Spaces:
Runtime error
Runtime error
File size: 6,023 Bytes
f3fb4c2 94cf70c f3fb4c2 94cf70c f3fb4c2 597458d 4ade2ba f3fb4c2 597458d f3fb4c2 94cf70c f3fb4c2 94cf70c f3fb4c2 94cf70c f3fb4c2 94cf70c f3fb4c2 94cf70c f3fb4c2 94cf70c f3fb4c2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 |
import requests
import pprint
import json
import os
import gradio as gr
import requests
from bs4 import BeautifulSoup
def get_dblp_bibref(title):
print(f'DBLP query: {title}')
try:
# Replace spaces in the title with '+'
title = title.replace(' ', '+')
# Send a GET request to the DBLP search page with the paper title
response = requests.get(f'https://dblp.org/search/publ/api?q={title}&format=xml')
soup = BeautifulSoup(response.content, 'lxml')
# Get the URL of the first paper in the search results
url = soup.select_one('url').text + '.bib'
response = requests.get(url)
paper_link = soup.select_one('url').text + '.html'
return response.text, paper_link
except Exception as e:
return f'Error during get bibref from DBLP: {e}', None
# set pprint width
pp = pprint.PrettyPrinter(width=128)
API_KEY = 'eRLnjZeWSs4gHjSemy5af1X7IbugACFg1tSX6F3R'
FIELDS = "paperId,title,url,year,authors,venue,abstract,citationCount,openAccessPdf,fieldsOfStudy,publicationDate,citations,references"
# def get_name_mapping(venues_data='/nfs/delong/data/s2orc/s2ag_full/publication-venues'):
# name_mapping = {} # from full name to abbreviated name
# for file in os.listdir(venues_data):
# with open(os.path.join(venues_data, file), 'r') as f:
# venues = [json.loads(line) for line in f.readlines()]
# print(f"Total number of venues in {file}: {len(venues)}")
# for venue in venues:
# if len(venue['alternate_names'])>0:
# # name_mapping[venue['name']] = venue['alternate_names'][0]
# # instead of using the first alternate name, use the shortest one
# name_mapping[venue['name']] = min(venue['alternate_names'], key=len)
# name_mapping['Neural Information Processing Systems'] = 'NeurIPS'
# print(f'loaded {len(name_mapping)} venues from {venues_data}')
# return name_mapping
# name_mapping = get_name_mapping()
# json.dump(name_mapping, open('name_mapping.json', 'w'), indent=4)
name_mapping = json.load(open('name_mapping.json', 'r'))
print(f'loaded {len(name_mapping)} venues from name_mapping.json')
def search_paper_title_semanticscholar(title):
url = "https://api.semanticscholar.org/graph/v1/paper/search"
headers = {"Accept": "application/json", "x-api-key": API_KEY}
params = {"query": title, "limit": 1}
response = requests.get(url, headers=headers, params=params)
if response.status_code == 200:
data = response.json()
if data['total']!=0:
paper_id = data['data'][0]['paperId']
url = f"https://api.semanticscholar.org/graph/v1/paper/{paper_id}"
params = {"fields": FIELDS}
response = requests.get(url, headers=headers, params=params)
if response.status_code == 200:
data = response.json()
return data
else:
print(f"Error: {response.status_code}")
return None
else:
print("No paper found with the given title.")
return None
else:
print(f"Error: {response.status_code}")
return None
def get_abbreviated_venue(name):
if name in name_mapping:
return name_mapping[name]
else:
return name
def get_md_citation(paper_info):
# citation_str = paper_info['authors'][0]['name'] + " *et al.* "
# citation_str = ', '.join([author['name'] for author in paper_info['authors']]) + '. '
citation_str = ''
for author in paper_info['authors'][:5]:
citation_str += f"{author['name']}, "
if len(paper_info['authors'])>5:
citation_str += '*et al.* '
else:
citation_str = citation_str[:-2] + '. '
citation_str += f"[{paper_info['title']}]({paper_info['url']}). "
citation_str += f"*{get_abbreviated_venue(paper_info['venue'])}*"
# citation_str += f" ({paper_info['year']})."
citation_str += f" ({paper_info['publicationDate'][:-3].replace('-', '.')})."
return citation_str
def summarize_paper_info(paper_info):
info_str = ""
# info_str += f"**Venue**: {paper_info['venue']}\n\n"
author_str = ''
for author in paper_info['authors']:
author_str += f"[{author['name']}](https://www.semanticscholar.org/author/{author['authorId']}), "
author_str = author_str[:-2]
info_str += f"**Authors**:\n\n{author_str}\n\n"
info_str += f"\n\n> **Abstract**: {paper_info['abstract']}\n\n"
info_str += f"**Citation Count**: {paper_info['citationCount']}\n\n"
return info_str
def get_output(title):
print(f"Title query: {title}")
paper_info = search_paper_title_semanticscholar(title)
if paper_info is not None:
citation_str = get_md_citation(paper_info)
else:
citation_str = "No paper found with that title."
bibtex, dblp_link = get_dblp_bibref(paper_info['title'])
citation_str = f"""
```text
{paper_info['title']}
```
{citation_str}
---
**Markdown source code**
```markdown
{citation_str}
```
**BibTex**
```bibtex
{bibtex}
```
{summarize_paper_info(paper_info)}
---
🔗 [[Open in Semantic Scholar]](https://www.semanticscholar.org/paper/{paper_info['paperId']}) | [[DBLP Page]]({dblp_link})
"""
print(citation_str)
return citation_str
def main():
iface = gr.Interface(
fn=get_output,
inputs=gr.components.Textbox(
lines=1,
label="Please input the title of the paper to get its citation.",
placeholder="Your title here",
autofocus=True,
),
outputs="markdown",
allow_flagging='never',
title="Citation Tool",
description="### Search paper title from [Semantic Scholar](https://www.semanticscholar.org/) and [DBLP](http://dblp.org/), and get structured citation.",
)
iface.launch()
if __name__=="__main__":
main()
|