crawler-twitter/main/copy_usersinfo.py

# -*- coding: utf-8 -*-
# @Author: wangkun
# @Time: 2022/6/20
import time

import requests
import urllib3
from main.common import Common
from main.feishu_lib import Feishu
proxies = {"http": None, "https": None}


class CopyUsersInfo:

    # 备份表数据
    @classmethod
    def copyed_data(cls):
        try:
            data_list = []
            lists = Feishu.get_values_batch("twitter", "WPJILC")
            for i in lists:
                for j in i:
                    # 过滤空的单元格内容
                    if j is None:
                        pass
                    else:
                        data_list.append(j)
            return data_list
        except Exception as e:
            Common.logger().error("获取备份表数据异常:{}", e)

    # 增加工作表，复制工作表、删除工作表。
    @classmethod
    def sheets_batch_update(cls):
        """
        https://open.feishu.cn/document/ukTMukTMukTM/uYTMzUjL2EzM14iNxMTN
        """
        url = "https://open.feishu.cn/open-apis/sheets/v2/spreadsheets/shtcn6BYfYuqegIP13ORB6rI2dh/sheets_batch_update"
        headers = {
            "Authorization": "Bearer " + Feishu.get_token(),
            "Content-Type": "application/json; charset=utf-8"
        }
        body = {
            "requests": [
                {
                    "copySheet": {
                        "source": {
                            "sheetId": "db114c"
                        },
                        "destination": {
                            "title": ""
                        }
                    }
                }
            ]
        }
        try:
            urllib3.disable_warnings()
            r = requests.post(url=url, headers=headers, json=body, proxies=proxies, verify=False)
            print(r.json())
            # Common.logger().info("增加工作表，复制工作表、删除工作表:{}", r.json()["msg"])
        except Exception as e:
            Common.logger().error("增加工作表，复制工作表、删除工作表异常:{}", e)

    # 复制用户信息
    @classmethod
    def copy_usersinfo(cls):
        try:
            user_list = Feishu.get_values_batch("twitter", "db114c")
            for i in range(1, len(user_list[1:])):
                uid = user_list[i][0]
                key_word = user_list[i][1]
                name = user_list[i][2]
                screen_name = user_list[i][3]
                person_url = user_list[i][4]
                description = user_list[i][5]
                location = user_list[i][6]
                friends_count = user_list[i][7]
                followers_count = user_list[i][8]
                favourites_count = user_list[i][9]
                listed_count = user_list[i][10]
                statuses_count = user_list[i][11]
                media_count = user_list[i][12]
                display_url = user_list[i][13]
                created_at = user_list[i][14]
                profile_image_url = user_list[i][15]
                profile_banner_url = user_list[i][16]
                ext_has_nft_avatar = user_list[i][17]
                verified = user_list[i][18]
                created_time = user_list[i][19]
                update_time = user_list[i][20]
                # print(f"\n第{i}个用户信息")
                # print(f"uid:{uid}")
                # print(f"key_word:{key_word}")
                # print(f"name:{name}")
                # print(f"screen_name:{screen_name}")
                # print(f"person_url:{person_url}")
                # print(f"description:{description}")
                # print(f"location:{location}")
                # print(f"friends_count:{friends_count}")
                # print(f"followers_count:{followers_count}")
                # print(f"favourites_count:{favourites_count}")
                # print(f"listed_count:{listed_count}")
                # print(f"statuses_count:{statuses_count}")
                # print(f"media_count:{media_count}")
                # print(f"display_url:{display_url}")
                # print(f"created_at:{created_at}")
                # print(f"profile_image_url:{profile_image_url}")
                # print(f"profile_banner_url:{profile_banner_url}")
                # print(f"ext_has_nft_avatar:{ext_has_nft_avatar}, type:{type(ext_has_nft_avatar)}")
                # print(f"verified:{verified}, type:{type(verified)}")
                # print(f"created_time:{created_time}")
                # print(f"update_time:{update_time}")
                # print("\n")

                if uid in cls.copyed_data():
                    Common.logger().info("用户信息已存在")
                    return
                else:
                    Common.logger().info("开始拷贝第{}个用户信息", i)
                    time.sleep(1)
                    Feishu.insert_columns("twitter", "WPJILC", "ROWS", 1, 2)
                    values = [[uid,
                               key_word,
                               name,
                               screen_name,
                               person_url,
                               description,
                               location,
                               friends_count,
                               followers_count,
                               favourites_count,
                               listed_count,
                               statuses_count,
                               media_count,
                               display_url,
                               created_at,
                               profile_image_url,
                               profile_banner_url,
                               str(ext_has_nft_avatar),
                               str(verified),
                               created_time,
                               update_time]]
                    time.sleep(1)
                    Feishu.update_values("twitter", "WPJILC", "A2:U2", values)

        except Exception as e:
            Common.logger().error("复制用户信息异常:{}", e)


if __name__ == "__main__":
    copy = CopyUsersInfo()
    copy.sheets_batch_update()
    # copy.copy_usersinfo()