调试

application/common/feishu/feishu_utils.py

@@ -0,0 +1,402 @@
+# -*- coding: utf-8 -*-
+# @Time: 2023/12/26
+"""
+飞书表配置: token 鉴权 / 增删改查 / 机器人报警
+"""
+import json
+import os
+import sys
+import requests
+import urllib3
+from loguru import logger
+
+sys.path.append(os.getcwd())
+
+proxies = {"http": None, "https": None}
+
+
+class FeishuUtils:
+    """
+    编辑飞书云文档
+    """
+    succinct_url = "https://w42nne6hzg.feishu.cn/sheets/"
+    # 飞书路径token
+    @classmethod
+    def spreadsheettoken(cls, crawler):
+        if crawler == "summary":
+            return "KsoMsyP2ghleM9tzBfmcEEXBnXg"
+        else:
+            return crawler
+
+
+
+    # 获取飞书api token
+    @classmethod
+    def get_token(cls):
+        """
+        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"}
+        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
+
+    # 获取表格元数据
+    @classmethod
+    def get_metainfo(cls, crawler):
+        """
+        获取表格元数据
+        :return:
+        """
+        try:
+            get_metainfo_url = "https://open.feishu.cn/open-apis/sheets/v2/spreadsheets/" \
+                               + cls.spreadsheettoken(crawler) + "/metainfo"
+
+            headers = {
+                "Authorization": "Bearer " + cls.get_token(),
+                "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
+            }
+            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:
+            logger.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, crawler, sheetid):
+        """
+        读取工作表中所有数据
+        :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(),
+            "Content-Type": "application/json; charset=utf-8"
+        }
+        params = {
+            "ranges": sheetid,
+            "valueRenderOption": "ToString",
+            "dateTimeRenderOption": "",
+            "user_id_type": "open_id"
+        }
+        urllib3.disable_warnings()
+        r = requests.get(url=get_values_batch_url, headers=headers, params=params, proxies=proxies, verify=False)
+        response = json.loads(r.content.decode("utf8"))
+        values = response["data"]["valueRanges"][0]["values"]
+        return values
+
+
+    # 工作表，插入行或列
+    @classmethod
+    def insert_columns(cls, 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
+        """
+        try:
+            insert_columns_url = "https://open.feishu.cn/open-apis/sheets/v2/spreadsheets/" \
+                                 + cls.spreadsheettoken(crawler) + "/insert_dimension_range"
+            headers = {
+                "Authorization": "Bearer " + cls.get_token(),
+                "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
+            }
+
+            urllib3.disable_warnings()
+            r = requests.post(url=insert_columns_url, headers=headers, json=body, proxies=proxies, verify=False)
+        except Exception as e:
+            logger.error("插入行或列异常:{}", e)
+
+    # 写入数据
+    @classmethod
+    def update_values(cls, 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
+        """
+        try:
+            update_values_url = "https://open.feishu.cn/open-apis/sheets/v2/spreadsheets/" \
+                                + cls.spreadsheettoken(crawler) + "/values_batch_update"
+            headers = {
+                "Authorization": "Bearer " + cls.get_token(),
+                "Content-Type": "application/json; charset=utf-8"
+            }
+            body = {
+                "valueRanges": [
+                    {
+                        "range": sheetid + "!" + ranges,
+                        "values": values
+                    },
+                ],
+            }
+            urllib3.disable_warnings()
+            r = requests.post(url=update_values_url, headers=headers, json=body, proxies=proxies, verify=False)
+        except Exception as e:
+            logger.error("写入数据异常:{}", e)
+
+    # 合并单元格
+    @classmethod
+    def merge_cells(cls, 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
+        """
+        try:
+            merge_cells_url = "https://open.feishu.cn/open-apis/sheets/v2/spreadsheets/" \
+                              + cls.spreadsheettoken(crawler) + "/merge_cells"
+            headers = {
+                "Authorization": "Bearer " + cls.get_token(),
+                "Content-Type": "application/json; charset=utf-8"
+            }
+
+            body = {
+                "range": sheetid + "!" + ranges,
+                "mergeType": "MERGE_ROWS"
+            }
+            urllib3.disable_warnings()
+            r = requests.post(url=merge_cells_url, headers=headers, json=body, proxies=proxies, verify=False)
+        except Exception as e:
+            logger.error("合并单元格异常:{}", e)
+
+    # 读取单元格数据
+    @classmethod
+    def get_range_value(cls, 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
+        """
+        try:
+            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(),
+                "Content-Type": "application/json; charset=utf-8"
+            }
+            params = {
+                "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"
+            }
+            urllib3.disable_warnings()
+            r = requests.get(url=get_range_value_url, headers=headers, params=params, proxies=proxies, verify=False)
+            # logger.error(r.text)
+            return r.json()["data"]["valueRange"]["values"][0]
+        except Exception as e:
+            logger.error("读取单元格数据异常:{}", e)
+    # 获取表内容
+    @classmethod
+    def get_sheet_content(cls, crawler, sheet_id):
+        try:
+            sheet = Feishu.get_values_batch(crawler, sheet_id)
+            content_list = []
+            for x in sheet:
+                for y in x:
+                    if y is None:
+                        pass
+                    else:
+                        content_list.append(y)
+            return content_list
+        except Exception as e:
+            logger.error(f'get_sheet_content:{e}\n')
+
+    # 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:
+        """
+        try:
