间
+        crawlerTaskTimestamp   爬虫创建时间（可以是当前时间）
+        videoPath  视频oss地址
+        coverImgPath  视频封面oss地址
+        title  标题
+        totalTime  视频时长
+        viewStatus  视频的有效状态 默认1
+        versionCode  版本 默认1
+        :return:
+        """
+        # Common.logger(log_type).info('publish request data: {}'.format(request_data))
+        result = cls.request_post('https://videotest.yishihui.com/longvideoapi/crawler/video/send', request_data)
+        # Common.logger(log_type).info('publish result: {}'.format(result))
+        video_id = result["data"]["id"]
+        # Common.logger(log_type).info('video_id: {}'.format(video_id))
+        if result['code'] != 0:
+            Common.logger(log_type).error('pushlish failure msg = {}'.format(result['msg']))
+        else:
+            Common.logger(log_type).info('publish success video_id = : {}'.format(request_data['crawlerSrcId']))
+        return video_id
+
+    @classmethod
+    def publish_video_prod(cls, log_type, request_data):
+        """
+        loginUid  站内uid (随机)
+        appType  默认：888888
+        crawlerSrcId   站外视频ID
+        crawlerSrcCode   渠道（自定义 KYK）
+        crawlerSrcPublishTimestamp  视频原发布时间
+        crawlerTaskTimestamp   爬虫创建时间（可以是当前时间）
+        videoPath  视频oss地址
+        coverImgPath  视频封面oss地址
+        title  标题
+        totalTime  视频时长
+        viewStatus  视频的有效状态 默认1
+        versionCode  版本 默认1
+        :return:
+        """
+        result = cls.request_post('https://longvideoapi.piaoquantv.com/longvideoapi/crawler/video/send', request_data)
+        # Common.logger(log_type).info('publish result: {}'.format(result))
+        video_id = result["data"]["id"]
+        # Common.logger(log_type).info('video_id: {}'.format(video_id))
+        if result['code'] != 0:
+            Common.logger(log_type).error('pushlish failure msg = {}'.format(result['msg']))
+        else:
+            Common.logger(log_type).info('publish success video_id = : {}'.format(request_data['crawlerSrcId']))
+        return video_id
+
+    @classmethod
+    def request_post(cls, request_url, request_data):
+        """
+        post 请求 HTTP接口
+        :param request_url: 接口URL
+        :param request_data: 请求参数
+        :return: res_data json格式
+        """
+        urllib3.disable_warnings()
+        response = requests.post(url=request_url, data=request_data, proxies=proxies, verify=False)
+        if response.status_code == 200:
+            res_data = json.loads(response.text)
+            return res_data
+
+    # 以下代码展示了基本的文件上传、下载、罗列、删除用法。
+
+    # 首先初始化AccessKeyId、AccessKeySecret、Endpoint等信息。
+    # 通过环境变量获取，或者把诸如“<你的AccessKeyId>”替换成真实的AccessKeyId等。
+    #
+    # 以杭州区域为例，Endpoint可以是：
+    #   http://oss-cn-hangzhou.aliyuncs.com
+    #   https://oss-cn-hangzhou.aliyuncs.com
+    # 分别以HTTP、HTTPS协议访问。
+    access_key_id = os.getenv('OSS_TEST_ACCESS_KEY_ID', 'LTAIP6x1l3DXfSxm')
+    access_key_secret = os.getenv('OSS_TEST_ACCESS_KEY_SECRET', 'KbTaM9ars4OX3PMS6Xm7rtxGr1FLon')
+    bucket_name = os.getenv('OSS_TEST_BUCKET', 'art-pubbucket')
+    # endpoint = os.getenv('OSS_TEST_ENDPOINT', 'oss-cn-hangzhou-internal.aliyuncs.com')
+    endpoint = os.getenv('OSS_TEST_ENDPOINT', 'oss-cn-hangzhou.aliyuncs.com')
+
+    # 确认上面的参数都填写正确了
+    for param in (access_key_id, access_key_secret, bucket_name, endpoint):
+        assert '<' not in param, '请设置参数：' + param
+
+    # 创建Bucket对象，所有Object相关的接口都可以通过Bucket对象来进行
+    bucket = oss2.Bucket(oss2.Auth(access_key_id, access_key_secret), endpoint, bucket_name)
+
+    """
+    处理流程：
+    1. 定时（每天凌晨1点执行一次）循环files文件下的内容 结构：files -> 视频文件夹 -> 视频文件 + 封面图 + 基本信息
+    2. 视频文件和封面上传到oss
+    - 视频文件oss目录  longvideo/crawler_local/video/prod/文件名
+    - 视频封面oss目录  longvideo/crawler_local/image/prod/文件名
+    3. 发布视频
+    - 读取 基本信息 调用发布接口
+    """
+    # env 日期20220225 文件名
+    oss_file_path_video = 'longvideo/crawler_local/video/{}/{}/{}'
+    oss_file_path_image = 'longvideo/crawler_local/image/{}/{}/{}'
+
+    @classmethod
+    def put_file(cls, log_type, oss_file, local_file):
+        cls.bucket.put_object_from_file(oss_file, local_file)
