zcdsj
/
paper_server
5
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat: get_abstract_from_elsevier 可自动触发自己

This commit is contained in:
caoqianming 2026-01-26 17:42:16 +08:00
parent a11dce1358
commit 5529f97ab8
1 changed files with 75 additions and 60 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
apps/resm/tasks.py
View File

@ -11,6 +11,7 @@ import requests
from lxml import etree from lxml import etree
from django.conf import settings from django.conf import settings
import os import os
from celery import current_app
config.email = "caoqianming@foxmail.com" config.email = "caoqianming@foxmail.com"
config.max_retries = 0 config.max_retries = 0
@ -61,11 +62,11 @@ def get_paper_meta_from_openalex(publication_year:int, search_key:str):
ELSEVIER_APIKEY = 'aa8868cac9e27d6153ab0a0acd7b50bf' ELSEVIER_APIKEY = 'aa8868cac9e27d6153ab0a0acd7b50bf'
@shared_task(base=CustomTask) @shared_task(base=CustomTask)
def get_abstract_from_elsevier(publication_year: int, number_of_task:int = 100): def get_abstract_from_elsevier(publication_year: int = None, number_of_task:int = 100):
qs = Paper.objects.filter( qs = Paper.objects.filter(has_abstract=True)
publication_year=publication_year, if publication_year is not None:
has_abstract=False qs = qs.filter(publication_year=publication_year)
).exclude( qs = qs.exclude(
fail_reason="elsevier_doi_not_found" fail_reason="elsevier_doi_not_found"
).order_by("publication_date") ).order_by("publication_date")
@ -77,8 +78,12 @@ def get_abstract_from_elsevier(publication_year: int, number_of_task:int = 100):
"httpAccept": "text/xml" "httpAccept": "text/xml"
} }
err_msg = "" err_msg = ""
req = requests.Session() if number_of_task is None:
for paper in qs[:number_of_task]: papers = qs.all()
else:
papers = qs[:number_of_task]
with requests.Session() as req:
for paper in papers:
try: try:
res = req.get( res = req.get(
f"https://api.elsevier.com/content/article/doi/{paper.doi}", f"https://api.elsevier.com/content/article/doi/{paper.doi}",
@ -111,12 +116,14 @@ def get_abstract_from_elsevier(publication_year: int, number_of_task:int = 100):
) )
paper.has_abstract = True paper.has_abstract = True
paper.has_abstract_xml = True paper.has_abstract_xml = True
paper.fetch_status = "abstract_ready"
paras = root.xpath("//ce:para", namespaces=ns) paras = root.xpath("//ce:para", namespaces=ns)
has_fulltext = len(paras) > 0 has_fulltext = len(paras) > 0
if has_fulltext: if has_fulltext:
paper.has_fulltext = True paper.has_fulltext = True
paper.has_fulltext_xml = True paper.has_fulltext_xml = True
paper.fetch_status = "fulltext_ready"
publication_date = paper.publication_date publication_date = paper.publication_date
paper_dir = os.path.join( paper_dir = os.path.join(
@ -143,4 +150,12 @@ def get_abstract_from_elsevier(publication_year: int, number_of_task:int = 100):
if remaining_count == 0: if remaining_count == 0:
return "done" return "done"
else: else:
current_app.send_task(
"apps.resm.tasks.get_abstract_from_elsevier",
kwargs={
"publication_year": publication_year,
"number_of_task": number_of_task,
},
countdown=5,
)
return f'{err_msg}, remaining {remaining_count} papers' return f'{err_msg}, remaining {remaining_count} papers'