| ~$sudo pip install django --upgrade | |
| Downloading/unpacking django | |
| Downloading Django-1.2.5.tar.gz (6.4Mb): 6.4Mb downloaded | |
| Running setup.py egg_info for package django | |
| Installing collected packages: django | |
| Running setup.py install for django | |
| Traceback (most recent call last): | |
| File "<string>", line 1, in <module> | |
| File "/Users/arihershowitz/build/django/setup.py", line 96, in <module> | |
| 'Topic :: Software Development :: Libraries :: Python Modules', |
| /** | |
| * npm install jsdom | |
| * npm install jquery | |
| */ | |
| var html = "<!doctype html><html><body><h1>Hello world!</h1></body></html>"; | |
| /* parse the html and create a dom window */ | |
| var window = require('jsdom').jsdom(html, null, { | |
| // standard options: disable loading other assets |
| // ==UserScript== | |
| // @name Jureeka | |
| // @namespace http://www.jureeka.org | |
| // @description Turns legal citations in webpages into hyperlinks that direct you to online legal source material. | |
| // ==/UserScript== | |
| /* | |
| Warnings: | |
| * This triggers a memory leak bug in Firefox. |
| //------------------------------------------------------------------------------ | |
| // <auto-generated> | |
| // This code was generated by a tool. | |
| // Runtime Version:2.0.50727.4206 | |
| // | |
| // Changes to this file may cause incorrect behavior and will be lost if | |
| // the code is regenerated. | |
| // </auto-generated> | |
| //------------------------------------------------------------------------------ |
| PART 10--PRACTICE BEFORE THE INTERNAL REVENUE SERVICE | |
| Sec. 10.0 Scope of part. | |
| (a) This part contains rules governing the recognition of | |
| attorneys, certified public accountants, enrolled agents, enrolled | |
| retirement plan agents, registered tax return preparers, and other | |
| persons representing taxpayers before the Internal Revenue Service. | |
| Subpart A of this part sets forth rules relating to the authority to | |
| practice before the Internal Revenue Service; subpart B of this part | |
| prescribes the duties and restrictions relating to such practice; |
| # -*- coding: utf-8 -*- | |
| ''' | |
| Usage: | |
| >>> f = open('usc08.10') | |
| >>> x = getlines(f) | |
| >>> x.next() | |
| GPOLocatorLine(code='F', arg='5800', data=u'\r\n') | |
| >>> print x.next().data | |
| TITLE 8–ALIENS AND NATIONALITY |
| <?xml version="1.0" encoding="UTF-8"?> | |
| <xsl:stylesheet version="1.0" | |
| xmlns:xsl="http://www.w3.org/1999/XSL/Transform"> | |
| <xsl:strip-space elements="*" /> | |
| <xsl:output method="xml" version="1.0" encoding="UTF-8" indent="yes"/> | |
| <xsl:template match="node()|@*"> | |
| <xsl:copy> | |
| <xsl:apply-templates select="@*|node()"/> | |
| </xsl:copy> | |
| </xsl:template> |
| import os | |
| from lxml.html.clean import clean_html | |
| import subprocess, re | |
| def convertpdf2html(pdffilepath): | |
| subprocess.call(['pdftotext', '-layout', pdffilepath]) | |
| txtfilepath = pdffilepath[:-4] + '.txt' | |
| with open(txtfilepath, 'rb') as filename: | |
| txt = filename.read() | |
| #txt = unicode(txt, "utf-8", errors = 'ignore') |
Note: I've added one line (#375) that appends the physical path to sys.path, because the PYTHONPATH cannot be easily overridden via web.config for multiple sites. Otherwise, the wfastcgi.py is identical to the Python Tools for Visual Studio v2.0 alpha at http://pytools.codeplex.com/releases
| m = re.findall('[Ww]ords?\s+[\"\']\s*\w+\s*[\"\']\s+[Ss]hall.*?\.',x) |