+        Common.logger(log_type).info("put oss file = {}, local file = {} success".format(oss_file, local_file))
+
+    # 清除本地文件
+    @classmethod
+    def remove_local_file(cls, log_type, local_file):
+        os.remove(local_file)
+        Common.logger(log_type).info("remove local file = {} success".format(local_file))
+
+    # 清除本地文件夹
+    @classmethod
+    def remove_local_file_dir(cls, log_type, local_file):
+        os.rmdir(local_file)
+        Common.logger(log_type).info("remove local file dir = {} success".format(local_file))
+
+    local_file_path = './videos'
+    video_file = 'video'
+    image_file = 'image'
+    info_file = 'info'
+    uids_dev_up = [6267140]
+    uids_dev_play = [6267141]
+    uids_prod_up = [20631253, 20631254, 20631255, 20631256, 20631257,
+                    20631258, 20631259, 20631260, 20631261]
+    uids_prod_play = [20631253, 20631254, 20631255, 20631256, 20631257,
+                      20631258, 20631259, 20631260, 20631261]
+
+    @classmethod
+    def upload_and_publish(cls, log_type, env, job):
+        """
+        上传视频到 oss
+        :param log_type: 选择的 log
+        :param env: 测试环境：dev，正式环境：prod
+        :param job: 上升榜：up，播放量：play
+        """
+        Common.logger(log_type).info("upload_and_publish starting...")
+        today = time.strftime("%Y%m%d", time.localtime())
+        # videos 目录下的所有视频文件夹
+        files = os.listdir(cls.local_file_path)
+        for f in files:
+            try:
+                # 单个视频文件夹
+                fi_d = os.path.join(cls.local_file_path, f)
+                # 确认为视频文件夹
+                if os.path.isdir(fi_d):
+                    # Common.logger(log_type).info('dir = {}'.format(fi_d))
+                    # 列出所有视频文件夹
+                    dir_files = os.listdir(fi_d)
+                    data = {'appType': '888888',
+                            'crawlerSrcCode': 'YINYUEXIANGCE',
+                            'viewStatus': '1',
+                            'versionCode': '1'}
+                    now_timestamp = int(round(time.time() * 1000))
+                    data['crawlerTaskTimestamp'] = str(now_timestamp)
+                    global uid
+                    if env == "dev" and job == "up":
+                        uid = str(random.choice(cls.uids_dev_up))
+                    elif env == "dev" and job == "play":
+                        uid = str(random.choice(cls.uids_dev_play))
+                    elif env == "prod" and job == "up":
+                        uid = str(random.choice(cls.uids_prod_up))
+                    elif env == "prod" and job == "play":
+                        uid = str(random.choice(cls.uids_prod_play))
+                    data['loginUid'] = uid
+                    # 单个视频文件夹下的所有视频文件
+                    for fi in dir_files:
+                        # 视频文件夹下的所有文件路径
+                        fi_path = fi_d + '/' + fi
+                        # Common.logger(log_type).info('dir fi_path = {}'.format(fi_path))
+                        # 读取 info.txt，赋值给 data
+                        if cls.info_file in fi:
+                            f = open(fi_path, "r", encoding="UTF-8")
+                            # 读取数据 数据准确性写入的时候保证 读取暂不处理
+                            for i in range(14):
+                                line = f.readline()
+                                line = line.replace('\n', '')
+                                if line is not None and len(line) != 0 and not line.isspace():
+                                    # Common.logger(log_type).info("line = {}".format(line))
+                                    if i == 0:
+                                        data['crawlerSrcId'] = line
+                                    elif i == 1:
+                                        data['title'] = line
+                                    elif i == 2:
+                                        data['totalTime'] = line
+                                    elif i == 8:
+                                        data['crawlerSrcPublishTimestamp'] = line
+                                else:
+                                    Common.logger(log_type).warning("{} line is None".format(fi_path))
+                            f.close()
+                            # remove info.txt
+                            cls.remove_local_file(log_type, fi_path)
+                    # 刷新数据
+                    dir_files = os.listdir(fi_d)
+                    for fi in dir_files:
+                        fi_path = fi_d + '/' + fi
+                        # Common.logger(log_type).info('dir fi_path = {}'.format(fi_path))
+                        # 上传oss
+                        if cls.video_file in fi:
+                            global oss_video_file
+                            if env == "dev":
+                                oss_video_file = cls.oss_file_path_video.format("dev", today, data['crawlerSrcId'])
+                            elif env == "prod":
+                                oss_video_file = cls.oss_file_path_video.format("prod", today, data['crawlerSrcId'])
+                            # Common.logger(log_type).info("oss_video_file = {}".format(oss_video_file))
+                            cls.put_file(log_type, oss_video_file, fi_path)
+                            data['videoPath'] = oss_video_file
+                            # Common.logger(log_type).info("videoPath = {}".format(oss_video_file))
+                        elif cls.image_file in fi:
+                            global oss_image_file
+                            if env == "dev":
+                                oss_image_file = cls.oss_file_path_image.format("env", today, data['crawlerSrcId'])
+                            elif env == "prod":
+                                oss_image_file = cls.oss_file_path_image.format("prod", today, data['crawlerSrcId'])
+                            # Common.logger(log_type).info("oss_image_file = {}".format(oss_image_file))
+                            cls.put_file(log_type, oss_image_file, fi_path)
+                            data['coverImgPath'] = oss_image_file
+                            # Common.logger(log_type).info("coverImgPath = {}".format(oss_image_file))
+                        # 全部remove
+                        cls.remove_local_file(log_type, fi_path)
+
+                    # 发布
+                    if env == "dev":
+                        video_id = cls.publish_video_dev(log_type, data)
+                    elif env == "prod":
+                        video_id = cls.publish_video_prod(log_type, data)
+                    else:
+                        video_id = cls.publish_video_dev(log_type, data)
+                    cls.remove_local_file_dir(log_type, fi_d)
+                    return video_id
+
+                else:
+                    Common.logger(log_type).warning('file not a dir = {}'.format(fi_d))
+            except Exception as e:
+                Common.logger(log_type).error('upload_and_publish error', e)

main/recommend_list.py

@@ -0,0 +1,437 @@
+# -*- coding: utf-8 -*-
+# @Author: wangkun
+# @Time: 2022/7/12
+import os
+import shutil
+import sys
+import time
+import ffmpeg
+import requests
+import urllib3
+
+sys.path.append(os.getcwd())
+from main.common import Common
+from main.feishu_lib import Feishu
+from main.publish import Publish
+
+
+class Recommend:
+    # 过滤词库
+    @classmethod
+    def sensitive_words(cls, log_type):
+        try:
+            # 敏感词库列表
+            word_list = []
+            # 从云文档读取所有敏感词，添加到词库列表
+            lists = Feishu.get_values_batch(log_type, "music_album", "kNTEno")
+            for i in lists:
+                for j in i:
+                    # 过滤空的单元格内容
+                    if j is None:
+                        pass
+                    else:
+                        word_list.append(j)
+            return word_list
+        except Exception as e:
+            Common.logger(log_type).error("获取过滤词库异常:{}", e)
+
+    # 抓取规则
+    @classmethod
+    def get_rule(cls, play_cnt, share_cnt, duration):
+        """
+        - 播放量≥20000
+        - 分享量≥200
+        - 视频时长≥1分钟
+        :return:
+        """
+        if int(play_cnt) >= 20000:
+            if int(share_cnt) >= 200:
+                if int(duration) >= 60:
+                    return True
+                else:
+                    return False
+            else:
+                return False
+        else:
+            return False
+
+    # 下载规则
+    @classmethod
+    def download_rule(cls, share_cnt, play_cnt):
+        """
+        - 标题为空的视频，不进行下载。
+        - 视频时长<1分钟，不进行下载。
+        - 分享率<1%的视频，不进行下载（分享量/播放量）
+        - 标题中含有以下词汇的视频，直接过滤掉，不进行下载。
+        :return:
+        """
+        if int(share_cnt) / int(play_cnt) >= 0.01:
+            return True
+        else:
+            return False
+
+    # 获取已下载视频宽高、时长等信息
+    @classmethod
+    def get_video_info_from_local(cls, video_path):
+        probe = ffmpeg.probe(video_path)
+        # print('video_path: {}'.format(video_path))
+        # format1 = probe['format']
+        # bit_rate = int(format1['bit_rate']) / 1000
+        # duration = format['duration']
+        # size = int(format1['size']) / 1024 / 1024
+        video_stream = next((stream for stream in probe['streams'] if stream['codec_type'] == 'video'), None)
+        if video_stream is None:
+            print('No video stream found!')
+            return
+        width = int(video_stream['width'])
+        height = int(video_stream['height'])
+        # num_frames = int(video_stream['nb_frames'])
+        # fps = int(video_stream['r_frame_rate'].split('/')[0]) / int(video_stream['r_frame_rate'].split('/')[1])
+        duration = float(video_stream['duration'])
+        # print('width: {}'.format(width))
+        # print('height: {}'.format(height))
+        # print('num_frames: {}'.format(num_frames))
+        # print('bit_rate: {}k'.format(bit_rate))
+        # print('fps: {}'.format(fps))
+        # print('size: {}MB'.format(size))
+        # print('duration: {}'.format(duration))
+        return width, height, duration
+
+    # 获取视频ID
+    @classmethod
+    def get_video_list(cls, log_type):
+        try:
+            # 翻十页
+            for num in range(1, 11):
+                Common.logger(log_type).info("正在抓取第{}页\n", num)
+                url = "https://pro.yaoman.net/api/work/list/%E6%8E%A8%E8%8D%90/" + str(num)
+                headers = {
+                    "accept": "*/*",
+                    "content-type": "application/json",
+                    "token": "%2FaEAzNLTTD%2FsGLazE6FsaaNUpTrgL%2FcNPVKzHD%2BgvhLiY"
+                             "ypZm%2BQWA2OQFvQEcPYPZXJNJ8Cm79KY2ueyjn"
+                             "5laR9RKc0D33DWK7ErpVFst4tVT%2BnQpxzdA1Fg%2F0Eop8LY",
+                    "accept-language": "zh-CN,zh-Hans;q=0.9",
+                    "user-agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 11_3 like Mac OS X)"
+                                  " AppleWebKit/605.1.15 (KHTML, like Gecko)"
+                                  " Mobile/15E217 MicroMessenger/6.8.0(0x16080000)"
+                                  " NetType/WIFI Language/en Branch/Br_trunk MiniProgramEnv/Mac",
+                    "accept-encoding": "gzip, deflate, br",
+                    "referer": "https://servicewechat.com/wx6d6f1348072452e9/21/page-frame.html"
+                }
+                urllib3.disable_warnings()
+                r = requests.get(url=url, headers=headers, verify=False)
+                if "data" not in r.json()["d"] or len(r.json()["d"]["data"]) == 0:
+                    Common.logger(log_type).warning("response:{}", r.text)
+                data = r.json()["d"]["data"]
+                for i in range(len(data)):
+                    if "id" in data[i]:
+                        video_id = data[i]["id"]
+                    else:
+                        video_id = 0
+                    if "cover_url" in data[i]:
+                        cover_url = data[i]["cover_url"]
+                    else:
+                        cover_url = 0
+                    cls.get_video_info(log_type, video_id, cover_url)
+        except Exception as e:
+            Common.logger(log_type).error("get_video_list异常:{}", e)
+
+    # 获取视频详情
+    @classmethod
+    def get_video_info(cls, log_type, video_id, cover_url):
+        try:
