changed dirs, clean code

MW_thesaurus.py

@@ -22,12 +22,46 @@ class MWThesaurusParser(WordParser):
                         [e.remove(ul) for ul in e.findall(".//ul")]
                         d = ot(e)
                         thes[d] = {"examples": examples}
-                    thes[d]["synonyms"] = [ ot(li) for li in se.findall( ".//span[@class='thes-list syn-list']/div[@class='thes-list-content synonyms_list']//li//a") ]
+                    thes[d]["synonyms"] = [
-                    thes[d]["near synonyms"] = [ ot(li) for li in se.findall( ".//span[@class='thes-list rel-list']/div[@class='thes-list-content synonyms_list']//li//a") ]
+                        ot(li)
-                    thes[d]["near synonyms"].extend([ ot(li) for li in se.findall( ".//span[@class='thes-list sim-list']/div[@class='thes-list-content synonyms_list']//li//a") ])
+                        for li in se.findall(
-                    thes[d]["near antonyms"] = [ ot(li) for li in se.findall( ".//span[@class='thes-list near-list']/div[@class='thes-list-content synonyms_list']//li//a") ]
+                            ".//span[@class='thes-list syn-list']/div[@class='thes-list-content synonyms_list']//li//a"
-                    thes[d]["near antonyms"].extend([ ot(li) for li in se.findall( ".//span[@class='thes-list opp-list']/div[@class='thes-list-content synonyms_list']//li//a") ])
+                        )
-                    thes[d]["antonyms"] = [ ot(li) for li in se.findall( ".//span[@class='thes-list ant-list']/div[@class='thes-list-content synonyms_list']//li//a") ]
+                    ]
+                    thes[d]["near synonyms"] = [
+                        ot(li)
+                        for li in se.findall(
+                            ".//span[@class='thes-list rel-list']/div[@class='thes-list-content synonyms_list']//li//a"
+                        )
+                    ]
+                    thes[d]["near synonyms"].extend(
+                        [
+                            ot(li)
+                            for li in se.findall(
+                                ".//span[@class='thes-list sim-list']/div[@class='thes-list-content synonyms_list']//li//a"
+                            )
+                        ]
+                    )
+                    thes[d]["near antonyms"] = [
+                        ot(li)
+                        for li in se.findall(
+                            ".//span[@class='thes-list near-list']/div[@class='thes-list-content synonyms_list']//li//a"
+                        )
+                    ]
+                    thes[d]["near antonyms"].extend(
+                        [
+                            ot(li)
+                            for li in se.findall(
+                                ".//span[@class='thes-list opp-list']/div[@class='thes-list-content synonyms_list']//li//a"
+                            )
+                        ]
+                    )
+                    thes[d]["antonyms"] = [
+                        ot(li)
+                        for li in se.findall(
+                            ".//span[@class='thes-list ant-list']/div[@class='thes-list-content synonyms_list']//li//a"
+                        )
+                    ]
 
         return thes
 
@@ -60,7 +94,7 @@ class MWThesaurusParser(WordParser):
 # print(w.todict())
 # exit()
 
-q = Queue(MWThesaurusParser, "en_MW_thesaurus/", "_mwt.json", prefix_length=2)
+q = Queue(MWThesaurusParser, "en_MWThesaurus/", "_MWT.json")
 q.loadDB()
 
 while True:

analysis.py

@@ -1,7 +1,6 @@
 # import matplotlib.pyplot as plt
 # from PIL import Image
 # from wordcloud import STOPWORDS, WordCloud
-from dict_dl import fulldictionary
 
 d = FullDictionary("en_merriam_webster/", "_mw.json")
 # d = Dictionary("en_MW_thesaurus/", "_mwt.json")
@@ -23,6 +22,7 @@ with open(f"{d.dir_prefix}redo", "at") as f:
     f.write("\n".join(list(again)))
 exit()
 
+
 def grey_color_func(
     word, font_size, position, orientation, random_state=None, **kwargs
 ):

duden.py

@@ -81,7 +81,8 @@ class DudenParser(WordParser):
         assert (
             self.type or self.definitions
         ), f"{self.time} {self.word}: type or definitions came back empty..."
-        return uqall({
+        return uqall(
+            {
                 self.word: {
                     "type": self.type,
                     "definitions": self.definitions,
@@ -91,14 +92,16 @@ class DudenParser(WordParser):
                     "wendungen": self.wendungen,
                     "time_of_retrieval": self.time,
                 }
-        })
+            }
+        )
+
 
 # d = DudenParser("hinfallen")
 # print(d.neighbours)
 # print(d.todict())
 # exit()
 
-q = Queue(DudenParser, "de_duden/", "_duden.json")
+q = Queue(DudenParser, "de_Duden/", "_D.json")
 q.loadDB()
 
 while True:

merriam_webster.py

@@ -108,7 +108,8 @@ class MerriamWebsterParser(WordParser):
         assert (
             self.type or self.definitions
         ), f"{self.time} {self.word}: type or definitions came back empty..."
-        return uqall({
+        return uqall(
+            {
                 self.word: {
                     "type": self.type,
                     "definitions": self.definitions,
@@ -121,7 +122,8 @@ class MerriamWebsterParser(WordParser):
                     "first_known_use": self.first_known_use,
                     "time_of_retrieval": self.time,
                 }
-        })
+            }
+        )
 
 
 # testword = "revivalist"
@@ -132,7 +134,7 @@ class MerriamWebsterParser(WordParser):
 #     print(f"### {k} ###\n", v)
 # exit()
 
-q = Queue(MerriamWebsterParser, "en_merriam_webster/", "_mw.json", prefix_length=2)
+q = Queue(MerriamWebsterParser, "en_MerriamWebster/", "_MW.json")
 q.loadDB()
 
 while True:

t.py

@@ -10,11 +10,22 @@ prefix = query[:2]
 
 d = Dictionary("en_MW_thesaurus/", f"{prefix}_mwt.json")
 print(f"###    {query:<70}###")
-print("================================================================================")
+print(
+    "================================================================================"
+)
 for k, v in d[query].items():
     if k != "type":
         print(f"  {k}")
-        print("--------------------------------------------------------------------------------")
+        print(
-        for ka in ["synonyms", "related" if "related" in v else "near synonyms", "near antonyms", "antonyms"]:
+            "--------------------------------------------------------------------------------"
+        )
+        for ka in [
+            "synonyms",
+            "related" if "related" in v else "near synonyms",
+            "near antonyms",
+            "antonyms",
+        ]:
             print(f"{ka:^13}: {' | '.join(v[ka])}")
-        print("--------------------------------------------------------------------------------")
+        print(
+            "--------------------------------------------------------------------------------"
+        )