python BeautifulSoup parsing table
PythonBeautifulsoupPython Problem Overview
I'm learning python requests
and BeautifulSoup. For an exercise, I've chosen to write a quick NYC parking ticket parser. I am able to get an html response which is quite ugly. I need to grab the lineItemsTable
and parse all the tickets.
You can reproduce the page by going here: https://paydirect.link2gov.com/NYCParking-Plate/ItemSearch
and entering a NY
plate T630134C
soup = BeautifulSoup(plateRequest.text)
#print(soup.prettify())
#print soup.find_all('tr')
table = soup.find("table", { "class" : "lineItemsTable" })
for row in table.findAll("tr"):
cells = row.findAll("td")
print cells
Can someone please help me out? Simple looking for all tr
does not get me anywhere.
Python Solutions
Solution 1 - Python
Here you go:
data = []
table = soup.find('table', attrs={'class':'lineItemsTable'})
table_body = table.find('tbody')
rows = table_body.find_all('tr')
for row in rows:
cols = row.find_all('td')
cols = [ele.text.strip() for ele in cols]
data.append([ele for ele in cols if ele]) # Get rid of empty values
This gives you:
[ [u'1359711259', u'SRF', u'08/05/2013', u'5310 4 AVE', u'K', u'19', u'125.00', u'$'],
[u'7086775850', u'PAS', u'12/14/2013', u'3908 6th Ave', u'K', u'40', u'125.00', u'$'],
[u'7355010165', u'OMT', u'12/14/2013', u'3908 6th Ave', u'K', u'40', u'145.00', u'$'],
[u'4002488755', u'OMT', u'02/12/2014', u'NB 1ST AVE @ E 23RD ST', u'5', u'115.00', u'$'],
[u'7913806837', u'OMT', u'03/03/2014', u'5015 4th Ave', u'K', u'46', u'115.00', u'$'],
[u'5080015366', u'OMT', u'03/10/2014', u'EB 65TH ST @ 16TH AV E', u'7', u'50.00', u'$'],
[u'7208770670', u'OMT', u'04/08/2014', u'333 15th St', u'K', u'70', u'65.00', u'$'],
[u'$0.00\n\n\nPayment Amount:']
]
Couple of things to note:
- The last row in the output above, the Payment Amount is not a part of the table but that is how the table is laid out. You can filter it out by checking if the length of the list is less than 7.
- The last column of every row will have to be handled separately since it is an input text box.
Solution 2 - Python
Updated Answer
If a programmer is interested in only parsing a table from a webpage, they can utilize the pandas method pandas.read_html
.
Let's say we want to extract the GDP data table from the website: https://worldpopulationreview.com/countries/countries-by-gdp/#worldCountries
Then following codes does the job perfectly (No need of beautifulsoup and fancy html):
Using pandas only
# sometimes we can directly read from the website
url = "https://en.wikipedia.org/wiki/AFI%27s_100_Years...100_Movies#:~:text=%20%20%20%20Film%20%20%20,%20%204%20%2025%20more%20rows%20"
df = pd.read_html(url)
df.head()
Using pandas and requests (More General Case)
# if pd.read_html does not work, we can use pd.read_html using requests.
import pandas as pd
import requests
url = "https://worldpopulationreview.com/countries/countries-by-gdp/#worldCountries"
r = requests.get(url)
df_list = pd.read_html(r.text) # this parses all the tables in webpages to a list
df = df_list[0]
df.head()
Required modules
pip install lxml
pip install requests
pip install pandas
Output
Solution 3 - Python
Solved, this is how your parse their html results:
table = soup.find("table", { "class" : "lineItemsTable" })
for row in table.findAll("tr"):
cells = row.findAll("td")
if len(cells) == 9:
summons = cells[1].find(text=True)
plateType = cells[2].find(text=True)
vDate = cells[3].find(text=True)
location = cells[4].find(text=True)
borough = cells[5].find(text=True)
vCode = cells[6].find(text=True)
amount = cells[7].find(text=True)
print amount
Solution 4 - Python
Here is working example for a generic <table>
. (question links-broken)
Extracting the table from here countries by GDP (Gross Domestic Product).
htmltable = soup.find('table', { 'class' : 'table table-striped' })
# where the dictionary specify unique attributes for the 'table' tag
The tableDataText
function parses a html segment started with tag <table>
followed by multiple <tr>
(table rows) and inner <td>
(table data) tags. It returns a list of rows with inner columns. Accepts only one <th>
(table header/data) in the first row.
