Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -9,6 +9,7 @@ from bs4 import BeautifulSoup
|
|
9 |
import arxiv
|
10 |
from PyPDF2 import PdfReader
|
11 |
from xml.etree import ElementTree
|
|
|
12 |
# Below is an example of a tool that does nothing. Amaze us with your creativity !
|
13 |
|
14 |
|
@@ -75,18 +76,16 @@ def get_paper_content(link:str)->str:
|
|
75 |
pdf_url = paper.entry_id.replace("abs", "pdf") + ".pdf"
|
76 |
response = requests.get(pdf_url)
|
77 |
response.raise_for_status()
|
78 |
-
|
79 |
-
with open(pdf_path, "wb") as file:
|
80 |
-
file.write(response.content)
|
81 |
|
82 |
-
|
83 |
content = ""
|
84 |
-
reader = PdfReader(
|
85 |
-
pages = reader.pages[:4]
|
86 |
for page in pages:
|
87 |
-
content += page.extract_text()
|
88 |
-
|
89 |
-
return content
|
90 |
|
91 |
except Exception as e:
|
92 |
return f"Error reading paper: {str(e)}"
|
|
|
9 |
import arxiv
|
10 |
from PyPDF2 import PdfReader
|
11 |
from xml.etree import ElementTree
|
12 |
+
import io
|
13 |
# Below is an example of a tool that does nothing. Amaze us with your creativity !
|
14 |
|
15 |
|
|
|
76 |
pdf_url = paper.entry_id.replace("abs", "pdf") + ".pdf"
|
77 |
response = requests.get(pdf_url)
|
78 |
response.raise_for_status()
|
79 |
+
pdf_buffer = io.BytesIO(response.content)
|
|
|
|
|
80 |
|
81 |
+
# Extract text from the first four pages
|
82 |
content = ""
|
83 |
+
reader = PdfReader(pdf_buffer)
|
84 |
+
pages = reader.pages[:4]
|
85 |
for page in pages:
|
86 |
+
content += page.extract_text() or ""
|
87 |
+
|
88 |
+
return content.strip()
|
89 |
|
90 |
except Exception as e:
|
91 |
return f"Error reading paper: {str(e)}"
|