Created
April 30, 2021 06:12
-
-
Save harishsg99/3c5ce07908b6b4a601c7f4a543341066 to your computer and use it in GitHub Desktop.
Script to scrape tn govt website
This file contains 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 autoscraper import AutoScraper | |
import pandas as pd | |
import json | |
import csv | |
url = 'https://stopcorona.tn.gov.in/beds.php' | |
wanted_list = ["Ariyalur","District","COVID BEDS","Sai Fertility Centre & Hospital, Vedhachalam Nagar","9941550979","8"] | |
scraper = AutoScraper() | |
result = scraper.build(url, wanted_list) | |
t = scraper.get_result_similar(url, grouped=True) | |
json_object = json.dumps(t) | |
print(json_object) | |
with open("sample.json", "w") as outfile: | |
outfile.write(json_object) | |
with open('sample.json') as json_file: | |
data = json.load(json_file) | |
employee_data = data['emp_details'] | |
data_file = open('data_file.csv', 'w') | |
csv_writer = csv.writer(data_file) | |
count = 0 | |
for emp in employee_data: | |
if count == 0: | |
# Writing headers of CSV file | |
header = emp.keys() | |
csv_writer.writerow(header) | |
count += 1 | |
# Writing data of CSV file | |
csv_writer.writerow(emp.values()) | |
data_file.close() | |
df = pd.read_csv("data_file.csv") | |
df.drop_duplicates(keep=False,inplace=True) | |
df.to_csv('scrapedcovid_data.csv', index = True) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment