I managed to extract data successfully from the given website . I created an excel file with the information for one product. However, when trying to scrape data for a second product, I encountered issues adding another sheet to the existing excel file. Any guidance on this matter would be greatly appreciated. Thank you in advance. Here is my code snippet: -
from selenium import webdriver
import time, re
from selenium.webdriver.support.ui import Select
from bs4 import BeautifulSoup
import pandas as pd
from selenium import webdriver
import time
chrome_path = r"C:\Users\user\Desktop\chromedriver_win32\chromedriver.exe"
driver = webdriver.Chrome(chrome_path)
driver.get("https://fcainfoweb.nic.in/Reports/Report_Menu_Web.aspx")
html_source = driver.page_source
results=[]
driver.find_element_by_xpath("""//*[@id="ctl00_MainContent_Rbl_Rpt_type_1"]""").click()
element_variation = driver.find_element_by_id ("ctl00_MainContent_Ddl_Rpt_Option1")
drp_variation = Select(element_variation)
drp_variation.select_by_visible_text("Daily Variation")
driver.find_element_by_id("ctl00_MainContent_Txt_FrmDate").send_keys("01/05/2020")
driver.find_element_by_id("ctl00_MainContent_Txt_ToDate").send_keys("27/05/2020")
element_commodity = driver.find_element_by_id ("ctl00_MainContent_Lst_Commodity")
drp_commodity = Select(element_commodity)
drp_commodity.select_by_visible_text("Rice")
driver.find_element_by_xpath("""//*[@id="ctl00_MainContent_btn_getdata1"]""").click()
soup = BeautifulSoup(driver.page_source, 'html.parser')
table = pd.read_html(driver.page_source)[2] #second table is the one that we want
print(len(table))
print(table)
results.append(table)
driver.back()
time.sleep(1)
with pd.ExcelWriter(r'C:\Users\user\Desktop\python.xlsx') as writer:
table.to_excel(writer, sheet_name = "rice", index=False) # Rice results on sheet named rice
writer.save()
driver.find_element_by_xpath("""//*[@id="btn_back"]""").click()
driver.find_element_by_xpath("""//*[@id="ctl00_MainContent_Rbl_Rpt_type_1"]""").click()
element_variation = driver.find_element_by_id ("ctl00_MainContent_Ddl_Rpt_Option1")
drp_variation = Select(element_variation)
drp_variation.select_by_visible_text("Daily Variation")
driver.find_element_by_id("ctl00_MainContent_Txt_FrmDate").send_keys("01/05/2020")
driver.find_element_by_id("ctl00_MainContent_Txt_ToDate").send_keys("27/05/2020")
element_commodity = driver.find_element_by_id ("ctl00_MainContent_Lst_Commodity")
drp_commodity = Select(element_commodity)
drp_commodity.select_by_visible_text("Wheat")
driver.find_element_by_xpath("""//*[@id="ctl00_MainContent_btn_getdata1"]""").click()
soup = BeautifulSoup(driver.page_source, 'html.parser')
table = pd.read_html(driver.page_source)[2] #second table is the one that we want
print(len(table))
print(table)
results.append(table)
driver.back()
time.sleep(1)
with pd.ExcelWriter(r'C:\Users\user\Desktop\python.xlsx') as writer:
table.to_excel(writer, sheet_name = "wheat", index=False) # Wheat results on sheet named wheat
writer.save()