gpt2-urls.py

#!/usr/bin/env python3

import re
import json
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
import numpy as np
import tensorflow as tf

import sys
sys.path.insert(0, 'gpt-2/src/')

import model, sample, encoder

import requests
from timeit import default_timer as timer

tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.ERROR)

def generate_chunks():
    """
    Interactively run the model
    :model_name=124M : String, which model to use
    :seed=None : Integer seed for random number generators, fix seed to reproduce
     results
    :nsamples=1 : Number of samples to return total
    :batch_size=1 : Number of batches (only affects speed/memory).  Must divide nsamples.
    :length=None : Number of tokens in generated text, if None (default), is
     determined by model hyperparameters
    :temperature=1 : Float value controlling randomness in boltzmann
     distribution. Lower temperature results in less random completions. As the
     temperature approaches zero, the model will become deterministic and
     repetitive. Higher temperature results in more random completions.
    :top_k=0 : Integer value controlling diversity. 1 means only 1 word is
     considered for each step (token), resulting in deterministic completions,
     while 40 means 40 words are considered at each step. 0 (default) is a
     special setting meaning no restrictions. 40 generally is a good value.
    :models_dir : path to parent folder containing model subfolders
     (i.e. contains the <model_name> folder)
    """
    model_name='124M'
    seed=1
    nsamples=1000
    batch_size=1
    length=25
    temperature=1
    top_k=0
    top_p=1
    models_dir='gpt-2/models'

    models_dir = os.path.expanduser(os.path.expandvars(models_dir))
    assert nsamples % batch_size == 0

    enc = encoder.get_encoder(model_name, models_dir)
    hparams = model.default_hparams()
    with open(os.path.join(models_dir, model_name, 'hparams.json')) as f:
        hparams.override_from_dict(json.load(f))
    
    with tf.Session(graph=tf.Graph()) as sess:
        context = tf.placeholder(tf.int32, [batch_size, None])
        np.random.seed(seed)
        tf.set_random_seed(seed)
        output = sample.sample_sequence(
            hparams=hparams, length=length,
            context=context,
            batch_size=batch_size,
            temperature=temperature, top_k=top_k, top_p=top_p
        )

        saver = tf.train.Saver()
        ckpt = tf.train.latest_checkpoint(os.path.join(models_dir, model_name))
        saver.restore(sess, ckpt)

        chunks = []
        context_tokens = enc.encode("http://")
        generated = 0
        for _ in range(nsamples // batch_size):
            start = timer()
            out = sess.run(output, feed_dict={
                context: [context_tokens for _ in range(batch_size)]
            })[:, len(context_tokens):]
            for i in range(batch_size):
                generated += 1
                text = enc.decode(out[i])
                chunks.append("http://" + text)
            end = timer()
            print(end-start)
    return chunks

def refine_chunks(chunks):
    url_re = re.compile(r'https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%_\+.~#?&//=]*)')
    for i in range(len(chunks)):
        try:
            chunks[i] = url_re.search(chunks[i]).group(0)
        except:
            chunks[i] = None
    return chunks

def get_code(url):
    try:
        if url is not None:
            r = requests.head(url, timeout=1).status_code
        else:
            r = -1
    except:
        r = -1

    return r

def test_urls(urls):
    return {k: get_code(k) for k in urls}

if __name__ == '__main__':
    with open('result.json', 'w') as fp:
        json.dump(test_urls(refine_chunks(generate_chunks())), fp)