I'm learning web scraping and found a fun challenge scraping a Javascript handlebars table from this page: Samsung Knox Devices
I eventually got the output I wanted, but I think it feels "hacky", so I'd appreciate any refinements to make it more elegant.
Desired output is a dataframe/csv table with columns = Device, Model_Nums, OS/Platform, Knox Version. Don't need anything else on the page, and I will split/expand and melt the Model Nums separately.
import pandas as pd
# Libraries for this task:
from bs4 import BeautifulSoup
from selenium import webdriver
# Because the target table is built using Javascript handlebars, we have to use Selenium and a webdriver
driver = webdriver.Edge("MY_PATH") # REPLACE WITH >YOUR< PATH!
# Point the driver at the target webpage:
driver.get('https://www.samsungknox.com/en/knox-platform/supported-devices')
# Get the page content
html = driver.page_source
# Typically I'd do something like: soup = BeautifulSoup(html, "lxml")
# Link below suggested the following, which works; I don't know if it matters
sp = BeautifulSoup(html, "html.parser")
# The 'table here is really a bunch of nested divs
tables = soup.find_all("div", class_='table-row')
# https://www.angularfix.com/2021/09/how-to-extract-text-from-inside-div-tag.html
rows = []
for t in tables:
row = t.text
rows.append(row)
# These are the table-row div classes within each table-row from the output at the previous step that I want:
# div class="supported-devices pivot-fixed"
# div class="model"
# div class="operating system"
# div class="knox-version"
# Define div class names:
targets = ["supported-devices pivot-fixed", "model", "operating-system", "knox-version"]
# Create an empty list and loop through each target div class; append to list
data = []
for t in targets:
hold = sp.find_all("div", class_=t)
for h in hold:
row = h.text
data.append({'column': t, 'value': row})
df = pd.DataFrame(data)
# This feels like a hack, but I got stuck and it works, so \shrug/
# Create Series from filtered df based on 'column' value (corresponding to the the four "targets" above)
name = pd.Series(df['value'][df['column']=='supported-devices pivot-fixed']).reset_index(drop=True)
model = pd.Series(df['value'][df['column']=='model']).reset_index(drop=True)
os = pd.Series(df['value'][df['column']=='operating-system']).reset_index(drop=True)
knox = pd.Series(df['value'][df['column']=='knox-version']).reset_index(drop=True)
# Concatenate Series into df
df2 = pd.concat([df_name, df_model, df_os, df_knox], axis=1)
# Make the first row the column names:
new_header = df2.iloc[0] #grab the first row for the header
sam_knox_table = df2[1:] #take the data less the header row
sam_knox_table.columns = new_header #set the header row as the df header
# Bob's your uncle
sam_knox_table.to_csv('sam_knox.csv', index=False)
