generalised code for expert report parsing

expert_report/parse_expert_pdf.py

@@ -9,34 +9,33 @@ from parse_expert_pdf_utils import (
 )
 import tika
 from tika import parser
-import re
-import warnings
-warnings.filterwarnings('ignore')
 
+tika.initVM()
+import os
 
-def main():
-    tika.initVM()
-    path = "/home/omkardesai/Code/pdf_parser/pdfs/expert_report1.pdf"
-    parsed_pdf = parser.from_file(path)
-    print(parsed_pdf.keys())
 
-    content = parsed_pdf['content'].strip().replace('\n', '')
-    # print(content)
-    # case_number = case_number_extraction(content)
-    # print(case_number)
-    # expert_name = expert_name_extraction(content)
-    # print(expert_name)
-    # plaintiff = plaintiff_extraction(content)
-    # print(plaintiff)
-    # defendent = defendent_extraction(content)
-    # print(defendent)
-    # patent = patent_extraction(content)
-    # print(patent)
-    # on_behalf_of = on_behalf_of_extraction(content)
-    # print(on_behalf_of)
-    acronym = acronym_extraction(content)
-    print(acronym)
+def main(PATH):
+    required_files = [file for file in os.listdir(PATH) if file.find(".pdf") != -1]
+    for file in required_files:
+        content = parser.from_file(file)["content"].strip().replace("\n", "")
+        # case_number = case_number_extraction(content)
+        # print(case_number)
+        # expert_name = expert_name_extraction(content)
+        # print(expert_name)
+        # plaintiff = plaintiff_extraction(content)
+        # print(plaintiff)
+        # defendent = defendent_extraction(content)
+        # print(defendent)
+        # patent = patent_extraction(content)
+        # print(patent)
+        # on_behalf_of = on_behalf_of_extraction(content)
+        # print(on_behalf_of)
+        acronym = acronym_extraction(content)
+        print(acronym)
 
 
 if __name__ == "__main__":
-    main()
+    HOME_DIR = os.path.expanduser("~")
+    BASE_DIR = "Code/pdf_parser/expert_report"
+    PATH = os.path.join(HOME_DIR, BASE_DIR)
+    main(PATH)