| <!DOCTYPE html> | |
| <html> | |
| <head> | |
| <title>TESS Search to XLS</title> | |
| </head> | |
| <body> | |
| <h1>TESS Search to XLS</h1> | |
| <h5>This tool converts a page of TESS results to an XLS file that can be opened in excel.</h5> | |
| <h5>The application is still in beta version. The conversion may produce an error page or an XLS file with no data. Simply reload the home page and try again.</h5> | |
| <h5>Since TESS Search results are limited to 50 entries per page, this tool will only capture the 50 entries on the URL provided.</h5> | |
| <h5>Please enter a valid URL into the Textbox. Simply copy and paste the TESS result's URL for best results. Failure to enter a valid URL will resut in an error page.</h5> | |
| <form method="post" action="/tess"> | |
| <p>Enter Result URL here: | |
| <input type="text" name="url"> | |
| <input type="submit" name = "Submit"> | |
| </p> | |
| </form> | |
| </body> | |
| </html> |
To accomplish this task, setup download and setup an Apache HTTP Server.
Assuming the apache default is unchanged (/var/www), the following structure will work:
html/index.html
html/downloads/ ## a directory named "downloads" must be present under the HTML folder
cgi-bin/tess.py
In the apache http.conf, the following line is needed under <IfModule alias_module>:
ScriptAlias /tess "/var/www/cgi-bin/tess.py"
The final step is to run the apache server daemon
| #!/usr/bin/python | |
| import sys | |
| import os | |
| import time | |
| import urllib | |
| import cgi | |
| import cgitb | |
| cgitb.enable() | |
| print("Content-Type: text/html;charset=utf-8") | |
| print("Download Link: ") | |
| success = True | |
| finished = False | |
| formData = cgi.FieldStorage() | |
| url = formData.getvalue('url') | |
| while not finished: | |
| try: | |
| response = urllib.urlopen(url) | |
| except: | |
| success = False | |
| print(" INVALID URL") | |
| sys.exit() | |
| html = response.read() | |
| read = False; | |
| start_tag = '<TABLE BORDER=2>' | |
| end_tag = '</TABLE>' | |
| timestamp = int(time.time()) | |
| file_name = 'downloads/TESS_Results_'+str(timestamp)+'.xls' | |
| output_file = open('../html/'+file_name, 'w+') | |
| for l in html.splitlines(): | |
| line = l.rstrip() | |
| if not line: | |
| continue | |
| if(start_tag in line): | |
| read = True | |
| if(read and (end_tag in line)): | |
| output_file.write(line) | |
| read = False | |
| if(read): | |
| output_file.write(line) | |
| finished = True | |
| output_file.close() | |
| print('<a href="../'+file_name+'"download>TESS Results as .XLS</a>') | |