arowser’s gists

arowser / objectifiedJson.py

Created March 30, 2013 23:15 — forked from aisipos/objectifiedJson.py

	import simplejson as json
	import lxml

	class objectJSONEncoder(json.JSONEncoder):
	"""A specialized JSON encoder that can handle simple lxml objectify types
	>>> from lxml import objectify
	>>> obj = objectify.fromstring("<Book><price>1.50</price><author>W. Shakespeare</author></Book>")
	>>> objectJSONEncoder().encode(obj)
	'{"price": 1.5, "author": "W. Shakespeare"}'
	"""

arowser / github-scrape.py

Created January 19, 2013 00:20 — forked from ngsankha/github-scrape.py

	import csv, httplib, json
	from string import ascii_lowercase

	con = httplib.HTTPSConnection('api.github.com')
	languages = ['java', 'c', 'ruby', 'python', 'javascript']
	for lang in languages:
	with open(lang + '.csv', 'wb') as csvfile:
	csvwriter = csv.writer(csvfile, delimiter = ',', quotechar='"', quoting = csv.QUOTE_MINIMAL)
	for ch in ascii_lowercase:
	print("Processing repos with " + ch + " for language " + lang)

arowser / gist:4274008

Created December 13, 2012 04:20 — forked from feilaoda/gist:4043549

	from gcrawler import GCrawler, Downloader
	import unittest
	import urllib2
	import logging
	import traceback
	from datetime import datetime
	import re

	logging.basicConfig(level=logging.DEBUG)

arowser / onverting HTML to Plain Text

Created December 7, 2012 08:18

onverting HTML to Plain Text

	import re

	##
	# Removes HTML markup from a text string.
	#
	# @param text The HTML source.
	# @return The plain text. If the HTML source contains non-ASCII
	# entities or character references, this is a Unicode string.

	def strip_html(text):

arowser / weibo_nooauth.py

Created November 24, 2012 02:44 — forked from stephenLee/weibo_nooauth.py

weibo_login script

	#!/usr/bin/env python
	#coding=utf8
	import urllib
	import urllib2
	import cookielib
	import base64
	import re
	import json
	import hashlib
	import os

arowser / gist:4133773

Created November 23, 2012 02:33 — forked from observerss/gist:3798922

Google Keyword Tool Scraper(casperjs version)

	// requires
	var utils = require('utils');
	var casper = require('casper').create()
	var casper = require('casper').create({
	verbose: true,
	logLevel: "debug"
	});

	// setup globals
	var email = casper.cli.options['email'] \|\| 'REPLACE THIS EMAIL';

arowser / gist:4133771

Created November 23, 2012 02:32 — forked from observerss/gist:3798896

Google Keyword Tool Scraper(selenium+python version)

	from selenium import webdriver
	from selenium.common.exceptions import TimeoutException
	import selenium.webdriver.support.wait
	selenium.webdriver.support.wait.POLL_FREQUENCY = 0.05

	import re
	import random
	import collections

	class AdwordsAutomater(object):

arowser / pythons

Created November 22, 2012 03:04 — forked from flufy3d/pythons

capture for http://simplecd.me/entry/L1Z9ddOT/

	#coding=utf-8
	from datetime import datetime
	import os
	import re
	import urllib.request
	from html.parser import HTMLParser
	from time import sleep

	import socket
	socket.setdefaulttimeout(60)

arowser / pytesser

Created November 22, 2012 02:58

pytesser example

	#!/usr/bin/env python
	#-- coding: UTF-8 --
	# filename: AutoLogin.py

	from __future__ import unicode_literals
	import urllib2
	import cookielib
	import urllib
	import Image
	from cStringIO import StringIO

arowser / guokr.json

Created November 20, 2012 07:21 — forked from leecade/guokr.json

json:guokr

{"hotsite":{"name":"热门网站","links":[{"name":"科学松鼠会","url":"http://songshuhui.net/","ico_url":"http://img1.guokr.com/gkimage/hf/9z/cy/hf9zcy.png","style":"","ico":""},{"name":"科学网","url":"http://www.sciencenet.cn/","ico_url":"http://img1.guokr.com/gkimage/ix/ep/rw/ixeprw.png","style":"","ico":""},{"name":"丁香园","url":"http://www.dxy.cn/","ico_url":"http://img1.guokr.com/gkimage/cu/m5/vf/cum5vf.png","style":"","ico":""},{"name":"PubMed","url":"http://www.ncbi.nlm.nih.gov/pubmed","ico_url":"http://img1.guokr.com/gkimage/2o/wv/mt/2owvmt.png","style":"","ico":""},{"name":"趣玩网","url":"http://www.quwan.com/","ico_url":"http://img1.guokr.com/gkimage/rr/50/0c/rr500c.png","style":"","ico":""},{"name":"穷游网","url":"http://www.qyer.com/","ico_url":"http://img1.guokr.com/gkimage/ym/6h/ne/ym6hne.png","style":"","ico":""},{"name":"糗事百科","url":"http://www.qiushibaike.com/","ico_url":"http://img1.guokr.com/gkimage/iz/cv/jx/izcvjx.png","style":"","ico":""},{"name":"36氪","url":"http://www.36kr.com/","ico_url":"http://img1.guokr.co