File size: 2,500 Bytes
c499f9e cab96b4 c499f9e |
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 |
#
# 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.
#
import random
from abc import ABC
from functools import partial
from Bio import Entrez
import pandas as pd
import xml.etree.ElementTree as ET
from graph.settings import DEBUG
from graph.component.base import ComponentBase, ComponentParamBase
class PubMedParam(ComponentParamBase):
"""
Define the PubMed component parameters.
"""
def __init__(self):
super().__init__()
self.top_n = 5
self.email = "[email protected]"
def check(self):
self.check_positive_integer(self.top_n, "Top N")
class PubMed(ComponentBase, ABC):
component_name = "PubMed"
def _run(self, history, **kwargs):
ans = self.get_input()
ans = " - ".join(ans["content"]) if "content" in ans else ""
if not ans:
return PubMed.be_output("")
try:
Entrez.email = self._param.email
pubmedids = Entrez.read(Entrez.esearch(db='pubmed', retmax=self._param.top_n, term=ans))['IdList']
pubmedcnt = ET.fromstring(
Entrez.efetch(db='pubmed', id=",".join(pubmedids), retmode="xml").read().decode("utf-8"))
pubmed_res = [{"content": 'Title:' + child.find("MedlineCitation").find("Article").find(
"ArticleTitle").text + '\nUrl:<a href=" https://pubmed.ncbi.nlm.nih.gov/' + child.find(
"MedlineCitation").find("PMID").text + '">' + '</a>\n' + 'Abstract:' + child.find(
"MedlineCitation").find("Article").find("Abstract").find("AbstractText").text} for child in
pubmedcnt.findall("PubmedArticle")]
except Exception as e:
return PubMed.be_output("**ERROR**: " + str(e))
if not pubmed_res:
return PubMed.be_output("")
df = pd.DataFrame(pubmed_res)
if DEBUG: print(df, ":::::::::::::::::::::::::::::::::")
return df
|