import requests
import pandas as pd
from tqdm import tqdm

def fetch_issues(base_url, search_term, max_pages=None):
    """
    分页获取指定搜索条件的issue数据
    :param base_url: 基础URL（不带search和page参数）
    :param search_term: 搜索关键词
    :param max_pages: 最大获取页数
    :return: 包含title和link的DataFrame
    """
    all_issues = []
    page = 1
    total_pages = None

    # 构造带搜索参数的URL
    search_url = f"{base_url}search={search_term}"

    with tqdm(desc=f"Fetching '{search_term}' issues") as pbar:
        while True:
            url = f"{search_url}&page={page}"
            try:
                response = requests.get(url, timeout=10)
                response.raise_for_status()
                data = response.json()

                if page == 1:
                    total_items = data.get("total", 0)
                    per_page = data.get("per_page", 10)
                    total_pages = (total_items + per_page - 1) // per_page
                    pbar.total = total_pages

                # 只提取title和link字段
                for issue in data.get("data", []):
                    all_issues.append({
                        "title": issue.get("title", ""),
                        "link": issue.get("link", ""),
                    })

                pbar.update(1)

                if page >= total_pages or not data.get("data"):
                    break
                page += 1

            except Exception as e:
                print(f"\nError fetching {search_term} page {page}: {e}")
                break

    return pd.DataFrame(all_issues)

def batch_fetch_issues(base_url, search_terms, max_pages=None):
    """
    批量获取多个搜索条件的数据
    :param base_url: 基础URL
    :param search_terms: 搜索关键词列表
    :param max_pages: 每类最大页数
    :return: 合并后的DataFrame
    """
    all_dfs = []

    for term in search_terms:
        df = fetch_issues(base_url, term, max_pages)
        if not df.empty:
            df["search_term"] = term  # 标记搜索关键词
            all_dfs.append(df)

    if all_dfs:
        return pd.concat(all_dfs, ignore_index=True)
    return pd.DataFrame()

def save_to_excel(df, filename):
    """
    保存数据到Excel，添加序列号
    :param df: 包含数据的DataFrame
    :param filename: 输出文件名
    """
    if df.empty:
        print("没有数据可保存")
        return

    # 添加序列号列
    df.insert(0, "序号", range(1, len(df) + 1))

    # 只保留需要的列
    final_df = df[["序号", "search_term", "title", "link"]]

    try:
        final_df.to_excel(filename, index=False)
        print(f"成功保存 {len(final_df)} 条数据到 {filename}")
    except Exception as e:
        print(f"保存文件时出错: {e}")

if __name__ == "__main__":
    # 基础URL（不包含search和page参数）
    base_url = "https://quickissue.openeuler.org/api-issues/issues/?per_page=10&issue_type=&priority=&direction=desc&create=&author=&sort=created_at&assignee=&label=&branch=&repo=&issue_state=&milestone=&exclusion=&"

    # 要搜索的关键词列表
    search_terms = ["技术支持", "安装问题", "兼容性"]

    # 获取数据（限制每类最多3页）
    combined_df = batch_fetch_issues(base_url, search_terms, max_pages=3)

    if not combined_df.empty:
        # 保存到Excel
        save_to_excel(combined_df, "openEuler_issues_optimized.xlsx")

        # 打印统计信息
        print("\n各搜索关键词获取数量:")
        print(combined_df["search_term"].value_counts())
    else:
        print("未获取到任何数据")