|
|
|
|
#! /usr/bin/env python
|
|
|
|
|
# -*- coding: utf-8 -*-
|
|
|
|
|
|
|
|
|
|
import urllib2, json, pprint, re
|
|
|
|
|
import xml.etree.ElementTree as ET
|
|
|
|
|
import subprocess, shlex
|
|
|
|
|
sid = '1234'
|
|
|
|
|
useragent = "Mozilla/5.001 (windows; U; NT4.0; en-US; rv:1.0) Gecko/25250101"
|
|
|
|
|
endpoint = "http://pzwiki.wdka.nl/mw-mediadesign/api.php?format=json&"
|
|
|
|
|
|
|
|
|
|
# API MODULES
|
|
|
|
|
def api_request(action, pagename): #get page: content, metadata, images, imageifnp
|
|
|
|
|
url = endpoint + action.format(pagename)
|
|
|
|
|
request = urllib2.urlopen(url)
|
|
|
|
|
jsonp = json.loads(request.read() )
|
|
|
|
|
json_dic= (jsonp.get('query').get('pages'))
|
|
|
|
|
# pprint.pprint( json_dic )
|
|
|
|
|
page_id = json_dic.keys()[0]
|
|
|
|
|
page_content = json_dic.get(page_id)
|
|
|
|
|
return page_content
|
|
|
|
|
|
|
|
|
|
def api_page(pageid, query):
|
|
|
|
|
if query == 'content':
|
|
|
|
|
api_response = api_request('action=query&pageids={}&prop=revisions&rvprop=content', pageid)
|
|
|
|
|
response = ((api_response.get('revisions'))[0])['*']
|
|
|
|
|
elif query == 'metadata':
|
|
|
|
|
response = api_request('action=query&pageids={}&prop=info', pageid)
|
|
|
|
|
elif query == 'articleimgs':
|
|
|
|
|
response = api_request('action=query&pageids={}&prop=images', pageid)
|
|
|
|
|
elif query == 'file':
|
|
|
|
|
response = api_request('action=query&titles=File:{}&prop=imageinfo&iiprop=url',pageid)
|
|
|
|
|
pprint.pprint( response )
|
|
|
|
|
elif query == 'imageinfo':
|
|
|
|
|
pagename = pageid # in imageinfo titles are used instead of id
|
|
|
|
|
response = api_request('action=query&titles=File:{}&prop=imageinfo&iiprop=url&iiurlwidth=500', pagename) # iiurlwidht dermines with of thumbnail
|
|
|
|
|
return response
|
|
|
|
|
|
|
|
|
|
def api_file_url(filename): # get full urls
|
|
|
|
|
page_content_dict = api_page(filename, 'file')
|
|
|
|
|
if 'imageinfo' in page_content_dict.keys():
|
|
|
|
|
imgurl = ((page_content_dict.get('imageinfo'))[0].get('url'))
|
|
|
|
|
return imgurl
|
|
|
|
|
else:
|
|
|
|
|
return None
|
|
|
|
|
|
|
|
|
|
def api_thumb_url(filename):
|
|
|
|
|
'''get thumbnail url of image'''
|
|
|
|
|
page_content_dict = api_page(filename, 'imageinfo')
|
|
|
|
|
if 'imageinfo' in page_content_dict.keys():
|
|
|
|
|
thumburl = ((page_content_dict.get('imageinfo'))[0].get('thumburl'))
|
|
|
|
|
return thumburl
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# http://pzwiki.wdka.nl/mw-mediadesign/api.php?format=json&action=query&titles=File:2x2 905.jpg&prop=imageinfo&iiprop=url&iiurlwidth=300
|
|
|
|
|
# http://pzwiki.wdka.nl/mw-mediadesign/api.php?format=json&action=query&pageids=10603&prop=revisions&rvprop=content
|
|
|
|
|
# http://pzwiki.wdka.nl/mw-mediadesign/api.php?format=json&action=query&titles=Graduation_Website_Braindump&prop=revisions&rvprop=content
|
|
|
|
|
|
|
|
|
|
# XML MODULES
|
|
|
|
|
|
|
|
|
|
def write_html_file(html_tree, filename):
|
|
|
|
|
doctype = "<!DOCTYPE HTML>"
|
|
|
|
|
html = doctype + ET.tostring(html_tree, encoding='utf-8', method='html')
|
|
|
|
|
edited = open(filename, 'w') #write
|
|
|
|
|
edited.write(html)
|
|
|
|
|
edited.close()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# Conversion Modules
|
|
|
|
|
def pandoc2html(mw_content):
|
|
|
|
|
if mw_content:
|
|
|
|
|
mw_content = mw_content.encode('utf-8')
|
|
|
|
|
# convert from mw to html
|
|
|
|
|
args_echo =shlex.split( ('echo "{}"'.format(mw_content)) )
|
|
|
|
|
args_pandoc = shlex.split( 'pandoc -f mediawiki -t html5' )
|
|
|
|
|
p1 = subprocess.Popen(args_echo, stdout=subprocess.PIPE)
|
|
|
|
|
p2 = subprocess.Popen(args_pandoc, stdin=p1.stdout, stdout=subprocess.PIPE)
|
|
|
|
|
html = (p2.communicate())[0]
|
|
|
|
|
return html
|
|
|
|
|
|
|
|
|
|
def img_fullurl(parent):
|
|
|
|
|
imgs = parent.findall('.//img')
|
|
|
|
|
print 'len IMG', len(imgs)
|
|
|
|
|
for img in imgs:
|
|
|
|
|
src = img.get('src')
|
|
|
|
|
fullurl = api_thumb_url(src)
|
|
|
|
|
print '----- IMG', ET.tostring(img ), src, fullurl
|
|
|
|
|
if fullurl != None:
|
|
|
|
|
img.set('src', fullurl)
|
|
|
|
|
|
|
|
|
|
# fileurl = api_request(src, endpoint)# find url of file
|
|
|
|
|
|
