spider_work/breakninja_spider/无翻页系列.py

# -*- coding: utf-8 -*-
# Author : Charley
# Python : 3.10.8
# Date   : 2025/11/26 15:25
import add_settings
import pandas as pd

series_url_list = add_settings.series_url_list

# 存储不含 page_no= 的记录
filtered_series = []

# 遍历 series_url_list
for category in series_url_list:
    category_name = category["category_name"]
    for year_data in category["years"]:
        year = year_data["year"]
        for series in year_data["series"]:
            series_name = series["series_name"]
            series_url = series["series_url"]

            # 判断是否含有 page_no=
            if "page_no=" not in series_url:
                filtered_series.append({
                    "category_name": category_name,
                    "year": year,
                    "series_name": series_name,
                    "series_url": series_url
                })

# 导出到 Excel 文件
df = pd.DataFrame(filtered_series)
df.to_excel("series_without.xlsx", index=False)