Improvements

main.py

@@ -1,14 +1,8 @@
 #!/usr/bin/python3
 
-import hashlib
-import json
 import os
-import time
-import typing
-from typing import cast
 
 import flask
-import requests
 import sqlalchemy
 from sqlalchemy import func, or_, update
 from werkzeug.wrappers import Response
@@ -21,37 +15,6 @@ app.debug = True
 app.config.from_object("config.default")
 database.init_app(app)
 
-wikidata_api = "https://www.wikidata.org/w/api.php"
-
-
-def md5sum(s: str) -> str:
-    return hashlib.md5(s.encode("utf-8")).hexdigest()
-
-
-def wikidata_search(q: str) -> list[dict[str, typing.Any]]:
-    q += " haswbstatement:P31=Q5"
-    q_md5 = md5sum(q)
-
-    cache_filename = os.path.join("cache", q_md5 + ".json")
-
-    if os.path.exists(cache_filename):
-        data = json.load(open(cache_filename))
-    else:
-        params: dict[str, str | int] = {
-            "action": "query",
-            "list": "search",
-            "format": "json",
-            "formatversion": 2,
-            "srsearch": q,
-            "srlimit": "max",
-        }
-        r = requests.get(wikidata_api, params=params)
-        open(cache_filename, "w").write(r.text)
-        data = r.json()
-        time.sleep(1)
-
-    return cast(list[dict[str, typing.Any]], data["query"]["search"])
-
 
 def top_speakers() -> sqlalchemy.orm.query.Query:
     q = (
@@ -89,6 +52,7 @@ def top_events() -> sqlalchemy.orm.query.Query:
 
 
 def drop_start(s: str, start: str) -> str:
+    """Remove text from the start of a string."""
     return s[len(start) :] if s.startswith(start) else s
 
 
@@ -121,7 +85,8 @@ def person(person_id: int) -> str | Response:
 
     wikidata_hits: list[dict[str, str]] = []
     if False and item.wikidata_qid is None:
-        search_hits = wikidata_search(item.name)
+        q = item.name + " haswbstatement:P31=Q5"
+        search_hits = wikidata.search(q)
         print(len(search_hits))
         for search_hit in search_hits:
             qid = search_hit["title"]
@@ -350,7 +315,8 @@ def link_to_wikidata() -> str:
     for person, num in top_speakers2():
         if person.wikidata_qid:
             continue
-        search_hits = wikidata_search(person.name)
+        q = person.name + " haswbstatement:P31=Q5"
+        search_hits = wikidata.search(q)
         if not search_hits:
             continue
 
@@ -361,7 +327,7 @@ def link_to_wikidata() -> str:
 
         for search_hit in search_hits:
             qid = search_hit["title"]
-            item = wikidata_get_item(qid)
+            item = wikidata.get_item(qid)
             if "en" in item["labels"]:
                 label = item["labels"]["en"]["value"]
             else:
@@ -425,7 +391,8 @@ def delete_person(person_id: int) -> str | Response:
     return flask.redirect(flask.url_for("index"))
 
 
-def person_image_filename(person_id):
+def person_image_filename(person_id: int) -> str:
+    """Filename for speaker photo."""
     person = model.Person.query.get(person_id)
     return os.path.join("wikidata_photo", "thumb", person.wikidata_photo[0])
 
@@ -440,6 +407,7 @@ def person_image_filename(person_id):
 
 @app.route("/github_wikidata")
 def github_wikidata() -> str:
+    """Look for speakers on Wikidata based on the GitHub property."""
     items = []
     for line in open("found_wikidata_github"):
         person_id, person_name, qid, wd_name, github, photo = eval(line)
@@ -453,6 +421,7 @@ def github_wikidata() -> str:
 
 @app.route("/reports")
 def reports_page() -> str:
+    """Page showing statistics."""
     event_count = model.Event.query.count()
 
     missing_event_date_count = model.Event.query.filter(