Last active
January 31, 2019 14:20
-
-
Save eyJhb/b592aafd9f5d05623164687c25299ea8 to your computer and use it in GitHub Desktop.
Transpose HTML table
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
from bs4 import BeautifulSoup | |
f = open("index.html", "r") | |
data = f.read() | |
f.close() | |
bs = BeautifulSoup(data, "html.parser") | |
elements = {} | |
services = [] | |
headers = [] | |
first = True | |
for row in bs.findAll("tr"): | |
if first: | |
first = False | |
columns = row.findAll("th") | |
header = columns[0].getText() | |
headers.append(header) | |
elements[header] = [] | |
for x in range(1,15): | |
column = str(columns[x]) | |
column = column[5:-6] | |
elements[header].append(column) | |
# print(column) | |
print(len(services)) | |
continue | |
# exit() | |
columns = row.findAll("td") | |
header = columns[0].getText() | |
headers.append(header) | |
elements[header] = [] | |
for x in range(1,15): | |
try: | |
elements[header].append(columns[x].getText().strip()) | |
except: | |
elements[header].append("") | |
print(len(elements)) | |
print(headers) | |
print(elements) | |
print("-----") | |
print('<table class="centered">') | |
print("\t"+'<tr>') | |
for header in headers: | |
print("\t\t"+'<th>'+header+'</th>') | |
print("\t"+'</tr>') | |
for x in range(0,14): | |
print("\t"+'<tr>') | |
# print("\t\t"+'<td>'+services[x]+'</td>') | |
for header in headers: | |
print("\t\t"+'<td>'+elements[header][x]+'</td>') | |
print("\t"+'</tr>') | |
print('</table>') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment