#! /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 = "" html = doctype + ET.tostring(html_tree, encoding='utf-8', method='html') edited = open(filename, 'w') #write edited.write(html) edited.close() # mw article modules def parse_work_page(title, content): # content = content.encode('utf-8') if re.match('\{\{\Graduation work', content): work_dict = {} work_dict['Title']=title template, extra = (re.findall('\{\{Graduation work\n(.*?)\}\}(.*)', content, re.DOTALL))[0] # template's key/value pair keyval = re.findall('\|(.*?)\=(.*?\n)', template, re.DOTALL) if extra: extra = ('Extra', extra) keyval.append(extra) # checkkeys = [keyval[i] for i in range(len(keyval)) if keyval[i][0] in mainkeys and len(keyval[i][1])>3] #list mainkeys present, w/ values, in tuples [(key, val),(key, val)...] # if len(checkkeys) == 3 : # checkkeys contains all mainkeys and values for pair in keyval: key = pair[0] val = pair[1] val = val.replace('\n','') if 'Creator' in key: val = val.replace(', ', '') elif 'Thumbnail' in key: thumburl = api_thumb_url(val) work_dict['Thumbnail_url']=thumburl print 'THUMB:', thumburl work_dict[key]=val return work_dict, extra # Alternative to parse_work_page - W/out dictionary def parse_work(title, content): if re.match('\{\{\Graduation work', content): template, extra = (re.findall('\{\{Graduation work\n(.*?)\}\}(.*)', content, re.DOTALL))[0] # template's key/value pair keyval = re.findall('\|(.*?)\=(.*?\n)', template, re.DOTALL) for pair in keyval: key = pair[0] val = pair[1] if 'Description' in key: description = val print keyval return extra, description # 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 pandoc(filename, title, creator, date, website, thumbnail, bio, description, extra, template) : '''pandoc: convert mediawiki syntax to html''' # mw_content = mw_content.encode('utf-8') args_echo =shlex.split( ('echo "{}"'.format( extra )) ) args_pandoc = shlex.split( 'pandoc -s -f mediawiki -t html \ --template {template} --variable title="{title}" --variable creator="{creator}" --variable date="{date}" --variable website="{website}" --variable website="{website}" --variable thumbnail="{thumbnail}" --variable bio="""{bio}""" -o {filename}'.format(template=template, title=title, creator=creator, date=date, website=website, thumbnail=thumbnail, bio=bio, description=description, extra=extra, filename=filename) ) print args_pandoc 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 # pandoc either reades input from stdin or through input file # pandoc DOES NOT convert variables; it has to receive the input from stdin. # to create html convert: bio, description, extra, of at time # insert them into HTML template by: ## gerating html in python? and insertion sub elements ? ## ?? # pandoc = 'pandoc -s -f mediawiki -t html5 \ # --template template_article.html \ # --variable title="{title}" \ # --variable section="{section}" \ # --variable topics="{topics}" \ # --variable issueName="{iname}" \ # --variable issueNumber="{inum}" \ # "articles/tmp_content.mw" -o "{articlepath}/{htmlfile}.html"'.format(articlepath=path, title=(pagename).replace("_"," "), section=in_section, topics=in_topic, iname=in_issuename, inum=in_issue, htmlfile=pagename) # subprocess.call(pandoc, shell=True) # saved in tmp_content.html html # html = open('tmp_content.html', 'r') #write mediawiki content to html in tmp_content.html # html = html.read() # 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