+            url = "https://pro.yaoman.net/api/work/detail/" + str(video_id)
+            headers = {
+                "accept": "*/*",
+                "content-type": "application/json",
+                "token": "%2FaEAzNLTTD%2FsGLazE6FsaaNUpTrgL%2FcNPVKzHD%2BgvhLiYypZm%2BQWA2OQFvQEcPYPZXJNJ8Cm79KY2ueyjn"
+                         "5laR9RKc0D33DWK7ErpVFst4tVT%2BnQpxzdA1Fg%2F0Eop8LY",
+                "accept-language": "zh-CN,zh-Hans;q=0.9",
+                "user-agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 11_3 like Mac OS X)"
+                              " AppleWebKit/605.1.15 (KHTML, like Gecko)"
+                              " Mobile/15E217 MicroMessenger/6.8.0(0x16080000)"
+                              " NetType/WIFI Language/en Branch/Br_trunk MiniProgramEnv/Mac",
+                "accept-encoding": "gzip, deflate, br",
+                "referer": "https://servicewechat.com/wx6d6f1348072452e9/21/page-frame.html"
+            }
+            urllib3.disable_warnings()
+            r = requests.get(url=url, headers=headers, verify=False)
+            if r.json()["m"] != "success":
+                Common.logger(log_type).warning("response:{}", r.text)
+
+            # video_title
+            if "name" in r.json()["d"]:
+                video_title = r.json()["d"]["name"][:30]
+            else:
+                video_title = 0
+
+            # video_id
+            if "id" in r.json()["d"]:
+                video_id = r.json()["d"]["id"]
+            else:
+                video_id = 0
+
+            # play_cnt
+            if "view_number" in r.json()["d"]:
+                play_cnt = r.json()["d"]["view_number"]
+            else:
+                play_cnt = 0
+
+            # like_cnt
+            if "flower_number" in r.json()["d"]:
+                like_cnt = r.json()["d"]["flower_number"]
+            else:
+                like_cnt = 0
+
+            # share_cnt
+            if "share_number" in r.json()["d"]:
+                share_cnt = r.json()["d"]["share_number"]
+            else:
+                share_cnt = 0
+
+            # comment_cnt
+            if "comment_number" in r.json()["d"]:
+                comment_cnt = r.json()["d"]["comment_number"]
+            else:
+                comment_cnt = 0
+
+            # send_time
+            if "updated_at" in r.json()["d"]:
+                send_time = r.json()["d"]["updated_at"]
+            else:
+                send_time = 0
+
+            # user_id
+            if "user" not in r.json()["d"]:
+                user_id = 0
+            elif "id" not in r.json()["d"]["user"]:
+                user_id = 0
+            else:
+                user_id = r.json()["d"]["user"]["id"]
+
+            # user_name
+            if "user" not in r.json()["d"]:
+                user_name = 0
+            elif "nickname" not in r.json()["d"]["user"]:
+                user_name = 0
+            else:
+                user_name = r.json()["d"]["user"]["nickname"]
+
+            # head_url
+            if "user" not in r.json()["d"]:
+                head_url = 0
+            elif "avatar" not in r.json()["d"]["user"]:
+                head_url = 0
+            else:
+                head_url = r.json()["d"]["user"]["avatar"]
+
+            # video_url
+            if "video_url" in r.json()["d"]:
+                video_url = r.json()["d"]["video_url"]
+            else:
+                video_url = 0
+
+            Common.logger(log_type).info("video_title:{}", video_title)
+            Common.logger(log_type).info("video_id:{}", video_id)
+            Common.logger(log_type).info("play_cnt:{}", play_cnt)
+            Common.logger(log_type).info("like_cnt:{}", like_cnt)
+            Common.logger(log_type).info("share_cnt:{}", share_cnt)
+            Common.logger(log_type).info("comment_cnt:{}", comment_cnt)
+            Common.logger(log_type).info("send_time:{}", send_time)
+            Common.logger(log_type).info("user_name:{}", user_name)
+            Common.logger(log_type).info("user_id:{}", user_id)
+            Common.logger(log_type).info("head_url:{}", head_url)
