From 66010479022c6603e7feedbf868312b27bfa1838 Mon Sep 17 00:00:00 2001
From: beaufilx <Est1tiam2y@24>
Date: Fri, 31 Jan 2025 18:10:56 +0100
Subject: [PATCH 1/4] =?UTF-8?q?AdsQuery=20externalis=C3=A9?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
---
src/ptf/external/ads.py | 78 +++++++++++++++++++++++++++++++++++++++++
1 file changed, 78 insertions(+)
create mode 100644 src/ptf/external/ads.py
diff --git a/src/ptf/external/ads.py b/src/ptf/external/ads.py
new file mode 100644
index 000000000..5421fa207
--- /dev/null
+++ b/src/ptf/external/ads.py
@@ -0,0 +1,78 @@
+from requests_cache import CachedSession
+from requests_cache import FileCache
+
+import json
+
+from datetime import timedelta
+from django.conf import settings
+
+session = CachedSession(
+ backend=FileCache(
+ getattr(settings, "REQUESTS_CACHE_LOCATION", None) or "/tmp/ptf_requests_cache",
+ decode_content=False,
+ ),
+ match_headers={
+ "Authorization": "Bearer " + settings.ADS_TOKEN,
+ "User-Agent": getattr(settings, "REQUESTS_USER_AGENT", None) or "Mathdoc/1.0.0",
+ "From": getattr(settings, "REQUESTS_EMAIL", None) or "accueil@listes.mathdoc.fr",
+ },
+ expire_after=timedelta(days=30),
+)
+
+
+class AdsQuery:
+ def __init__(self):
+ self._start = 0
+ self._count = 0
+ self._present = {}
+
+ def query_referencing(self, pub: str):
+ while self._count >= self._start:
+ data = self._query(pub)
+ self._load(data)
+ return self._present
+
+ def _load(self, _results):
+ for result in _results:
+ if 'doi' in result:
+ for doi in result["doi"]:
+ if doi[:7] == '10.5802':
+ self._present[doi] = AdsArticle(doi, result['title'][0], result['pub'])
+ else:
+ print(result)
+
+ def _query(self, pub: str):
+ url = "https://api.adsabs.harvard.edu/v1/search/query"
+ query_param = {
+ "fl": "doi,title,pub",
+ "rows": "200",
+ "start": self._start,
+ "q": f"pub:\"{pub}\"",
+ }
+ response = session.get(url, params=query_param, headers={"Authorization": "Bearer " + settings.ADS_TOKEN})
+ response.raise_for_status()
+ data = json.loads(response.text)
+ self._count = data["response"]["numFound"]
+ self._start += 200
+ return data["response"]["docs"]
+
+
+class AdsArticle:
+ _doi: str
+ _pub: str
+ _title: str
+
+ def __init__(self, doi, title, pub):
+ self._title = title
+ self._doi = doi
+ self._pub = pub
+
+ def doi(self) -> str:
+ return self._doi
+
+ def title(self) -> str:
+ return self._title
+
+ def pub(self) -> str:
+ return self._pub
+
--
GitLab
From 7b08a6ec369c7de5ba4d9626567b8de577a39689 Mon Sep 17 00:00:00 2001
From: beaufilx <Est1tiam2y@24>
Date: Thu, 6 Feb 2025 09:24:10 +0100
Subject: [PATCH 2/4] Recherche par ISSN
---
src/ptf/external/ads.py | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/src/ptf/external/ads.py b/src/ptf/external/ads.py
index 5421fa207..6e0af2b83 100644
--- a/src/ptf/external/ads.py
+++ b/src/ptf/external/ads.py
@@ -2,10 +2,11 @@ from requests_cache import CachedSession
from requests_cache import FileCache
import json
-
from datetime import timedelta
from django.conf import settings
+from ptf.model_data import ArticleData
+
session = CachedSession(
backend=FileCache(
getattr(settings, "REQUESTS_CACHE_LOCATION", None) or "/tmp/ptf_requests_cache",
@@ -37,17 +38,17 @@ class AdsQuery:
if 'doi' in result:
for doi in result["doi"]:
if doi[:7] == '10.5802':
- self._present[doi] = AdsArticle(doi, result['title'][0], result['pub'])
+ self._present[doi] = ArticleData(doi=doi, title_html=result['title'][0], pub=result['pub'])
else:
print(result)
- def _query(self, pub: str):
+ def _query(self, issn: str):
url = "https://api.adsabs.harvard.edu/v1/search/query"
query_param = {
"fl": "doi,title,pub",
"rows": "200",
"start": self._start,
- "q": f"pub:\"{pub}\"",
+ "q": f"issn:\"{issn}\"",
}
response = session.get(url, params=query_param, headers={"Authorization": "Bearer " + settings.ADS_TOKEN})
response.raise_for_status()
--
GitLab
From 79357e971f6cbdecc51b56252672d2a47ead407d Mon Sep 17 00:00:00 2001
From: beaufilx <Est1tiam2y@24>
Date: Mon, 10 Feb 2025 10:35:10 +0100
Subject: [PATCH 3/4] =?UTF-8?q?Acces=20=C3=A0=20ADS=5FTOKEN?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
---
src/ptf/external/ads.py | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/src/ptf/external/ads.py b/src/ptf/external/ads.py
index 6e0af2b83..c4aeba0f7 100644
--- a/src/ptf/external/ads.py
+++ b/src/ptf/external/ads.py
@@ -43,6 +43,7 @@ class AdsQuery:
print(result)
def _query(self, issn: str):
+ ads_token = getattr(settings, "ADS_TOKEN", None)
url = "https://api.adsabs.harvard.edu/v1/search/query"
query_param = {
"fl": "doi,title,pub",
@@ -50,7 +51,7 @@ class AdsQuery:
"start": self._start,
"q": f"issn:\"{issn}\"",
}
- response = session.get(url, params=query_param, headers={"Authorization": "Bearer " + settings.ADS_TOKEN})
+ response = session.get(url, params=query_param, headers={"Authorization": "Bearer " + ads_token})
response.raise_for_status()
data = json.loads(response.text)
self._count = data["response"]["numFound"]
--
GitLab
From b48158aa405a96c0037d55534270fdfcd2254141 Mon Sep 17 00:00:00 2001
From: beaufilx <Est1tiam2y@24>
Date: Tue, 11 Feb 2025 10:35:36 +0100
Subject: [PATCH 4/4] =?UTF-8?q?Acces=20=C3=A0=20ADS=5FTOKEN?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
---
src/ptf/external/ads.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/src/ptf/external/ads.py b/src/ptf/external/ads.py
index c4aeba0f7..574260da3 100644
--- a/src/ptf/external/ads.py
+++ b/src/ptf/external/ads.py
@@ -13,7 +13,7 @@ session = CachedSession(
decode_content=False,
),
match_headers={
- "Authorization": "Bearer " + settings.ADS_TOKEN,
+ "Authorization": "Bearer " + getattr(settings, "ADS_TOKEN", ""),
"User-Agent": getattr(settings, "REQUESTS_USER_AGENT", None) or "Mathdoc/1.0.0",
"From": getattr(settings, "REQUESTS_EMAIL", None) or "accueil@listes.mathdoc.fr",
},
--
GitLab