Skip to content Skip to sidebar Skip to footer
Home / Csv / Html / Html Table / Python

Converting A HTML Table To A CSV In Python

Post a Comment
I am trying to convert a table in HTML to a csv in Python. The table I am trying to extract is this one:
Dades de per&iacut

Solution 1:

Here's a way of doing it, it's probably not the nicest way but it works! You can read through the comments to figure out what the code is doing!

from bs4 import BeautifulSoup
import csv

#read the html
html = open("table.html").read()
soup = BeautifulSoup(html, 'html.parser')

# get the table from html
table = soup.select_one("table.tblperiode")

# find all rows
rows = table.findAll('tr')

# strip the header from rows
headers = rows[0]
header_text = []

# add the header text to array
for th in headers.findAll('th'):
    header_text.append(th.text)

# init row text array
row_text_array = []

# loop through rows and add row text to array
for row in rows[1:]:
    row_text = []
    # loop through the elements
    for row_element in row.findAll(['th', 'td']):
        # append the array with the elements inner text
        row_text.append(row_element.text.replace('\n', '').strip())
    # append the text array to the row text array
    row_text_array.append(row_text)

# output csv
with open("out.csv", "w") as f:
    wr = csv.writer(f)
    wr.writerow(header_text)
    # loop through each row array
    for row_text_single in row_text_array:
        wr.writerow(row_text_single)

Solution 2:

With this script:

import csv
from bs4 import BeautifulSoup

html = open('table.html').read()
soup = BeautifulSoup(html, features='lxml')
table = soup.select_one('table.tblperiode')
rows = []
for i, table_row in enumerate(table.findAll('tr')):
    if i > 0:
        periode = [' '.join(table_row.findAll('th')[0].text.split())]
        data = [x.text for x in table_row.findAll('td')]
        rows.append(periode + data)

header = ['Periode', 'TM', 'TX', 'TN', 'HRM', 'PPT', 'VVM', 'DVM', 'VVX', 'PM', 'RS']
with open('result.csv', 'w', newline='') as f:
    w = csv.writer(f)
    w.writerow(header)
    w.writerows(rows)

I've managed to generate following CSV file on output:

Periode,TM,TX,TN,HRM,PPT,VVM,DVM,VVX,PM,RS
00:00 - 00:30,16.2,16.5,15.4,93,0.0,6.5,293,10.4,0
00:30 - 01:00,16.4,16.5,16.1,90,0.0,5.8,288,8.6,0

Solution 3: 

import csv
from bs4 import BeautifulSoup
import pandas as pd

html = open('test.html').read()
soup = BeautifulSoup(html, features='lxml')
#Specify table name which you want to read.
#Example: <table class="queryResults" border="0" cellspacing="1">
table = soup.select_one('table.queryResults')

def get_all_tables(soup):
    return soup.find_all("table")


tbls = get_all_tables(soup)
for i, tablen in enumerate(tbls, start=1):
    print(i)
    print(tablen)

def get_table_headers(table):
    headers = []
    for th in table.find("tr").find_all("th"):
        headers.append(th.text.strip())
    return headers

head = get_table_headers(table)
#print(head)

def get_table_rows(table):    
    rows = []
    for tr in table.find_all("tr")[1:]:
        cells = []
        # grab all td tags in this table row
        tds = tr.find_all("td")
        if len(tds) == 0:
            # if no td tags, search for th tags
            # can be found especially in wikipedia tables below the table
            ths = tr.find_all("th")
            for th in ths:
                cells.append(th.text.strip())
        else:
            # use regular td tags
            for td in tds:
                cells.append(td.text.strip())
        rows.append(cells)
    return rows

table_rows = get_table_rows(table)
#print(table_rows)

def save_as_csv(table_name, headers, rows):
    pd.DataFrame(rows, columns=headers).to_csv(f"{table_name}.csv")

save_as_csv("Test_table", head, table_rows)

Post a Comment for "Converting A HTML Table To A CSV In Python"

Menu Halaman Statis

© 2022 - Html5 Tutorial