keyan/main.py

import gradio as gr
import os

from te_u.arxiv import get_news_from_arxiv
#
# os.environ['http_proxy'] = '127.0.0.1:7890'
# os.environ['https_proxy'] = '127.0.0.1:7890'

from utils import get_news, get_clouds
from gradio_pdf import PDF

current_pdf_file = None
news = []
choose_news = []

with gr.Blocks() as demo:
    with gr.Row():
        with gr.Column(scale=20):
            gr.HTML("""<h1 align="center" id="space-title" style="font-size:35px;">科研情报</h1>""")
        with gr.Column(scale=1, min_width=100):
            gr.HTML(
                """<h5 align="center">  </h5> """
            )
            gr.HTML(
                """<h5 align="center"> Created by 朱瑞</h5> """
            )

    with gr.Tabs(elem_classes="tab-buttons") as tabs:
        with gr.TabItem("科研文献分析"):
            with gr.Row():
                with gr.Accordion("文献采集区", open=True, ) as area_news_get_fn:
                    keywords = gr.Dropdown(choices=["对抗攻击", "knowledge graph", "认知智能与先进计算", "电磁空间感知与利用", "信息安全与攻防博弈"],
                                           value="对抗攻击", label="关键词", show_label=True)
                    source = gr.Dropdown(choices=["知网", "arxiv"], value="知网", label="数据源", show_label=True)
                    num = gr.Slider(1, 100, value=10, label="采集条数", step=1)
                    news_get = gr.Button("获取论文", variant='primary')

            with gr.Row():
                with gr.Accordion("文献标记分析区", open=True, elem_id="news-panel") as news_get_fn:
                    chosen_news = gr.CheckboxGroup(choices=[item['name'] for item in news], label="需要进行操作的文献")

            with gr.Row():
                news_mark = gr.Button("标记文献")
                news_all_mark = gr.Button("全部标记", variant='primary')


            def recover_news_by_choose(news_titles):
                select_news = []
                global news

                for news_title in news_titles:
                    for i in news:
                        if news_title == i['name']:
                            new_i = i
                            select_news.append(new_i)
                            break

                return select_news


            def mark_new(titles):
                global choose_news
                mark_news = recover_news_by_choose(titles)
                choose_news = mark_news


            def get_news_temp(num, keywords, source):
                """ 获取临时的文献 """
                global news
                results = []
                if source == "知网":
                    results = get_news(num, keywords)
                elif source == "arxiv":
                    results = get_news_from_arxiv(num, keywords)

                news.extend(results)
                return gr.CheckboxGroup(choices=[item['name'] for item in news], label="需要进行操作的文献")


            def mark_all_new():
                global news
                global choose_news
                choose_news = news
                return gr.CheckboxGroup(choices=[item['name'] for item in news], value=[item['name'] for item in news], label="需要进行操作的文献")


            news_get.click(get_news_temp, inputs=[num, keywords, source], outputs=[chosen_news])
            news_mark.click(mark_new, inputs=[chosen_news])
            news_all_mark.click(mark_all_new, outputs=[chosen_news])

        with gr.TabItem("科研文献获取"):
            with gr.Row():
                with gr.Accordion("功能区", open=True, ) as area_news_analyse_fn:
                    with gr.Row():
                        ci_yun_by_title = gr.Button("题目词云", variant='primary')
                        ci_yun_by_abstract = gr.Button("摘要词云", variant='primary')
            with gr.Row():
                with gr.Accordion("结果展示区", open=True, ) as area_news_result_fn:
                    result_place = gr.Image()


            def g_ci_yun_by_title():
                global choose_news
                word_list = [c["name"] for c in choose_news]
                pic = get_clouds(word_list)
                return pic


            def g_ci_yun_by_abstract():
                global choose_news
                word_list = [c["abstract"] for c in choose_news]
                pic = get_clouds(word_list)
                return pic


            ci_yun_by_title.click(g_ci_yun_by_title, outputs=[result_place])
            ci_yun_by_abstract.click(g_ci_yun_by_abstract, outputs=[result_place])

        with gr.TabItem("会议论文查看"):
            with gr.Row():
                with gr.Column(scale=1):
                    with gr.Row():
                        # gr.Label("会议名称")
                        conf_name = gr.Dropdown(choices=["ECCV2022", "ECCV2020", "CVPR2024"], value="ECCV2022", label="会议名称", show_label=True)
                        conf_button = gr.Button("查看会议论文", variant='primary')
                    dataframe = gr.Dataframe(headers=["论文名称"], col_count=(1, "fixed"), type='array', height=800)
                    with gr.Row():
                        look_input = gr.Textbox(placeholder="关键词检索", label="关键词过滤")
                        filter_button = gr.Button("过滤")
                    # up_button = gr.Button("加载")

                with gr.Column(scale=2):
                    pdf = PDF(label="Upload a PDF", interactive=True, height=1000)


                # name = gr.Textbox(show_label=False)
                # pdf.upload(lambda f: f, pdf, name)

                def up_load():
                    global current_pdf_file
                    n = r"D:\py\keyan_qingbao\te_u\paper_down_load\ECCV_2022\main_paper\3d-siamese-transformer-network-for-single-object-tracking-on-point-clouds_ECCV_2022.pdf"
                    current_pdf_file = n
                    return n


                def load_conf_list(conf_name):
                    if conf_name == "ECCV2022":
                        root_dir = r"D:\py\keyan_qingbao\te_u\paper_down_load\ECCV_2022\main_paper"
                        return [[i] for i in os.listdir(root_dir)]


                def look_dataframe(evt: gr.SelectData):
                    global current_pdf_file
                    if evt.value:
                        root_dir = r"D:\py\keyan_qingbao\te_u\paper_down_load\ECCV_2022\main_paper"
                        n = os.path.join(root_dir, evt.value)
                        if os.path.exists(n):
                            current_pdf_file = n
                    return current_pdf_file


                def filter_by_word(words, paper_list):
                    word_list = words.strip().split()
                    paper_list_filter = [p[0] for p in paper_list]
                    for word in word_list:
                        paper_list_filter = [p for p in paper_list_filter if word in p]
                    return [[p] for p in paper_list_filter]


                filter_button.click(filter_by_word, inputs=[look_input, dataframe], outputs=[dataframe])
                dataframe.select(look_dataframe, inputs=None, outputs=[pdf])
                conf_button.click(load_conf_list, inputs=[conf_name], outputs=[dataframe])
                # up_button.click(up_load, inputs=None, outputs=[pdf])s

if __name__ == '__main__':
    demo.queue().launch(inbrowser=True, server_name='127.0.0.1', server_port=23223)