def tableDataText(table):
rows = []
trs = table.find_all('tr')
headerow = [td.get_text(strip=True) for td in trs[0].find_all('th')] # header row
if headerow: # if there is a header row include first
rows.append(headerow)
trs = trs[1:]
for tr in trs: # for every table row
rows.append([td.get_text(strip=True) for td in tr.find_all('td')]) # data row
return rows
Using it we get (first two rows).
list_table = tableDataText(htmltable)
list_table[:2]
[['Rank', 'Name', "GDP (IMF '19)", "GDP (UN '16)", 'GDP Per Capita', '2019 Population'],
['1', 'United States', '21.41 trillion', '18.62 trillion', '$65,064', '329,064,917']]
That can be easily transformed in a pandas.DataFrame
for more advanced tools.
import pandas as pd
dftable = pd.DataFrame(list_table[1:], columns=list_table[0])
dftable.head(4)
Solution 5 - Python
from behave import *
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as ec
import pandas as pd
import requests
from bs4 import BeautifulSoup
from tabulate import tabulate
class readTableDataFromDB:
def LookupValueFromColumnSingleKey(context, tablexpath, rowName, columnName):
print("element present readData From Table")
element = context.driver.find_elements_by_xpath(tablexpath+"/descendant::th")
indexrow = 1
indexcolumn = 1
for values in element:
valuepresent = values.text
print("text present here::"+valuepresent+"rowName::"+rowName)
if valuepresent.find(columnName) != -1:
print("current row"+str(indexrow) +"value"+valuepresent)
break
else:
indexrow = indexrow+1
indexvalue = context.driver.find_elements_by_xpath(
tablexpath+"/descendant::tr/td[1]")
for valuescolumn in indexvalue:
valuepresentcolumn = valuescolumn.text
print("Team text present here::" +
valuepresentcolumn+"columnName::"+rowName)
print(indexcolumn)
if valuepresentcolumn.find(rowName) != -1:
print("current column"+str(indexcolumn) +
"value"+valuepresentcolumn)
break
else:
indexcolumn = indexcolumn+1
print("index column"+str(indexcolumn))
print(tablexpath +"//descendant::tr["+str(indexcolumn)+"]/td["+str(indexrow)+"]")
#lookupelement = context.driver.find_element_by_xpath(tablexpath +"//descendant::tr["+str(indexcolumn)+"]/td["+str(indexrow)+"]")
#print(lookupelement.text)
return context.driver.find_elements_by_xpath(tablexpath+"//descendant::tr["+str(indexcolumn)+"]/td["+str(indexrow)+"]")
def LookupValueFromColumnTwoKeyssss(context, tablexpath, rowName, columnName, columnName1):
print("element present readData From Table")
element = context.driver.find_elements_by_xpath(
tablexpath+"/descendant::th")
indexrow = 1
indexcolumn = 1
indexcolumn1 = 1
for values in element:
valuepresent = values.text
print("text present here::"+valuepresent)
indexrow = indexrow+1
if valuepresent == columnName:
print("current row value"+str(indexrow)+"value"+valuepresent)
break
for values in element:
valuepresent = values.text
print("text present here::"+valuepresent)
indexrow = indexrow+1
if valuepresent.find(columnName1) != -1:
print("current row value"+str(indexrow)+"value"+valuepresent)
break
indexvalue = context.driver.find_elements_by_xpath(
tablexpath+"/descendant::tr/td[1]")
for valuescolumn in indexvalue:
valuepresentcolumn = valuescolumn.text
print("Team text present here::"+valuepresentcolumn)
print(indexcolumn)
indexcolumn = indexcolumn+1
if valuepresent.find(rowName) != -1:
print("current column"+str(indexcolumn) +
"value"+valuepresentcolumn)
break
print("indexrow"+str(indexrow))
print("index column"+str(indexcolumn))
lookupelement = context.driver.find_element_by_xpath(
tablexpath+"//descendant::tr["+str(indexcolumn)+"]/td["+str(indexrow)+"]")
print(tablexpath +
"//descendant::tr["+str(indexcolumn)+"]/td["+str(indexrow)+"]")
print(lookupelement.text)
return context.driver.find_element_by_xpath(tablexpath+"//descendant::tr["+str(indexrow)+"]/td["+str(indexcolumn)+"]")