You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

220 lines
8.7 KiB
Python

#! /usr/bin/env python
# -*- coding: utf-8 -*-
import urllib2, json, pprint, re
import xml.etree.ElementTree as ET
import subprocess, shlex, urllib
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
print 'API REQUEST'
print pagename
print 'TEST', action.format(pagename)
url = endpoint + (action.format(pagename))
print 'API REQUEST', url
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)
elif query == 'imageinfo':
pagename = pageid # in imageinfo titles are used instead of id
print 'IMAGEINFO', pagename
response = api_request("action=query&titles=File:{}&prop=imageinfo&iiprop=url&iiurlwidth=500", pagename) # iiurlwidht dermines with of thumbnail
return response
##############################
# CATEGORIES AND PAGES
################
# * MUST BE REPLACE BY SMARTER CODE (USING PY MD LIB)
##############################
def api_pagecategories(pageid):
'''Find all the categories, and their parent category of a page '''
query = 'action=query&pageids={}&prop=categories'.format(pageid)
url = endpoint + query
request = urllib2.urlopen(url)
jsonp = json.loads(request.read())
json_dic = jsonp['query']['pages']
page_id = json_dic.keys()[0]
page_categories = json_dic[page_id][u'categories']
all_cats = [ entry[u'title'].encode('utf-8') for entry in page_categories ] #.replace('Category:', '')
return all_cats
def api_pagesincategories(category, year):
# Find all pages incategory and add to allworks dictionary
category = category.replace(' ', '_')
apiCatMembers = endpoint + 'action=query&list=categorymembers&cmlimit=1000&cmtitle=Category:{}'.format(category)
request = urllib2.urlopen(apiCatMembers)
jsonp = json.loads(request.read())
graduationWorkMembers = jsonp['query']['categorymembers']
intersectCatMembers = []
if year:
for member in graduationWorkMembers:
page_cats = api_pagecategories(member['pageid'])
if ('Category:{}'.format(year)) in page_cats:
print year, 'in', page_cats
intersectCatMembers.append(member)# add member to intersectCatMembers
else:
intersectCatMembers = graduation_work_members
return intersectCatMembers
# for page in intersectCatMembers:
# title = ((page['title']).encode('utf-8') ).replace(" ", "_") #snakecase for page titles
# pageid = page['pageid']
# article = api_page(pageid, 'content')
# # print title
# # pprint.pprint(article)
# work = parse_work_page(title, article)
# if work:
# allworks[pageid] = work #dictionary(allworks) entry
# print pprint.pprint( work )
# # Create work page
# else:
# print 'WORK DOES NOT CONTAIN REQUIRED CONTENT'
# print '-------------'
# print
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):
print '''get thumbnail url of image'''
thumburl = api_page(filename, 'imageinfo')
thumburl = ((thumburl.get('imageinfo'))[0].get('thumburl'))
print 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
# PROCESSING 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()
# 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]
keyval = re.findall('\|(.*?)\=(.*?\n)', template, re.DOTALL) # template's key/value pair
if extra: #append 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
def parse_work(title, content):
workdict = {'Title':title, 'Creator':'', 'Date':'', 'Website':'', 'Thumbnail':'', 'Bio':'', 'Description':'', 'Extra':''}
if re.match('\{\{\Graduation work', content):
template, extra = (re.findall('\{\{Graduation work\n(.*?)\}\}(.*)', content, re.DOTALL))[0]
if extra:
workdict['Extra'] = extra.encode('utf-8')
# template's key/value pair
# Note:Extra value is NOT CAPTURED by this regex
keyval = re.findall('\|(.*?)\=(.*?\n)', template, re.DOTALL)
for pair in keyval:
key = pair[0]
val = (pair[1]).replace('\n', '')
if 'Creator' in key:
val = val.replace(', ', '')
elif 'Thumbnail' in key:
val = api_thumb_url(val)
elif 'Website' in key:
val = urllib.unquote(val)
workdict[key]=val.encode('utf-8')
# pprint.pprint(workdict)
return workdict
# Conversion Modules
def pandoc2html(mw_content):
'''convert individual mw sections to html'''
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')
for img in imgs:
src = img.get('src')
fullurl = api_thumb_url(src)
if fullurl != None:
img.set('src', fullurl)
gallery_exp=re.compile('<gallery>(.*?)</gallery>', re.S)
imgfile_exp=re.compile('(File:(.*?)\.(gif|jpg|jpeg|png))')
def replace_gallery(content):
content = re.sub(imgfile_exp, '[[\g<1>]]', content) #add [[ ]] to File:.*?
content = re.sub(gallery_exp, '\g<1>', content) #remove gallery wrapper
return content
video_exp=re.compile('\{\{(.*?)\|(.*?)\}\}')
vimeo_exp=re.compile('\{\{vimeo\|(.*?)\}\}')
youtube_exp=re.compile('\{\{youtube\|(.*?)\}\}')
def replace_video(content):
content = re.sub(vimeo_exp,"<iframe src='https://player.vimeo.com/video/\g<1>' width='600px' height='450px'> </iframe>", content)
content = re.sub(youtube_exp, "<iframe src='https://www.youtube.com/embed/\g<1>' width='600px' height='450px'> </iframe>", content)
return content