alex2awesome alex2awesome
Smerity
/ fetch_page.py
Created
August 7, 2015 21:30
An example of fetching a page from Common Crawl using the Common Crawl Index
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 gzip | |
| import json | |
| import requests | |
| try: | |
| from cStringIO import StringIO | |
| except: | |
| from StringIO import StringIO | |
| # Let's fetch the Common Crawl FAQ using the CC index | |
| resp = requests.get('http://index.commoncrawl.org/CC-MAIN-2015-27-index?url=http%3A%2F%2Fcommoncrawl.org%2Ffaqs%2F&output=json') |
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
| """ | |
| This is a batched LSTM forward and backward pass | |
| """ | |
| import numpy as np | |
| import code | |
| class LSTM: | |
| @staticmethod | |
| def init(input_size, hidden_size, fancy_forget_bias_init = 3): |