├── README.md
├── .gitignore
├── LICENSE
└── mysql_dump_to_csv.py


/README.md:
--------------------------------------------------------------------------------
1 | # mysql-dump-to-csv
2 | Quickly put together script to parse a mysql dump and generate CSVs for all of the tables in the dump.
3 | 
4 | Example:
5 | 
6 | `python mysql_dump_to_csv.py dump.sql output`
7 | 
8 | Should output a CSV file for each table that has data within the dump file.
9 | 


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
 1 | # Byte-compiled / optimized / DLL files
 2 | __pycache__/
 3 | *.py[cod]
 4 | 
 5 | # C extensions
 6 | *.so
 7 | 
 8 | # Distribution / packaging
 9 | .Python
10 | env/
11 | build/
12 | develop-eggs/
13 | dist/
14 | downloads/
15 | eggs/
16 | .eggs/
17 | lib/
18 | lib64/
19 | parts/
20 | sdist/
21 | var/
22 | *.egg-info/
23 | .installed.cfg
24 | *.egg
25 | 
26 | # PyInstaller
27 | #  Usually these files are written by a python script from a template
28 | #  before PyInstaller builds the exe, so as to inject date/other infos into it.
29 | *.manifest
30 | *.spec
31 | 
32 | # Installer logs
33 | pip-log.txt
34 | pip-delete-this-directory.txt
35 | 
36 | # Unit test / coverage reports
37 | htmlcov/
38 | .tox/
39 | .coverage
40 | .coverage.*
41 | .cache
42 | nosetests.xml
43 | coverage.xml
44 | *,cover
45 | 
46 | # Translations
47 | *.mo
48 | *.pot
49 | 
50 | # Django stuff:
51 | *.log
52 | 
53 | # Sphinx documentation
54 | docs/_build/
55 | 
56 | # PyBuilder
57 | target/
58 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
 1 | The MIT License (MIT)
 2 | 
 3 | Copyright (c) 2015 Michael Hahn
 4 | 
 5 | Permission is hereby granted, free of charge, to any person obtaining a copy
 6 | of this software and associated documentation files (the "Software"), to deal
 7 | in the Software without restriction, including without limitation the rights
 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 | 
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 | 
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 | 
23 | 


--------------------------------------------------------------------------------
/mysql_dump_to_csv.py:
--------------------------------------------------------------------------------
 1 | import ast
 2 | import csv
 3 | import os
 4 | import sys
 5 | import re
 6 | 
 7 | SCHEMAS = {}
 8 | 
 9 | 
10 | def is_create_statement(line):
11 |     return line.startswith('CREATE TABLE')
12 | 
13 | 
14 | def is_field_definition(line):
15 |     return line.strip().startswith('`')
16 | 
17 | 
18 | def is_insert_statement(line):
19 |     return line.startswith('INSERT INTO')
20 | 
21 | 
22 | def get_mysql_name_value(line):
23 |     value = None
24 |     result = re.search(r'\`([^\`]*)\`', line)
25 |     if result:
26 |         value = result.groups()[0]
27 |     return value
28 | 
29 | 
30 | def get_value_tuples(line):
31 |     values = line.partition(' VALUES ')[-1].strip().replace('NULL', "''")
32 |     if values[-1] == ';':
33 |         values = values[:-1]
34 | 
35 |     return ast.literal_eval(values)
36 | 
37 | 
38 | def write_file(output_directory, table_name, schema, values):
39 |     file_name = os.path.join(output_directory, '%s.csv' % (table_name,))
40 |     with open(file_name, 'w') as write_file:
41 |         writer = csv.DictWriter(write_file, fieldnames=schema)
42 |         writer.writeheader()
43 |         for value in values:
44 |             writer.writerow(dict(zip(schema, value)))
45 | 
46 | 
47 | def parse_file(file_name, output_directory):
48 |     current_table_name = None
49 | 
50 |     with open(file_name, 'r') as read_file:
51 |         for line in read_file:
52 |             if is_create_statement(line):
53 |                 current_table_name = get_mysql_name_value(line)
54 |                 SCHEMAS[current_table_name] = []
55 |             elif current_table_name and is_field_definition(line):
56 |                 field_name = get_mysql_name_value(line)
57 |                 SCHEMAS[current_table_name].append(field_name)
58 |             elif is_insert_statement(line):
59 |                 current_table_name = get_mysql_name_value(line)
60 |                 current_schema = SCHEMAS[current_table_name]
61 |                 values = get_value_tuples(line)
62 |                 write_file(output_directory, current_table_name, current_schema, values)
63 | 
64 | if __name__ == '__main__':
65 |     parse_file(sys.argv[1], sys.argv[2])
66 | 


--------------------------------------------------------------------------------