+            Common.logger(log_type).info("cover_url:{}", cover_url)
+            Common.logger(log_type).info("video_url:{}", video_url)
+
+            # 过滤无效视频
+            if video_title == 0 or video_id == 0 or send_time == 0 or head_url == 0 or cover_url == 0 or video_url == 0:
+                Common.logger(log_type).info("无效视频\n")
+            # 抓取规则
+            elif cls.get_rule(play_cnt, share_cnt, "60") is False:
+                Common.logger(log_type).info("不满足抓取规则\n")
+            # 已下载视频表去重
+            elif video_id in [n for m in Feishu.get_values_batch(log_type, "music_album", "f5a76e") for n in m]:
+                Common.logger(log_type).info("该视频已下载\n")
+            # recommend_feeds去重
+            elif video_id in [n for m in Feishu.get_values_batch(log_type, "music_album", "69UxPo") for n in m]:
+                Common.logger(log_type).info("该视频已在recommend_feeds中\n")
+            else:
+                time.sleep(1)
+                Feishu.insert_columns(log_type, "music_album", "69UxPo", "ROWS", 1, 2)
+                get_feeds_time = int(time.time())
+                values = [[str(time.strftime("%Y/%m/%d %H:%M:%S", time.localtime(get_feeds_time))),
+                           "推荐榜",
+                           video_id,
+                           video_title,
+                           play_cnt,
+                           like_cnt,
+                           share_cnt,
+                           comment_cnt,
+                           send_time,
+                           user_name,
+                           user_id,
+                           head_url,
+                           cover_url,
+                           video_url]]
+                time.sleep(1)
+                Feishu.update_values(log_type, "music_album", "69UxPo", "A2:N2", values)
+                Common.logger(log_type).info("添加至recommend_feeds成功\n")
+        except Exception as e:
+            Common.logger(log_type).error("get_video_info异常:{}", e)
+
+    # 下载/上传视频
+    @classmethod
+    def download_publish(cls, log_type, env):
+        try:
+            recommend_feeds_sheet = Feishu.get_values_batch(log_type, "music_album", "69UxPo")
+            for i in range(1, len(recommend_feeds_sheet)):
+                download_video_id = recommend_feeds_sheet[i][2]
+                download_video_title = recommend_feeds_sheet[i][3]
+                download_video_play_cnt = recommend_feeds_sheet[i][4]
+                download_video_comment_cnt = recommend_feeds_sheet[i][7]
+                download_video_like_cnt = recommend_feeds_sheet[i][5]
+                download_video_share_cnt = recommend_feeds_sheet[i][6]
+                download_video_send_time = recommend_feeds_sheet[i][8]
+                download_user_name = recommend_feeds_sheet[i][9]
+                download_user_id = recommend_feeds_sheet[i][10]
+                download_head_url = recommend_feeds_sheet[i][11]
+                download_cover_url = recommend_feeds_sheet[i][12]
+                download_video_url = recommend_feeds_sheet[i][13]
+
+                Common.logger(log_type).info("正在判断第{}行", i + 1)
+                Common.logger(log_type).info("download_video_title:{}", download_video_title)
+                Common.logger(log_type).info("download_video_play_cnt:{}", download_video_play_cnt)
+                # Common.logger(log_type).info("download_video_id:{}", download_video_id)
+                # Common.logger(log_type).info("download_video_comment_cnt:{}", download_video_comment_cnt)
+                # Common.logger(log_type).info("download_video_like_cnt:{}", download_video_like_cnt)
+                Common.logger(log_type).info("download_video_share_cnt:{}", download_video_share_cnt)
+                # Common.logger(log_type).info("download_video_send_time:{}", download_video_send_time)
+                # Common.logger(log_type).info("download_user_name:{}", download_user_name)
+                # Common.logger(log_type).info("download_user_id:{}", download_user_id)
+                # Common.logger(log_type).info("download_head_url:{}", download_head_url)
+                # Common.logger(log_type).info("download_cover_url:{}", download_cover_url)
+                Common.logger(log_type).info("download_video_url:{}", download_video_url)
+
+                # 过滤空行
+                if download_video_id is None or download_video_title is None or download_video_play_cnt is None:
+                    Common.logger(log_type).warning("空行，略过\n")
+                # 过滤敏感词
+                elif any(word if word in download_video_title else False for word in
+                         cls.sensitive_words(log_type)) is True:
+                    Feishu.dimension_range(log_type, "music_album", "69UxPo", "ROWS", i + 1, i + 1)
+                    Common.logger(log_type).info("视频已中敏感词，删除成功\n")
+                    return
+                # 下载规则
+                elif cls.download_rule(download_video_share_cnt, download_video_play_cnt) is False:
+                    Feishu.dimension_range(log_type, "music_album", "69UxPo", "ROWS", i + 1, i + 1)
+                    Common.logger(log_type).info("不满足下载规则，删除成功\n")
+                    return
+                # 已下载视频表去重
+                elif download_video_id in [n for m in Feishu.get_values_batch(log_type, "music_album", "f5a76e") for n
+                                           in m]:
+                    Feishu.dimension_range(log_type, "music_album", "69UxPo", "ROWS", i + 1, i + 1)
+                    Common.logger(log_type).info("该视频已下载，删除成功\n")
+                    return
+                # 满足下载规则
+                else:
+                    # 下载视频
+                    Common.download_method(log_type=log_type, text="video",
+                                           d_name=str(download_video_title), d_url=str(download_video_url))
+                    # 获取视频时长
+                    video_info = cls.get_video_info_from_local("./videos/" + download_video_title + "/video.mp4")
+                    download_video_resolution = str(video_info[0])+"*"+str(video_info[1])
+                    download_video_duration = video_info[2]
+
+                    # 视频时长<60s，直接删除
+                    if int(download_video_duration) < 60:
+                        shutil.rmtree("./videos/" + download_video_title + "/")
+                        Feishu.dimension_range(log_type, "music_album", "69UxPo", "ROWS", i + 1, i + 1)
+                        Common.logger(log_type).info("时长:{}<60秒，删除成功\n", int(download_video_duration))
+                        return
+                    else:
+                        # 下载封面
+                        Common.download_method(log_type=log_type, text="cover",
+                                               d_name=str(download_video_title), d_url=str(download_cover_url))
+                        # 保存视频信息至 "./videos/{download_video_title}/info.txt"
+                        with open("./videos/" + download_video_title
+                                  + "/" + "info.txt", "a", encoding="UTF-8") as f_a:
+                            f_a.write(str(download_video_id) + "\n" +
+                                      str(download_video_title) + "\n" +
+                                      str(int(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(int(time.mktime(
+                                          time.strptime(download_video_send_time, "%Y-%m-%d %H:%M:%S")))) + "\n" +
+                                      str(download_user_name) + "\n" +
+                                      str(download_head_url) + "\n" +
+                                      str(download_video_url) + "\n" +
+                                      str(download_cover_url) + "\n" +
+                                      "YINYUEXIANGCE")
+                        Common.logger(log_type).info("==========视频信息已保存至info.txt==========")
+
+                        # 上传视频
+                        Common.logger(log_type).info("开始上传视频:{}".format(download_video_title))
+                        our_video_id = Publish.upload_and_publish(log_type, env, "play")
+                        our_video_link = "https://admin.piaoquantv.com/cms/post-detail/" + str(our_video_id) + "/info"
+                        Common.logger(log_type).info("视频上传完成:{}", download_video_title)
+
+                        # 保存视频 ID 到云文档:https://w42nne6hzg.feishu.cn/sheets/shtcnT6zvmfsYe1g0iv4pt7855g?sheet=f5a76e
+                        Common.logger(log_type).info("保存视频ID至云文档:{}", download_video_title)
+                        # 视频ID工作表，插入首行
+                        Feishu.insert_columns(log_type, "music_album", "f5a76e", "ROWS", 1, 2)
+                        # 视频ID工作表，首行写入数据
+                        upload_time = int(time.time())
+                        values = [[time.strftime("%Y/%m/%d %H:%M:%S", time.localtime(upload_time)),
+                                   "推荐榜",
+                                   str(download_video_id),
+                                   str(download_video_title),
+                                   our_video_link,
+                                   download_video_play_cnt,
+                                   download_video_comment_cnt,
+                                   download_video_like_cnt,
+                                   download_video_share_cnt,
+                                   int(download_video_duration),
+                                   str(download_video_resolution),
+                                   str(download_video_send_time),
+                                   str(download_user_name),
+                                   str(download_user_id),
+                                   str(download_head_url),
+                                   str(download_cover_url),
+                                   str(download_video_url)]]
+                        time.sleep(1)
+                        Feishu.update_values(log_type, "music_album", "f5a76e", "F2:V2", values)
+
+                        # 删除行或列，可选 ROWS、COLUMNS
+                        Feishu.dimension_range(log_type, "music_album", "69UxPo", "ROWS", i + 1, i + 1)
+                        Common.logger(log_type).info("视频:{}，下载/上传成功\n", download_video_title)
+                        return
+
+        except Exception as e:
+            Feishu.dimension_range(log_type, "music_album", "69UxPo", "ROWS", 2, 2)
+            Common.logger(log_type).error("download_publish异常:{}，删除成功", e)
+
+    # 执行下载/上传
+    @classmethod
+    def run_download_publish(cls, log_type, env):
+        try:
+            while True:
+                recommend_feeds_sheet = Feishu.get_values_batch(log_type, "music_album", "69UxPo")
+                if len(recommend_feeds_sheet) == 1:
+                    Common.logger(log_type).info("下载/上传完成\n")
+                    break
+                else:
+                    cls.download_publish(log_type, env)
+        except Exception as e:
+            Common.logger(log_type).error("run_download_publish异常:{}", e)
+
+
+if __name__ == "__main__":
+    recommend = Recommend()
+    # recommend.get_video_list("recommend")
+    # recommend.get_video_info("recommend", "16911678")
+    recommend.download_publish("recommend", "dev")

main/run_recommend.py

@@ -0,0 +1,32 @@
+# -*- coding: utf-8 -*-
+# @Author: wangkun
+# @Time: 2022/7/13
+import os
+import sys
+import time
+sys.path.append(os.getcwd())
+from main.common import Common
+from main.recommend_list import Recommend
+
+
+class Main:
+    @classmethod
+    def main(cls):
+        while True:
+            # 抓取视频
+            Common.logger("recommend").info("开始抓取音乐相册小程序推荐榜\n")
+            Recommend.get_video_list("recommend")
+            # 下载/上传
+            Common.logger("recommend").info("开始下载/上传音乐相册小程序推荐榜\n")
+            Recommend.run_download_publish("recommend", "prod")
+            # 清除日志
+            Common.logger("recommend").info("开始清除日志")
+            Common.del_logs("recommend")
+            # 休眠
+            Common.logger("recommend").info("休眠 10 分钟\n")
+            time.sleep(600)
+
+
+if __name__ == "__main__":
+    main = Main()
+    main.main()

requirements.txt

@@ -0,0 +1,6 @@
+ffmpeg==1.4
+ffmpeg_python==0.2.0
+loguru==0.6.0
+oss2==2.15.0
+requests==2.27.1
+urllib3==1.26.9

videos/__init__.py

@@ -0,0 +1,3 @@
+# -*- coding: utf-8 -*-
+# @Author: wangkun
+# @Time: 2022/7/12