VideoToArticles/test/test4.py

import json
import pymysql
import pandas as pd

connection = pymysql.connect(
    host='rm-bp1159bu17li9hi94.mysql.rds.aliyuncs.com',
    port=3306,
    user='crawler',
    password='crawler123456@',
    db='piaoquan-crawler',
    charset='utf8mb4'
)

columns = pd.read_csv("piaoquan_crawler_long_articles_video.csv").columns.tolist()


def extract_desired_key(json_str):
    """
    ppp
    :param json_str:
    :return:
    """
    try:
        data = json.loads(json_str)
        return data['productionPath'].split("rootSourceId%3D")[1]
    except json.JSONDecodeError:
        return None


sql = f"""
select * from long_articles_video where account_name in ("小阳看天下", "小惠爱厨房") and update_time > "2024-07-04";
"""
cursor = connection.cursor()
cursor.execute(sql)
result = cursor.fetchall()
connection.close()
L = []
for line in result:
    temp = list(line)
    temp[-5] = json.loads(temp[-5])['productionPath'].split("rootSourceId%3D")[1] if temp[-5] else None
    temp[-6] = json.loads(temp[-6])['productionPath'].split("rootSourceId%3D")[1] if temp[-6] else None
    temp[-7] = json.loads(temp[-7])['productionPath'].split("rootSourceId%3D")[1] if temp[-7] else None
    print(temp)
    L.append(temp)
df = pd.DataFrame(L, columns=columns)
df.to_excel("root_source_id.xlsx", index=False)