Created
May 26, 2015 18:25
-
-
Save arafsheikh/6ae88c6118090bc0e415 to your computer and use it in GitHub Desktop.
Scraper written in Python using Mechanize and BeautifulSoup (4632700)
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 mechanize import Browser | |
| import mechanize | |
| from bs4 import BeautifulSoup | |
| def getRoll(): | |
| global base | |
| base += 1 | |
| return str(base) | |
| def main(): | |
| roll = '4632719' | |
| browser = Browser() | |
| browser.set_handle_robots(False) | |
| browser.addheaders = [('User-agent', 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.1) Gecko/2008071615 Fedora/3.0.1-1.fc9 Firefox/3.0.1')] | |
| browser.open('http://cbseresults.nic.in/class12/cbse122015_all.htm') | |
| f = open('Name.txt', 'a') | |
| while True: | |
| roll = getRoll() | |
| print roll | |
| browser.select_form(nr=0) | |
| browser.form['regno'] = roll | |
| res = browser.submit() | |
| soup = BeautifulSoup(res.read()) | |
| name = soup.find_all('td')[10].text | |
| name = str(name) | |
| mother = soup.find_all('td')[12].text | |
| mother = str(mother) | |
| father = soup.find_all('td')[14].text | |
| father = str(father) | |
| f.write(roll) | |
| f.write(' : ') | |
| f.write(name) | |
| f.write(' : ') | |
| f.write(mother) | |
| f.write(' : ') | |
| f.write(father) | |
| f.write('\n') | |
| browser.back() | |
| if __name__ == '__main__': | |
| base = 4632000 | |
| main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment