datamule 1.3.0__tar.gz → 1.4.0__tar.gz

{datamule-1.3.0 → datamule-1.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datamule
-Version: 1.3.0
+Version: 1.4.0
 Summary: Work with SEC submissions at scale.
 Home-page: https://github.com/john-friedman/datamule-python
 Author: John Friedman

{datamule-1.3.0 → datamule-1.4.0}/datamule/document/document.py

@@ -3,11 +3,14 @@ import csv
 import re
 from doc2dict import xml2dict, txt2dict, dict2dict
 from doc2dict.mapping import flatten_hierarchy
+from doc2dict import html2dict, visualize_dict, get_title, unnest_dict
 from ..mapping_dicts.txt_mapping_dicts import dict_10k, dict_10q, dict_8k, dict_13d, dict_13g
 from ..mapping_dicts.xml_mapping_dicts import dict_345
+from ..mapping_dicts.html_mapping_dicts import dict_10k_html, dict_10q_html, dict_8k_html
 from selectolax.parser import HTMLParser
 from .processing import process_tabular_data
 from pathlib import Path
+import webbrowser
 
 class Document:
     def __init__(self, type, content, extension,accession,filing_date,path=None):
@@ -99,26 +102,10 @@ class Document:
         if self.data:
             return self.data
         
-        # preprocess content
-        if self.extension == '.txt':
-            self.content = self._preprocess_txt_content()
-        elif self.extension in ['.htm', '.html']:
-            self.content = self._preprocess_html_content()
-
         mapping_dict = None
-
-        if self.extension == '.xml':
-            if self.type in ['3', '4', '5', '3/A', '4/A', '5/A']:
-                mapping_dict = dict_345
-
-            self.data = xml2dict(content=self.content, mapping_dict=mapping_dict)
-
-
-
-        # will deprecate this when we add html2dict
-        elif self.extension in ['.htm', '.html','.txt']:
-
-
+        
+        if self.extension == '.txt':
+            content = self._preprocess_txt_content()
             if self.type == '10-Q':
                 mapping_dict = dict_10q
             elif self.type == '10-K':
@@ -131,8 +118,24 @@ class Document:
                 mapping_dict = dict_13g
             
             self.data = {}
-            self.data['document'] = dict2dict(txt2dict(content=self.content, mapping_dict=mapping_dict))
-        return self.data
+            self.data['document'] = dict2dict(txt2dict(content=content, mapping_dict=mapping_dict))
+        elif self.extension in ['.htm', '.html']:
+            if self.type == '10-K':
+                mapping_dict = dict_10k_html
+            elif self.type == '10-Q':
+                mapping_dict = dict_10q_html
+            elif self.type == '8-K':
+                mapping_dict = dict_8k_html
+            
+            dct = html2dict(content=self.content, mapping_dict=mapping_dict)
+            self.data = dct
+        elif self.extension == '.xml':
+            if self.type in ['3', '4', '5', '3/A', '4/A', '5/A']:
+                mapping_dict = dict_345
+            
+            self.data = xml2dict(content=self.content, mapping_dict=mapping_dict)
+        else:
+            pass
     
     def write_json(self, output_filename=None):
         if not self.data:
@@ -206,6 +209,31 @@ class Document:
                     })
         
         return items
+    
+    def visualize(self):
+        if not self.data:
+            self.parse()
+
+        if not self.data:
+            if self.extension in ['.jpg', '.png', '.pdf']:
+                webbrowser.open('file://' + str(self.path))
+            else:
+                pass
+        else:
+            visualize_dict(self.data)
+
+    def get_section(self, title, format='dict'):
+        if not self.data:
+            self.parse()
+
+        result = get_title(self.data,title)
+
+        if format == 'text':
+            result = [item[1] for item in result]
+            result = [unnest_dict(item) for item in result]
+
+        return result
+
    
    # this will all have to be changed. default will be to flatten everything
    # candidate for deletion

{datamule-1.3.0 → datamule-1.4.0}/datamule/helper.py

@@ -5,28 +5,17 @@ import os
 
 def _load_package_csv(name):
     """Load CSV files from package data directory"""
-    # First try to load from the package data directory
-    try:
-        package_dir = os.path.dirname(os.path.dirname(__file__))
-        csv_path = os.path.join(package_dir, "data", f"{name}.csv")
-        
-        # Fallback to the legacy location
-        if not os.path.exists(csv_path):
-            csv_path = Path.home() / ".datamule" / f"{name}.csv"
-        
-        data = []
-        with open(csv_path, 'r') as csvfile:
-            csv_reader = csv.DictReader(csvfile)
-            for row in csv_reader:
-                data.append(row)
-        
-        return data
+    package_dir = os.path.dirname(os.path.dirname(__file__))
+    csv_path = os.path.join(package_dir,"datamule", "data", f"{name}.csv")
+    
+    data = []
+    with open(csv_path, 'r') as csvfile:
+        csv_reader = csv.DictReader(csvfile)
+        for row in csv_reader:
+            data.append(row)
+    
+    return data
     
-    except FileNotFoundError:
-        raise FileNotFoundError(
-            f"Required data file '{name}.csv' not found. "
-            f"This file should be in the datamule package directory or in ~/.datamule/"
-        )
 
 def load_package_dataset(dataset):
     if dataset =='listed_filer_metadata':

datamule-1.4.0/datamule/mapping_dicts/html_mapping_dicts.py

@@ -0,0 +1,11 @@
+dict_10k_html = {
+    ('part',r'^part\s*([ivx]+)$') : 0,
+    ('signatures',r'^signatures?\.*$') : 0,
+    ('item',r'^item\s*(\d+)\.?([a-z])?') : 1,
+}
+dict_10q_html = dict_10k_html
+
+dict_8k_html = {
+    ('signatures',r'^signatures?\.*$') : 0,
+    ('item',r'^item\s*(\d+\.\d+)') : 0,
+}

{datamule-1.3.0 → datamule-1.4.0}/datamule.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datamule
-Version: 1.3.0
+Version: 1.4.0
 Summary: Work with SEC submissions at scale.
 Home-page: https://github.com/john-friedman/datamule-python
 Author: John Friedman

{datamule-1.3.0 → datamule-1.4.0}/datamule.egg-info/SOURCES.txt

@@ -42,6 +42,7 @@ datamule/document/mappings/thirteenfhr.py
 datamule/document/mappings/twentyfivense.py
 datamule/document/mappings/twentyfourf2nt.py
 datamule/mapping_dicts/__init__.py
+datamule/mapping_dicts/html_mapping_dicts.py
 datamule/mapping_dicts/txt_mapping_dicts.py
 datamule/mapping_dicts/xml_mapping_dicts.py
 datamule/sec/__init__.py

{datamule-1.3.0 → datamule-1.4.0}/setup.py

@@ -32,7 +32,7 @@ if not os.path.exists(file_path):
 setup(
     name="datamule",
     author="John Friedman",
-    version="1.3.0",
+    version="1.4.0",
     description="Work with SEC submissions at scale.",
     packages=find_packages(include=['datamule', 'datamule.*']),
     url="https://github.com/john-friedman/datamule-python",