Skip to content

Instantly share code, notes, and snippets.

[
{
"_id": "58d5c70c27ea7d070060160e",
"categories": [
"55de81ac9d1fa51000f94770",
"55de81929d1fa51000f94769",
"55de81879d1fa51000f94766"
],
"coverImage": {
"_id": "58f318cc4909c907004ac575",
import requests
import time
from bs4 import BeautifulSoup
def get_web_page(url):
resp = requests.get(
url=url,
cookies={'over18': '1'}
)
[
{
"href": "/bbs/Beauty/M.1482072854.A.DDC.html",
"num_image": 3,
"push_count": 18,
"title": "[神人] 長榮空姐"
},
{
"href": "/bbs/Beauty/M.1482075654.A.C1D.html",
"num_image": 7,
import json
import math
from collections import Counter
from matplotlib import pyplot as plt
def mean(x):
return sum(x) / len(x)
from bs4 import BeautifulSoup
html_doc = """
<html>
<head>
<title>我是網頁標題</title>
<style>
.large {
color:blue;
text-align: center;
beautifulsoup4
cycler
matplotlib
numpy
pyparsing
python-dateutil
pytz
requests
six
import os, json
from bs4 import BeautifulSoup
import preprocess
if __name__ == '__main__':
current_dir = os.path.dirname(__file__)
form_dir = os.path.join(current_dir, 'forms')
input_dir = os.path.join(current_dir, 'corpus', 'all-input')
input_types = ['text', 'email', 'password']
#!/usr/bin/python
# -*- coding: utf-8 -*-
"""
Extract features from htmls
"""
import sys, os, random, datetime
from bs4 import BeautifulSoup
from preprocess import extract_features