jwlin

{
    "_id": "58744feda8aae907000d06c0",
    "categories": [
      "55de81ac9d1fa51000f94770",
      "55de81929d1fa51000f94769"
    ],
    "coverImage": {
      "_id": "588421e46ecf3a0700b7a31d",
      "url": "https://hahow.in/images/588421e46ecf3a0700b7a31d"
    },

jwlin

import requests


def get_web_page(url):
    resp = requests.get(
        url=url,
        cookies={'over18': '1'}
    )
    if resp.status_code != 200:
        print('Invalid url:', resp.url)

jwlin

jwlin

import requests
import json
import time
import numpy as np
import os

category = {
    '55de818a9d1fa51000f94767': '生活',
    '55de818d9d1fa51000f94768': '藝術',
    '55de819a9d1fa51000f9476b': '運動',

jwlin

def getTopic(self, ai, imgtopic, Dict): 
    # JW:　features 是準備要被預測 topic 的變數, 應該要挪到下方 prediction 開始前, 程式比較連貫
    #extrat the features of the element
    features = str(re.sub(' +', ' ', ' '.join(self.extract_features(ai, imgtopic, Dict, 1))))
    #print (features)
    
    # JW:　從這裡開始可以獨立切一個 function, 只呼叫一次, 把 train 好的 model 存起來
    #open training data file
    current_dir = os.path.dirname(_file_)
    corpus_dir = os.path.join(current_dir, 'corpus', 'all-corpus')

jwlin

#!/usr/bin/python
# -*- coding: utf-8 -*-

"""
Extract features from htmls
"""

import sys, os, random, datetime
from bs4 import BeautifulSoup
# preprocess.py 檔案在這裡

jwlin

from django.http import HttpResponse
from django.shortcuts import get_object_or_404, render
from .models import Account, Client

def show(request):
    uname = request.POST["uname"]
    if "injection" in request.POST:  
        # Use raw SQL and string concatenation, resulting in SQL injection
        accounts = Account.objects.raw(f'SELECT * FROM atm_account as a, atm_client as c WHERE a.client_id=c.id and c.username="{uname}"')    
    else:

jwlin

import requests
import time
from bs4 import BeautifulSoup
import os
import re
import urllib.request
import json


PTT_URL = 'https://www.ptt.cc'