+            dimension_range_url = "https://open.feishu.cn/open-apis/sheets/v2/spreadsheets/" \
+                                  + cls.spreadsheettoken(crawler) + "/dimension_range"
+            headers = {
+                "Authorization": "Bearer " + cls.get_token(),
+                "Content-Type": "application/json; charset=utf-8"
+            }
+            body = {
+                "dimension": {
+                    "sheetId": sheetid,
+                    "majorDimension": major_dimension,
+                    "startIndex": startindex,
+                    "endIndex": endindex
+                }
+            }
+            urllib3.disable_warnings()
+            r = requests.delete(url=dimension_range_url, headers=headers, json=body, proxies=proxies, verify=False)
+        except Exception as e:
+            logger.error("删除视频数据异常:{}", e)
+
+    # 获取用户 ID
+    @classmethod
+    def get_userid(cls, username):
+        try:
+            url = "https://open.feishu.cn/open-apis/user/v1/batch_get_id?"
+            headers = {
+                "Authorization": "Bearer " + cls.get_token(),
+                "Content-Type": "application/json; charset=utf-8"
+            }
+            name_phone_dict = {
+                "xinxin": "15546206651",
+                "muxinyi": "13699208058",
+                "wangxueke": "13513479926",
+                "yuzhuoyi": "18624010360",
+                "luojunhui": "18801281360",
+                "fanjun": "15200827642",
+                "zhangyong": "17600025055",
+                'liukunyu': "18810931977"
+            }
+            username = name_phone_dict.get(username)
+
+            data = {"mobiles": [username]}
+            urllib3.disable_warnings()
+            r = requests.get(url=url, headers=headers, params=data, verify=False, proxies=proxies)
+            open_id = r.json()["data"]["mobile_users"][username][0]["open_id"]
+
+            return open_id
+        except Exception as e:
+            pass
+            # logger.error(f"get_userid异常:{e}\n")
+
+    # 飞书机器人
+    @classmethod
+    def bot(cls, log_type, crawler, text, mark_name):
+        try:
+
+            headers = {'Content-Type': 'application/json'}
+            if crawler == "机器自动改造消息通知":
+                url = "https://open.feishu.cn/open-apis/bot/v2/hook/e7697dc6-5254-4411-8b59-3cd0742bf703"
+                sheet_url = "https://w42nne6hzg.feishu.cn/sheets/KsoMsyP2ghleM9tzBfmcEEXBnXg?sheet=bc154d"
+                users = f"<at id=" + str(cls.get_userid(log_type)) + f">{mark_name}</at>"
+            elif crawler == "快手关键词搜索":
+                url = "https://open.feishu.cn/open-apis/bot/v2/hook/e7697dc6-5254-4411-8b59-3cd0742bf703"
+                sheet_url = "https://w42nne6hzg.feishu.cn/sheets/KsoMsyP2ghleM9tzBfmcEEXBnXg?sheet=U1gySe"
+                users = "".join([f'<at id="{cls.get_userid(type)}">{name}</at>' for type, name in
+                                 zip(log_type, mark_name)])
+                # users = f"<at id=" + str(cls.get_userid(log_type)) + f">{mark_name}</at>"
+            else:
+                url = "https://open.feishu.cn/open-apis/bot/v2/hook/7928f182-08c1-4c4d-b2f7-82e10c93ca80"
+                sheet_url = "https://w42nne6hzg.feishu.cn/sheets/KsoMsyP2ghleM9tzBfmcEEXBnXg?sheet=bc154d"
+                users = f"<at id=" + str(cls.get_userid(log_type)) + f">{mark_name}</at>"
+            data = json.dumps({
+                "msg_type": "interactive",
+                "card": {
+                    "config": {
+                        "wide_screen_mode": True,
+                        "enable_forward": True
+                    },
+                    "elements": [{
+                        "tag": "div",
+                        "text": {
+                            "content": users + text,
+                            "tag": "lark_md"
+                        }
+                    }, {
+                        "actions": [{
+                            "tag": "button",
+                            "text": {
+                                "content": "详情,点击～～～～～",
+                                "tag": "lark_md"
+                            },
+                            "url": sheet_url,
+                            "type": "default",
+                            "value": {}
+                        }],
+                        "tag": "action"
+                    }],
+                    "header": {
+                        "title": {
+                            "content": "📣消息提醒",
+                            "tag": "plain_text"
+                        }
+                    }
+                }
+            })
+            urllib3.disable_warnings()
+            r = requests.post(url, headers=headers, data=data, verify=False, proxies=proxies)
+        except Exception as e:
+            logger.error(f"bot异常:{e}\n")
+
+    # 飞书机器人-改造计划完成通知
+    @classmethod
+    def finish_bot(cls, text, url, content):
+        try:
+            headers = {'Content-Type': 'application/json'}
+            data = json.dumps({
+                "msg_type": "interactive",
+                "card": {
+                    "config": {
+                        "wide_screen_mode": True,
+                        "enable_forward": True
+                    },
+                    "elements": [{
+                        "tag": "div",
+                        "text": {
+                            "content": text,
+                            "tag": "lark_md"
+                        }
+                    }],
+                    "header": {
+                        "title": {
+                            "content": content,
+                            "tag": "plain_text"
+                        }
+                    }
+                }
+            })
+            urllib3.disable_warnings()
+            r = requests.post(url, headers=headers, data=data, verify=False, proxies=proxies)
+        except Exception as e:
+            logger.error(f"bot异常:{e}\n")
+
+
+if __name__ == "__main__":
+    Feishu.bot('recommend', '抖音', '测试: 抖音cookie失效，请及时更换')
+

application/pipeline/pipeline.py

@@ -4,6 +4,8 @@ import sys
 import os
 import time
 
+from application.common.feishu.feishu_utils import FeishuUtils
+
 sys.path.append(os.getcwd())
 
 from application.common import MysqlHelper, AliyunLogger
@@ -123,12 +125,41 @@ class PiaoQuanPipeline(object):
                 continue
         return True
 
+    def feishu_list(self):
+        summary = FeishuUtils.get_values_batch("KsoMsyP2ghleM9tzBfmcEEXBnXg", "letS93")
+        for row in summary[1:]:
+            channel = row[0]
+            day_count = row[1]
+            if channel:
+                if channel == self.platform:
+                    return day_count
+            else:
+                return None
+        return None
+
     # 按照某个具体平台来去重
     def repeat_video(self):
         """
         视频是否重复
         :return:
         """
+        out_id = self.item["out_video_id"]
+        day_count = self.feishu_list()
+        if day_count:
+            sql_2 = f"""select create_time from crawler_video where platform = "{self.platform}" and  out_video_id="{out_id}" AND create_time >= DATE_SUB(NOW(), INTERVAL {int(day_count)} DAY);"""
+            repeat_video = self.mysql.select(sql=sql_2)
+            if repeat_video:
+                self.aliyun_log.logging(
+                    code="2002",
+                    trace_id=self.trace_id,
+                    message="重复的视频",
+                    data=self.item,
+                    account=self.account
+                )
+                return False
+            else:
+                return True
+
         if self.platform == "zhufuniannianshunxinjixiang" or  self.platform == "weiquanshipin" or  self.platform == "piaoquangushi" or  self.platform == "lepaoledong" or  self.platform == "zhufukuaizhuan" or self.platform == "linglingkuailezhufu" or self.platform == "lepaoledongdijie":
             return True
         if self.platform == "jierizhufuhuakaifugui" or self.platform == "yuannifuqimanman" or self.platform == "haoyunzhufuduo":
@@ -145,7 +176,6 @@ class PiaoQuanPipeline(object):
             return True
         if self.platform == "tiantianjufuqi" and self.mode == "recommend":
             return True
-        out_id = self.item["out_video_id"]
         # 判断加上标题去重
         if self.mode == "recommend" and self.platform == "zhufuhaoyunbaofu":
             title = self.item["video_title"]