Add component google scholar (#1790)

### What problem does this PR solve?

#1739 

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
H 2024-08-02 17:34:38 +08:00 committed by GitHub
parent 418700b455
commit 5d55e6a049
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 84 additions and 4 deletions

View File

@ -16,6 +16,7 @@ from .pubmed import PubMed, PubMedParam
from .arxiv import ArXiv, ArXivParam from .arxiv import ArXiv, ArXivParam
from .google import Google, GoogleParam from .google import Google, GoogleParam
from .bing import Bing, BingParam from .bing import Bing, BingParam
from .googlescholar import GoogleScholar, GoogleScholarParam
def component_class(class_name): def component_class(class_name):

View File

@ -0,0 +1,70 @@
#
# Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
from abc import ABC
import pandas as pd
from graph.settings import DEBUG
from graph.component.base import ComponentBase, ComponentParamBase
from scholarly import scholarly
class GoogleScholarParam(ComponentParamBase):
"""
Define the GoogleScholar component parameters.
"""
def __init__(self):
super().__init__()
self.top_n = 6
self.sort_by = 'relevance'
self.year_low = None
self.year_high = None
self.patents = True
def check(self):
self.check_positive_integer(self.top_n, "Top N")
self.check_valid_value(self.sort_by, "GoogleScholar Sort_by", ['date', 'relevance'])
self.check_boolean(self.patents, "Whether or not to include patents, defaults to True")
class GoogleScholar(ComponentBase, ABC):
component_name = "GoogleScholar"
def _run(self, history, **kwargs):
ans = self.get_input()
ans = " - ".join(ans["content"]) if "content" in ans else ""
if not ans:
return GoogleScholar.be_output("")
scholar_client = scholarly.search_pubs(ans, patents=self._param.patents, year_low=self._param.year_low,
year_high=self._param.year_high, sort_by=self._param.sort_by)
scholar_res = []
for i in range(self._param.top_n):
try:
pub = next(scholar_client)
scholar_res.append({"content": 'Title: ' + pub['bib']['title'] + '\n_Url: <a href="' + pub[
'pub_url'] + '"></a> ' + "\n author: " + ",".join(pub['bib']['author']) + '\n Abstract: ' + pub[
'bib'].get('abstract', 'no abstract')})
except StopIteration or Exception as e:
print("**ERROR** " + str(e))
break
if not scholar_res:
return GoogleScholar.be_output("")
df = pd.DataFrame(scholar_res)
if DEBUG: print(df, ":::::::::::::::::::::::::::::::::")
return df

View File

@ -12,6 +12,7 @@ datrie==0.8.2
demjson3==3.0.6 demjson3==3.0.6
discord.py==2.3.2 discord.py==2.3.2
duckduckgo_search==6.1.9 duckduckgo_search==6.1.9
editdistance==0.8.1
elastic_transport==8.12.0 elastic_transport==8.12.0
elasticsearch==8.12.1 elasticsearch==8.12.1
elasticsearch_dsl==8.12.0 elasticsearch_dsl==8.12.0
@ -31,7 +32,9 @@ httpx==0.27.0
huggingface_hub==0.20.3 huggingface_hub==0.20.3
infinity_emb==0.0.51 infinity_emb==0.0.51
itsdangerous==2.1.2 itsdangerous==2.1.2
jina==3.27.2
Markdown==3.6 Markdown==3.6
markdown_to_json==2.1.1
minio==7.2.4 minio==7.2.4
mistralai==0.4.2 mistralai==0.4.2
nltk==3.8.1 nltk==3.8.1
@ -51,6 +54,7 @@ pipreqs==0.5.0
protobuf==5.27.2 protobuf==5.27.2
pyclipper==1.3.0.post5 pyclipper==1.3.0.post5
pycryptodomex==3.20.0 pycryptodomex==3.20.0
pypdf==4.3.0
PyPDF2==3.0.1 PyPDF2==3.0.1
pytest==8.2.2 pytest==8.2.2
python-dotenv==1.0.1 python-dotenv==1.0.1
@ -61,6 +65,7 @@ redis==5.0.3
Requests==2.32.2 Requests==2.32.2
roman_numbers==1.0.2 roman_numbers==1.0.2
ruamel.base==1.0.0 ruamel.base==1.0.0
scholarly==1.7.11
scikit_learn==1.5.0 scikit_learn==1.5.0
selenium==4.22.0 selenium==4.22.0
setuptools==70.0.0 setuptools==70.0.0
@ -80,5 +85,3 @@ word2number==1.1
xgboost==2.1.0 xgboost==2.1.0
xpinyin==0.7.6 xpinyin==0.7.6
zhipuai==2.0.1 zhipuai==2.0.1
pypdf==4.3.0
jina==3.27.2

View File

@ -155,4 +155,7 @@ Bio==1.7.1
arxiv==2.1.3 arxiv==2.1.3
pypdf==4.3.0 pypdf==4.3.0
google_search_results==2.4.2 google_search_results==2.4.2
jina==3.27.2 jina==3.27.2
editdistance==0.8.1
markdown_to_json==2.1.1
scholarly==1.7.11

View File

@ -140,4 +140,7 @@ Bio==1.7.1
arxiv==2.1.3 arxiv==2.1.3
pypdf==4.3.0 pypdf==4.3.0
google_search_results==2.4.2 google_search_results==2.4.2
jina==3.27.2 jina==3.27.2
editdistance==0.8.1
markdown_to_json==2.1.1
scholarly==1.7.11