Scraping names of participants in a class from a raw HTML dump.

name-scraper.py

from bs4 import BeautifulSoup
import re # Regular Expressions
import collections # Data Types
import sys # File operations
import codecs # UniCode support

def scrape(page):
  # Dump raw HTML into Soup
  raw_data = codecs.open(page, 'r', encoding='utf-8').read()
	soup = BeautifulSoup(raw_data)

  # Build a list of cells containing the name
	lines = [line.find('a') for line in soup.find_all('td', 'cell c1')] # Specifics vary

	students = []

	for link in lines:
		line_soup = BeautifulSoup(str(link).encode('utf-8'))
		student = line_soup.get_text()
		if not re.match('[\d]', student): # Exclude zombie members with numbers in their names
			students.append(student)
	
	return students

if __name__ == '__main__':
	page = '/file_dir/file_name.html'
	print scrape(page)