Upload 2 files

app.py

@@ -0,0 +1,88 @@
+import os
+import requests
+import xml.etree.ElementTree as ET
+import urllib.request
+import re
+from datetime import datetime
+import pandas as pd
+from fpdf import FPDF
+import gradio as gr
+
+def get_arxiv_data(search_query, number):
+    url = f'http://export.arxiv.org/api/query?search_query={search_query}&start=0&max_results={number}'
+    response = requests.get(url)
+    xml_data = response.text
+    root = ET.fromstring(xml_data)
+    entries = root.findall('{http://www.w3.org/2005/Atom}entry')
+    results = []
+
+    # Create folder for current date and time
+    current_time = datetime.now().strftime('%Y_%m_%d__%H_%M')
+    folder_path = os.path.join('data', current_time)
+    os.makedirs(folder_path, exist_ok=True)
+
+    for entry in entries:
+        title = entry.find('{http://www.w3.org/2005/Atom}title').text
+        link = entry.find('{http://www.w3.org/2005/Atom}link').attrib['href']
+        published = entry.find('{http://www.w3.org/2005/Atom}published').text
+        author = entry.find('{http://www.w3.org/2005/Atom}author/{http://www.w3.org/2005/Atom}name').text
+
+        # Skip non-arXiv links
+        if not link.startswith('http://arxiv.org/'):
+            continue
+
+        result_string = f'Title: {title}\nLink: {link}\nPublished: {published}\nAuthor: {author}\n'
+        results.append(result_string)
+
+        # Download PDF file
+        pdf_link = link.replace('abs', 'pdf') + '.pdf'
+        filename = re.sub(r'[^a-zA-Z0-9_]', '_', title) + '.pdf'
+        filepath = os.path.join(folder_path, filename)
+
+        try:
+            urllib.request.urlretrieve(pdf_link, filepath)
+        except Exception as e:
+            continue
+
+    # Save search query and results to PDF
+    pdf = FPDF()
+    pdf.add_page()
+    pdf.set_font('Arial', 'B', 16)
+    pdf.cell(0, 10, f"Search Query: {search_query}", ln=True)
+    pdf.set_font('Arial', '', 12)
+    for i, result in enumerate(results):
+        pdf.multi_cell(0, 10, f"Result {i + 1}:\n{result}\n")
+        pdf.ln(5)  # Add newline after each result
+    pdf.output(os.path.join(folder_path, '1_Search_query_AND_results.pdf'))
+
+    # Save search query, results, and current time to Excel file
+    current_time = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+    df = pd.DataFrame({'Search Query': [search_query], 'Results': ['\n'.join(results)], 'Timestamp': [current_time]})
+    folder_path = 'data'
+    os.makedirs(folder_path, exist_ok=True)
+    excel_filepath = os.path.join(folder_path, 'information.xlsx')
+    if os.path.exists(excel_filepath):
+        existing_df = pd.read_excel(excel_filepath)
+        df = pd.concat([existing_df, df], ignore_index=True)
+    df.to_excel(excel_filepath, index=False)
+
+    return results
+
+def search_arxiv(search_query, max_results):
+    start_time = datetime.now()
+    results = get_arxiv_data(search_query, max_results)
+    elapsed_time = datetime.now() - start_time
+    elapsed_time_str = f"Elapsed Time: {elapsed_time.total_seconds()} seconds"
+
+    return '\n'.join(results), elapsed_time_str
+
+search_query_input = gr.inputs.Textbox(label="Search Query")
+max_results_input = gr.inputs.Textbox(label="Max Results")
+
+output_text = gr.outputs.Textbox(label="Results")
+output_time = gr.outputs.Textbox(label="Elapsed Time")
+
+title = "ArXiv Search"
+description = "Crawling Papers on Arxiv"
+
+gr.Interface(fn=search_arxiv, inputs=[search_query_input, max_results_input], outputs=[output_text, output_time], title=title, description=description).launch()

requirements.txt

@@ -0,0 +1,242 @@
+aiofiles==23.1.0
+aiohttp==3.8.4
+aiosignal==1.3.1
+alabaster==0.7.13
+altair==4.2.2
+altgraph==0.17.3
+anyio==3.6.2
+argilla==1.7.0
+arrow==1.2.3
+arxiv==1.4.7
+asttokens==2.2.1
+async-generator==1.10
+async-timeout==4.0.2
+attrs==22.2.0
+Babel==2.12.1
+backcall==0.2.0
+backoff==2.2.1
+backports.functools-lru-cache==1.6.4
+beautifulsoup4==4.12.2
+bibtexparser==1.4.0
+boto3==1.26.121
+botocore==1.29.121
+bottle==0.12.25
+bottle-websocket==0.2.9
+cachetools==5.3.0
+certifi==2022.12.7
+cffi==1.15.1
+chardet==5.1.0
+charset-normalizer==3.1.0
+ci-info==0.3.0
+click==8.1.3
+cloudpickle==2.2.1
+cmake==3.26.3
+colorama==0.4.6
+comm==0.1.3
+configobj==5.0.8
+configparser==5.3.0
+contourpy==1.0.7
+cryptography==40.0.2
+cycler==0.11.0
+dataclasses-json==0.5.7
+debugpy==1.6.7
+decorator==5.1.1
+Deprecated==1.2.13
+dnspython==2.3.0
+docopt==0.6.2
+docutils==0.18.1
+Eel==0.16.0
+entrypoints==0.4
+et-xmlfile==1.1.0
+etelemetry==0.3.0
+exceptiongroup==1.1.1
+executing==1.2.0
+fake-useragent==1.1.3
+fastapi==0.95.1
+feedparser==6.0.10
+ffmpy==0.3.0
+filelock==3.12.0
+fitz==0.0.1.dev2
+fonttools==4.39.2
+fpdf==1.7.2
+free-proxy==1.1.1
+frozenlist==1.3.3
+fsspec==2023.4.0
+future==0.18.3
+gevent==22.10.2
+gevent-websocket==0.10.1
+googleapis-common-protos==1.59.0
+gpt-index==0.6.2
+gradio==3.28.1
+gradio_client==0.1.3
+greenlet==2.0.2
+grpc-gateway-protoc-gen-openapiv2==0.1.0
+grpcio==1.54.2
+gym==0.26.2
+gym-notices==0.0.8
+h11==0.14.0
+httpcore==0.16.3
+httplib2==0.22.0
+httpx==0.23.3
+huggingface-hub==0.13.4
+idna==3.4
+imagesize==1.4.1
+importlib-metadata==6.3.0
+ipykernel==6.22.0
+ipython==8.12.0
+isodate==0.6.1
+jedi==0.18.2
+Jinja2==3.1.2
+jmespath==1.0.1
+joblib==1.2.0
+jsonschema==4.17.3
+jupyter_client==8.1.0
+jupyter_core==5.3.0
+kiwisolver==1.4.4
+langchain==0.0.183
