Last active
August 29, 2015 14:15
-
-
Save JenkinsDev/24f650074d3ab86d243f to your computer and use it in GitHub Desktop.
HTML table to CSV
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import sys | |
def generate_csv_data_from_html_table(html): | |
csv_header = "" | |
csv_rows = [] | |
rows = create_rows_from_trs(remove_tab_and_newline(html)) | |
for row in rows: | |
if not row.find("<th>") == -1: | |
csv_header = row.replace("<th>", "").replace("</th>", ",") | |
elif not row.find("<td>") == -1: | |
csv_rows.append(row.replace("<td>", "").replace("</td>", ",")) | |
return (csv_header, csv_rows) | |
def remove_tab_and_newline(string): | |
return string.replace("\n", "").replace("\t", "") | |
def create_rows_from_trs(string): | |
return string.replace("<table", "").replace("</table>", "") \ | |
.replace("</tr>", "").split("<tr>") | |
if __name__ == '__main__': | |
file = sys.argv[1] | |
out_file = sys.argv[2] | |
with open(file) as f: | |
(header, rows) = generate_csv_data_from_html_table(f.read()) | |
with open(out_file, 'a') as out_f: | |
# We want to make sure the file is empty, so beware! | |
out_f.truncate() | |
out_f.write("{0}\n".format(header)) | |
for row in rows: | |
out_f.write("{0}\n".format(row)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment