crawler_jeff/jeff_crawler_ver2.py

from PyPtt import PTT
ptt_bot = PTT.API()
ptt_bot.login('jeffchen111', 'ntuee111')

def cc(RESRES):
    def crawl_handler(post_info):
    
        if post_info.delete_status != PTT.data_type.post_delete_status.NOT_DELETED:
            if post_info.delete_status == PTT.data_type.post_delete_status.MODERATOR:
                # print(f"[板主刪除][{post_info.author}]")
                pass
            elif post_info.delete_status == PTT.data_type.post_delete_status.AUTHOR:
                # print(f"[作者刪除][{post_info.author}]")
                pass
            elif post_info.delete_status == PTT.data_type.post_delete_status.UNKNOWN:
                # print(f"[不明刪除]")
                pass
            return
    
        # print(f"[{post_info.aid}][{post_info.title}]")
        # return post_info
        PP = dict(
            aid=post_info.aid,
            index=post_info.index,
            web_url=post_info.web_url,
            title=post_info.title,
        )
        RESRES.append(PP)
    return crawl_handler


boardname = "Gossiping"
newest = ptt_bot.get_newest_index(PTT.data_type.index_type.BBS, boardname)
RESRES = []
error_post_list, del_post_list = ptt_bot.crawl_board(
    PTT.data_type.crawl_type.BBS,
    # crawl_handler,
    cc(RESRES),
    boardname,
    start_index=newest - 1000 * 2,
    end_index=newest,  #  - 100 * 2,
    # Optional
    query=True,
)