Last active
August 11, 2017 10:25
-
-
Save kartikv11/5a72d06e3bbd7e6b4ad3bbd36939d9ba to your computer and use it in GitHub Desktop.
Example of parsing/scraping data[with Proxy] for All Doctors using BeautifulSoup. Source used here: https://old.mciindia.org [NOTE: Please control Threads as per your Proxy Restrictions]
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
import requests | |
from bs4 import BeautifulSoup | |
import sys | |
import json | |
import threading | |
import re | |
import time | |
import os | |
proxies = { | |
'http': '<give http proxy here>', | |
'https': '<give https proxy here>' | |
} | |
class writeDocDetailThread (threading.Thread): | |
def __init__(self, index, limit): | |
super(writeDocDetailThread, self).__init__() | |
self.index = index | |
self.limit = limit | |
def run(self): | |
try: | |
log_doc_details(self.index, self.limit) | |
except: | |
print("Unexpected error : {:s} at {:s}.".format(str(sys.exc_info()[0].__name__), str(sys.exc_info()[2].tb_lineno))) | |
class doctorsListThread (threading.Thread): | |
def __init__(self, startingIndex): | |
super(doctorsListThread, self).__init__() | |
self.startingIndex = startingIndex | |
def run(self): | |
try: | |
get_doctors_detail(self.startingIndex) | |
except: | |
print("Unexpected error : {:s} at {:s}.".format(str(sys.exc_info()[0].__name__), str(sys.exc_info()[2].tb_lineno))) | |
def get_doctors_detail(startingIndex): | |
if startingIndex != 1: | |
startingLimit = (startingIndex - 1) * 1000 | |
else: | |
startingLimit = 1 | |
upperLimit = startingIndex * 1000 | |
try: | |
for i in range(startingLimit, upperLimit + 1): | |
writeDocDetail = writeDocDetailThread(i, upperLimit) | |
writeDocDetail.run() | |
print "Logging: {} , Upper: {}".format(i, upperLimit) | |
except: | |
print("Unexpected error : {:s} at {:s}.".format(str(sys.exc_info()[0].__name__), | |
str(sys.exc_info()[2].tb_lineno))) | |
def log_doc_details(index, limit): | |
url_to_scrape = 'https://old.mciindia.org/ViewDetails.aspx?ID={}'.format(index) | |
r = requests.get(url_to_scrape,proxies=proxies) | |
soup = BeautifulSoup(r.text, "html.parser") | |
doc_detailed_data = {} | |
try: | |
doc_detailed_data['Name'] = soup.find("span", {"id": "Name"}).text | |
doc_detailed_data['FatherName'] = soup.find("span", {"id": "FatherName"}).text | |
doc_detailed_data['YearOfInfo'] = soup.find("span", {"id": "lbl_Info"}).text | |
doc_detailed_data['RegistrationNo'] = soup.find("span", {"id": "Regis_no"}).text | |
doc_detailed_data['DateOfReg'] = soup.find("span", {"id": "Date_Reg"}).text | |
doc_detailed_data['StateMedicalCouncil'] = soup.find("span", {"id": "Lbl_Council"}).text | |
doc_detailed_data['Qualification'] = soup.find("span", {"id": "Qual"}).text | |
doc_detailed_data['QualificationYear'] = soup.find("span", {"id": "QualYear"}).text | |
doc_detailed_data['University'] = soup.find("span", {"id": "Univ"}).text | |
doc_detailed_data['Address'] = soup.find("span", {"id": "Address"}).text | |
except: | |
pass | |
fileName = "doc_details_{}".format(limit) | |
with open('/home/ubuntu/doctors_data/raw_files/{}.txt'.format(fileName),'a') as f: | |
f.write(json.dumps(doc_detailed_data)) | |
if __name__ == "__main__": | |
count = 0 | |
for i in range(1, 1001): | |
count += 1 | |
print "Iteration: {}x1000entries (1000 iterations)".format(count) | |
if count%50 == 0: | |
time.sleep(10) | |
doctorsListFetch = doctorsListThread(i) | |
doctorsListFetch.start() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment