Created
January 17, 2020 14:14
-
-
Save nandini-menon/eaad3c8c86effc6c7c23175fe812a9b8 to your computer and use it in GitHub Desktop.
To get the details of all faculties in colleges registered with AICTE
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 csv | |
from selenium import webdriver | |
from selenium.webdriver.common.by import By | |
def main(): | |
id_list = list() | |
name_list = list() | |
with open('institute_list.csv', 'r') as csv_file: | |
csv_reader = csv.reader(csv_file, delimiter=',') | |
for lines in csv_reader: | |
id_list.append(lines[0]) | |
name_list.append(lines[1]) | |
f = open('faculty_details.csv', 'w') | |
driver = webdriver.Chrome() | |
for college_id in id_list: | |
index = id_list.index(college_id) | |
url = 'http://www.knowyourcollege-gov.in/facultyDetails.php?insti_id=' + college_id | |
driver.get(url) | |
rows = driver.find_elements_by_xpath('//div[@class="CSSTableGenerator"]/table/tbody/tr') | |
row_num = len(rows) - 1 | |
for i in range (2, row_num + 1): | |
name_xpath = '//*[@id="institute-detail"]/div[2]/table/tbody/tr[' + str(i) + ']/td[2]' | |
email_xpath = '//*[@id="institute-detail"]/div[2]/table/tbody/tr[' + str(i) + ']/td[4]/a' | |
subject_xpath = '//*[@id="institute-detail"]/div[2]/table/tbody/tr[' + str(i) + ']/td[7]' | |
name = driver.find_element_by_xpath(name_xpath).text | |
email = driver.find_element_by_xpath(email_xpath).text | |
subject = driver.find_element_by_xpath(subject_xpath).text | |
f.write(name + ', ' + email + ', ' + subject + ', ' + name_list[index] + '\n') | |
driver.close() | |
f.close() | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment