Spaces:
Sleeping
Sleeping
Create pubmedScraper.py
Browse files- pubmedScraper.py +55 -0
pubmedScraper.py
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from Bio import Entrez
|
| 2 |
+
|
| 3 |
+
def remove_blankets(ls):
|
| 4 |
+
for i in range(len(ls)):
|
| 5 |
+
if i<len(ls):
|
| 6 |
+
if ls[i]=="" or ls[i]==" ":
|
| 7 |
+
ls.remove(ls[i])
|
| 8 |
+
else:
|
| 9 |
+
pass
|
| 10 |
+
else:
|
| 11 |
+
pass
|
| 12 |
+
|
| 13 |
+
def search_pubmed(query, max_results, address):
|
| 14 |
+
Entrez.email = address # Replace with your email
|
| 15 |
+
handle = Entrez.esearch(db="pubmed", term=query, retmax=max_results)
|
| 16 |
+
record = Entrez.read(handle)
|
| 17 |
+
handle.close()
|
| 18 |
+
return record["IdList"]
|
| 19 |
+
|
| 20 |
+
def fetch_pubmed_details(pubmed_ids, address):
|
| 21 |
+
Entrez.email = address # Replace with your email
|
| 22 |
+
handle = Entrez.efetch(db="pubmed", id=pubmed_ids, rettype="medline", retmode="text")
|
| 23 |
+
records = handle.read()
|
| 24 |
+
handle.close()
|
| 25 |
+
return records
|
| 26 |
+
|
| 27 |
+
def respond_to_query(query,address,max_results=10):
|
| 28 |
+
|
| 29 |
+
# Perform the PubMed search
|
| 30 |
+
pubmed_ids = search_pubmed(query, max_results,address)
|
| 31 |
+
|
| 32 |
+
# Fetch details for the retrieved PubMed IDs
|
| 33 |
+
pubmed_details = fetch_pubmed_details(pubmed_ids,address)
|
| 34 |
+
|
| 35 |
+
pubmed_split=pubmed_details.split("\n")
|
| 36 |
+
str_container=[]
|
| 37 |
+
counter=-1
|
| 38 |
+
for i in pubmed_split:
|
| 39 |
+
str_container.append({})
|
| 40 |
+
counter+=1
|
| 41 |
+
if i.startswith("TI"):
|
| 42 |
+
str_container[counter].update({"Title (sometimes not complete)": i.replace('TI - ', '')})
|
| 43 |
+
if i.startswith("AU - "):
|
| 44 |
+
str_container[counter].update({"Author": i.replace('AU - ', '')})
|
| 45 |
+
if i.startswith("PHST") and i.endswith("[pubmed]"):
|
| 46 |
+
str_container[counter].update({"Published on PubMed on": i.replace('PHST- ', '').replace('[pubmed]','')})
|
| 47 |
+
if i.endswith("[doi]") and i.startswith("AID - "):
|
| 48 |
+
str_container[counter].update({"doi": f"https://doi.org/{i[6:len(i)-5]}\n"})
|
| 49 |
+
results=[]
|
| 50 |
+
for j in str_container:
|
| 51 |
+
ls=[f"{key}: {j[key]}\n" for key in list(j.keys())]
|
| 52 |
+
results.append("".join(ls))
|
| 53 |
+
remove_blankets(results)
|
| 54 |
+
defstr="".join(results)
|
| 55 |
+
return defstr
|