theSage21

#Todo

• attendance/home.html
• principal_home.html
• notice_view.html
• notice_home.html
• event.html
• department.html
• contact.html
• archive.html
• alumni.html

theSage21

import os
import re
from bs4 import BeautifulSoup


def get_files():
    folder = os.path.join(os.getcwd(), 'html')
    names = [os.path.join(folder, i) for i in os.listdir(folder)]
    names.sort()
    return names

theSage21

#! /bin/bash


echo Creating directory
mkdir $1


# copy standard project stuff
echo Copying License
lic=$1/LICENSE

theSage21

from requests import post


def save_page(html):
    f = open('html/' + str(hash(html)), 'w')
    f.write(html)
    f.close()


def mark_done(roll):

theSage21

from bs4 import BeautifulSoup as BS
from urllib2 import urlopen
html = urlopen('https://in.pycon.org/cfp/pycon-india-2015/proposals/')
html = ''.join(html.readlines())
html[:30]
soup = BS(html)
soup.find_all('div',{'class':'user-proposals'})
proposals=soup.find_all('div',{'class':'user-proposals'})
ordered = []
for p in proposals:

theSage21

from time import time

# dummy functions
def html_minify(content, ignore_comments, parser):
    "Constant time function"
    return content

class Request:
    def __init__(self):
        self._hit_htmlmin = True

theSage21

class Primer:
    def __init__(self, store_name='data'):
        self.store_name = store_name
        try:
            fl = open(self.store_name, 'r')
            fl.close()
        except:
            with open(self.store_name, 'w') as fl:
                fl.write('2\n')

theSage21

Wrote profile results to testing.py.lprof
Timer unit: 1e-06 s

Total time: 18.9654 s
File: html2text/__init__.py
Function: optwrap at line 784

Line #      Hits         Time  Per Hit   % Time  Line Contents
==============================================================
   784                                               @profile

theSage21

Wrote profile results to testing.py.lprof
Timer unit: 1e-06 s

Total time: 0.001185 s
File: html2text/__init__.py
Function: feed at line 121

Line #      Hits         Time  Per Hit   % Time  Line Contents
==============================================================
   121                                               @profile

theSage21

import os
from requests import get
from hashlib import md5


urls = ['http://ststephens.edu/',
        'http://cmi.ac.in/']

try:
    with open('.website_signatures', 'r') as fl: