Updates core rank to 2023, removes a bug concerning certain old journals, adds...

Updates core rank to 2023, removes a bug concerning certain old journals, adds capability to clean the cache

get_rankings/get_rankings.py

@@ -4,12 +4,14 @@ import logging
 from tqdm import tqdm
 from tqdm.contrib.logging import logging_redirect_tqdm
 import os
+import sys
 import datetime
 from dateutil.parser import parse as parsedate
 from bs4 import BeautifulSoup
 import pandas as pd
 import argparse
 import re
+import shutil
 
 from get_rankings.hash_cache import load_hash_caches, save_hash_caches, default_cache
 from get_rankings.tools import levenshtein, download, get_in_ordered_list
@@ -48,6 +50,8 @@ def get_dblp(url, cache=True, cache_dir=None):
 
 
 def get_core_year(year):
+    if year >= 2023:
+        return "CORE2023"
     if year >= 2021:
         return "CORE2021"
     if year >= 2020:
@@ -98,9 +102,12 @@ class Sjr:
         data = download("https://dblp.org/db/journals/%s/index.html" % acronym)
         soup = BeautifulSoup(data, "html.parser")
         full_name = soup.find("h1").text
-        issn = soup.find(
-            "a", attrs={"href": re.compile("^https://portal.issn.org/resource/ISSN/")}
-        ).text
+        try:
+            issn = soup.find(
+                "a", attrs={"href": re.compile("^https://portal.issn.org/resource/ISSN/")}
+            ).text
+        except:
+            issn = None
         return (full_name, issn)
 
     def get(self, name, second_name, year):
@@ -110,13 +117,15 @@ class Sjr:
             _ , issn = self.get_issn(second_name)
             rankings = self.get_sjr_rank(issn)
             self.ranking_caches[(name, second_name)] = rankings
-        rank = get_in_ordered_list(rankings, int(year))
+        rank = None if rankings is None else get_in_ordered_list(rankings, int(year))
         if rank is None:
             return ["J", name, second_name, int(year), None, None, None]
         else:
             return ["J", name, second_name, int(year), rank[1], None, rank[2]]
 
     def get_sjr_rank(self, name):
+        if name is None:
+            return None
         url = "https://www.scimagojr.com/journalsearch.php?q=%s" % name.replace(
             " ", "+"
         )
@@ -172,7 +181,7 @@ def main():
     parser = argparse.ArgumentParser(
         description="Get ranking from DBLP and show a small summary"
     )
-    parser.add_argument("url", help="DBLP url")
+    parser.add_argument("url", help="DBLP url (or use clear-cache to clear the cache, is should be done regularly)")
     parser.add_argument("--start", type=int, default=-1, help="starting year")
     parser.add_argument("--end", type=int, default=10000, help="ending year")
     parser.add_argument(
@@ -206,6 +215,13 @@ def main():
     display_list = args.d
     logging.basicConfig(level=args.loglevel, format="%(levelname)s %(message)s")
 
+    if args.url == 'clear-cache':
+        cache_dir = default_cache()
+        print("Cleaning the cache :", cache_dir);
+        shutil.rmtree(cache_dir)
+        print("Cache clear");
+        sys.exit(0)
+    
     username, elements = get_dblp(url)
 
     # Keeps only elements in the requested range

setup.py

@@ -5,7 +5,7 @@ with open("README.md", "r") as fh:
 
 setuptools.setup(
     name="get_rankings",
-    version="0.8",
+    version="0.9",
     author="Georges Da Costa",
     author_email="georges.da-costa@irit.fr",
     description="DBLP ranking using CORE Rank and SJR",