+linkify-it-py==2.0.0
+llama-index==0.6.4
+loguru==0.7.0
+lxml==4.9.2
+lz4==4.3.2
+Markdown==3.4.3
+markdown-it-py==2.2.0
+MarkupSafe==2.1.2
+marshmallow==3.19.0
+marshmallow-enum==1.5.1
+matplotlib==3.7.1
+matplotlib-inline==0.1.6
+mdit-py-plugins==0.3.3
+mdurl==0.1.2
+mpmath==1.3.0
+msg-parser==1.2.0
+multidict==6.0.4
+mypy-extensions==1.0.0
+nest-asyncio==1.5.6
+networkx==3.1
+nibabel==5.1.0
+nipype==1.8.6
+nltk==3.8.1
+numexpr==2.8.4
+numpy==1.23.5
+olefile==0.46
+openai==0.27.2
+openapi-schema-pydantic==1.2.4
+openpyxl==3.1.2
+openreview-py==1.22.1
+orjson==3.8.10
+outcome==1.2.0
+packaging==23.0
+pandas==1.5.3
+parso==0.8.3
+pdfminer.six==20221105
+pefile==2023.2.7
+pickleshare==0.7.5
+Pillow==9.4.0
+pip==23.1.2
+pipreqs==0.4.13
+platformdirs==3.2.0
+prompt-toolkit==3.0.38
+protobuf==4.23.2
+prov==2.0.0
+psutil==5.9.4
+pure-eval==0.2.2
+pyasn1==0.5.0
+pyasn1-modules==0.3.0
+pycparser==2.21
+pycryptodome==3.17
+pydantic==1.10.7
+pydot==1.4.2
+pydub==0.25.1
+Pygments==2.15.1
+pyinstaller==5.10.1
+pyinstaller-hooks-contrib==2023.2
+PyJWT==2.6.0
+PyMuPDF==1.22.3
+pypandoc==1.11
+pyparsing==3.0.9
+pypdf==3.9.0
+PyPDF2==3.0.1
+pypdfium2==4.12.0
+pyrsistent==0.19.3
+PySocks==1.7.1
+python-dateutil==2.8.2
+python-docx==0.8.11
+python-dotenv==1.0.0
+python-magic==0.4.27
+python-multipart==0.0.6
+python-pptx==0.6.21
+pytz==2023.3
+pywin32==304
+pywin32-ctypes==0.2.0
+pyxnat==1.5
+PyYAML==6.0
+pyzmq==25.0.2
+rdflib==6.3.2
+regex==2023.5.5
+requests==2.28.2
+rfc3986==1.5.0
+rich==13.0.1
+rsa==4.9
+s3transfer==0.6.0
+scholarly==1.7.11
+scipy==1.10.1
+selenium==4.9.1
+semantic-version==2.10.0
+setuptools==65.5.1
+sgmllib3k==1.0.0
+shutup==0.2.0
+simplejson==3.19.1
+six==1.16.0
+sniffio==1.3.0
+sortedcontainers==2.4.0
+soupsieve==2.4.1
+Sphinx==6.2.1
+sphinx-rtd-theme==1.2.0
+sphinxcontrib-applehelp==1.0.4
+sphinxcontrib-devhelp==1.0.2
+sphinxcontrib-htmlhelp==2.0.1
+sphinxcontrib-jquery==4.1
+sphinxcontrib-jsmath==1.0.1
+sphinxcontrib-qthelp==1.0.3
+sphinxcontrib-serializinghtml==1.1.5
+SQLAlchemy==2.0.12
+stack-data==0.6.2
+starlette==0.26.1
+sympy==1.12
+tenacity==8.2.2
+tiktoken==0.4.0
+tld==0.13
+toolz==0.12.0
+torch==2.0.1+cu117
+torchvision==0.15.2+cu117
+tornado==6.2
+tqdm==4.65.0
+traitlets==5.9.0
+traits==6.3.2
+trio==0.22.0
+trio-websocket==0.10.2
+typer==0.9.0
+typing_extensions==4.5.0
+typing-inspect==0.8.0
+tzdata==2023.3
+uc-micro-py==1.0.1
+unstructured==0.6.10
+urllib3==1.26.15
+uvicorn==0.21.1
+wcwidth==0.2.6
+websockets==11.0.2
+wget==3.2
+wheel==0.40.0
+whichcraft==0.6.1
+wikipedia==1.4.0
+win32-setctime==1.1.0
+wrapt==1.14.1
+wsproto==1.2.0
+xlrd==2.0.1
+XlsxWriter==3.1.1
+yarg==0.1.9
+yarl==1.8.2
+zipp==3.15.0
+zope.event==4.6
+zope.interface==6.0