Mizuno and Aiim templates. Almost done with the default class and liquid extraction script.

Scripts/all_default_class_names.py

@@ -1,64 +1,73 @@
-import re
 from html.parser import HTMLParser
+import json
+import pandas as pd
 from pathlib import Path
-# import pandas as pd
 from bs4 import BeautifulSoup
+import pprint
+import re
+
+# from collections import Iterable
 
 # MASDICT = {'file': "", 'attributes' : { 'id': [], 'class': [] } }
+pp = pprint.PrettyPrinter(indent=4)
+MASDICT = {}
 MASLIST = []
 PARS = HTMLParser
-p = Path('/Users/normrasmussen/Documents/Work/Custom_Templates/current_templates_2-15-2024/')
-x = list(p.glob('**/*.html.liquid'))
-for posfile in x:
-    file = str(posfile)
-    htmlfile = open(file, 'r', encoding='utf-8')
-    file2 = open(file, 'r', encoding='utf-8')
-    # finfile = file.split('/')[-1]
-    code = file2.readlines()
-    inclst = [include for include in code if '{% include' in include]
-    print(inclst)
-    for lines in code:
-        if '{% include' in lines:
-            pass
 
-    soup = BeautifulSoup(htmlfile, 'html.parser')
-    clst = [node['class'] for node in soup.find_all() if node.has_attr('class')]
-    # print(clst)
-    ilst = [node['id'] for node in soup.find_all() if node.has_attr('id')]
-    # print(ilst)
 
-    # ids = []
-    # classes = []
-    #     if "class=" in lines:
-    #         tmpline = lines
-    #         if "id=" not in tmpline:
-    #             try:
-    #                 htmlclass = re.search('class="(.*)"', tmpline)
-    #                 classes.append(htmlclass.group(1))
-    #             except AttributeError as t:
-    #                 print("Class: ", t)
-    #                 pass
-    #             finally:
-    #                 pass
-    #     elif "id=" in lines:
-    #         try:
-    #             id = re.search('id="(.*)"', lines)
-    #             ids.append(id.group(1))
-    #         except AttributeError as t:
-    #             print("ID: ", t)
-    #             pass
-    #         finally:
-    #             pass
-    #     else:
-    #         pass
-    # seconddict = { 'file': finfile, 'attributes': { 'id' : ids, 'class': classes } }
-    # MASLIST.append(seconddict)
-    #
-# df = pd.json_normalize(MASLIST)
-# print(df)
-# kp = (df.set_index('file').apply(lambda x: x.str.split(",").explode()).reset_index())
-# ksp = df.set_index('file').apply(lambda x: df['attributes.class']([x.split(',') ]))
-# print(ksp)
-# kp2 = (df.set_index('file').apply(lambda x: x.str.split(" ").explode('attributes.class')).reset_index())
-# print(kp2)
+def main():
+    p = Path(
+        "/Users/normrasmussen/Documents/Work/Custom_Templates/current_templates_2-15-2024/"
+    )
+    x = list(p.glob("**/*.html.liquid"))
+    for posfile in x:
+        file = str(posfile)
+        strpfile = file.split("/")[7]
+        htmlfile = open(file, "r", encoding="utf-8")
+        file2 = open(file, "r", encoding="utf-8")
+        code = file2.readlines()
+        liq = [liquid for liquid in code if re.search('{{(.*)}}', liquid)]
+        quidlist = []
+        for quid in liq:
+            liqcludes = quid.strip()
+            liqclude = re.search('{{(.*)}}', liqcludes)
+            quidlist.append(liqclude.group(0))
+        inclst = [include for include in code if "{% include" in include]
+        inclist = []
+        for item in inclst:
+            includes = item.strip().split(" ")[2].replace('"','')
+            inclist.append(includes)
 
+        soup = BeautifulSoup(htmlfile, "html.parser")
+        clst = [node["class"] for node in soup.find_all() if node.has_attr("class")]
+        flatclass = flatten(clst)
+        flatclass = [it for it in flatclass if "np" in it]
+        ilst = [node["id"] for node in soup.find_all() if node.has_attr("id")]
+        flatid = flatten(ilst)
+
+        MASLIST.append({strpfile: {"includes": inclist,"liquid": quidlist, "class": flatclass, "id": flatid}})
+        MASDICT = {"data": MASLIST}
+    # pp.pprint(MASDICT)
+    to_pandas(MASDICT)
+
+
+def flatten(xs):
+    # Initialize list for this layer
+    flat_list = []
+    for x in xs:
+        # If it's a list, recurse down and return the interior list
+        if isinstance(x, list):
+            flat_list += flatten(x)
+        # Otherwise, add to this layer's list
+        else:
+            flat_list.append(x)
+    return flat_list
+
+def to_pandas(obj):
+    # df = pd.json_normalize(obj)
+    df = pd.json_normalize(obj['data'])
+    print(df)
+    df.to_csv('/Users/normrasmussen/Downloads/example_liquid.csv')
+
+if __name__ == "__main__":
+    main()