Dragon Dave McKee scraperdragon

html5lib - ihatexml.py - line 254: DataLossWarning: Coercing non-XML name

In my case this was caused by an malformed attribute: ``

	'--- https://support.microsoft.com/en-us/kb/195763
	' NB: remove PtrSafe if old Excel
	Private Declare PtrSafe Function GetTempPath Lib "kernel32" _
	Alias "GetTempPathA" (ByVal nBufferLength As Long, _
	ByVal lpBuffer As String) As Long

	'--- https://support.microsoft.com/en-us/kb/195763
	' NB: remove PtrSafe if old Excel
	Private Declare PtrSafe Function GetTempFileName Lib "kernel32" _
	Alias "GetTempFileNameA" (ByVal lpszPath As String, _

	<html>
	<head>
	<script type="text/javascript" src="https://www.dropbox.com/static/api/2/dropins.js" id="dropboxjs" data-app-key="w7qbnscwwlxgtz0"></script>
	<script type="text/javascript" src="https://cdn.rawgit.com/Nijikokun/5192472/raw/4c80b2c2688841ffb086f8c2b3f57520b0bd817d/base64-utf8.module.js"></script>
	</head>
	<body>
	<a href="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAUA
	AAAFCAYAAACNbyblAAAAHElEQVQI12P4//8/w38GIAXDIBKE0DHxgljNBAAO
	9TXL0Y4OHwAAAABJRU5ErkJggg==" data-filename="reddot.png" alt="Red dot" id=save class="dropbox-saver" onclick='save.href="data:text/text;base64,"+base64.encode(foo.value);save.dataset.filename = "mytext"'></a>
	<input type='text

	# -*- coding: utf-8
	from __future__ import unicode_literals
	import warnings
	import unicodedata

	def build_lookup(macro, micro):
	assert len(macro) == len(micro), (len(macro), len(micro))
	output = {}
	for pair in zip(macro, micro):
	if pair[1] != ' ':

	import xml.etree.ElementTree as etree
	import html5lib

	def fromstring(s):
	tb = html5lib.getTreeBuilder("lxml", implementation=etree)
	p = html5lib.HTMLParser(tb, namespaceHTMLElements=False)
	return p.parse(s)

	class BatchSaver(object):
	def __init__(self, max_queue=2000, save_callback=None):
	self.queue = []
	self.max_queue = max_queue
	self.callback = save_callback
	import atexit
	atexit.register(self.save_now)

	def push(self, row):
	self.queue.append(row)

	#!/bin/bash
	mkdir -p ~/BAK && mv ~/tool ~/incoming ~/http ~/BAK
	git clone http://bitbucket.org/scraperwikids/data-services-scraper-template
	./data-services-scraper-template/install.sh .
	rm -rf ./data-services-scraper-template
	echo -n "Remote repository: "
	read REMOTE
	git remote add origin $REMOTE
	git push -u origin --all
	./tool/first_run.sh

	pip install line_profiler

	kernprof.py -l worldbank.py
	python -m line_profiler worldbank.py.lprof

	# put @profile before the functions you care about

	//jsonData contains data in the appropriate format
	var json_table = new google.visualization.Table(document.getElementById('table_div_json'))
	var json_data = new google.visualization.DataTable(jsonData, 0.6);
	json_table.draw(json_data, {showRowNumber: true});