forked from srbhr/Resume-Matcher
-
Notifications
You must be signed in to change notification settings - Fork 0
/
run_first.py
77 lines (60 loc) · 2.56 KB
/
run_first.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
import json
import logging
import os
from scripts import JobDescriptionProcessor, ResumeProcessor
from scripts.utils import get_filenames_from_dir, init_logging_config
init_logging_config()
PROCESSED_RESUMES_PATH = "Data/Processed/Resumes"
PROCESSED_JOB_DESCRIPTIONS_PATH = "Data/Processed/JobDescription"
def read_json(filename):
with open(filename) as f:
data = json.load(f)
return data
def remove_old_files(files_path):
for filename in os.listdir(files_path):
try:
file_path = os.path.join(files_path, filename)
if os.path.isfile(file_path):
os.remove(file_path)
except Exception as e:
logging.error(f"Error deleting {file_path}:\n{e}")
logging.info("Deleted old files from " + files_path)
logging.info("Started to read from Data/Resumes")
try:
# Check if there are resumes present or not.
# If present then parse it.
remove_old_files(PROCESSED_RESUMES_PATH)
file_names = get_filenames_from_dir("Data/Resumes")
logging.info("Reading from Data/Resumes is now complete.")
except:
# Exit the program if there are no resumes.
logging.error("There are no resumes present in the specified folder.")
logging.error("Exiting from the program.")
logging.error("Please add resumes in the Data/Resumes folder and try again.")
exit(1)
# Now after getting the file_names parse the resumes into a JSON Format.
logging.info("Started parsing the resumes.")
for file in file_names:
processor = ResumeProcessor(file)
success = processor.process()
logging.info("Parsing of the resumes is now complete.")
logging.info("Started to read from Data/JobDescription")
try:
# Check if there are resumes present or not.
# If present then parse it.
remove_old_files(PROCESSED_JOB_DESCRIPTIONS_PATH)
file_names = get_filenames_from_dir("Data/JobDescription")
logging.info("Reading from Data/JobDescription is now complete.")
except:
# Exit the program if there are no resumes.
logging.error("There are no job-description present in the specified folder.")
logging.error("Exiting from the program.")
logging.error("Please add resumes in the Data/JobDescription folder and try again.")
exit(1)
# Now after getting the file_names parse the resumes into a JSON Format.
logging.info("Started parsing the Job Descriptions.")
for file in file_names:
processor = JobDescriptionProcessor(file)
success = processor.process()
logging.info("Parsing of the Job Descriptions is now complete.")
logging.info("Success now run `streamlit run streamlit_second.py`")