#! /usr/bin/env python # -*- coding: utf-8 -*- ########### # Testing downloading and converting mw page content to html ########### # OVER VIEW: # * creating one single html page # request all the pages # build index # build all pages import pprint from mmdc_modules import api_request, api_page, api_thumb_url, pandoc2html, parse_work_page, parse_work template = open("web/page-template.html", "r") template = template.read() # download pageid='16025'#'15965'#Qq #'15986'Jozeph work = 'Mina'#'User:Joak/graduation/catalog1' workpage_mw = api_page(pageid, 'content') # parsing workpage_mw workdict = parse_work(work, workpage_mw) for key in workdict.keys(): if key in ['Extra', 'Description', 'Bio']: workdict[key] = pandoc2html(workdict[key].encode('utf-8')) # print key # print workdict[key] # print '--------------------' template = template.format(title=workdict['Title'], creator=workdict['Creator'], date=workdict['Date'], website=workdict['Website'], thumbnail=workdict['Thumbnail'], bio=workdict['Bio'],description=workdict['Description'], extra=workdict['Extra'] ) work_filename = 'web/{}-{}-{}.html'.format(workdict['Date'], (workdict['Creator'].encode('ascii', 'ignore')).replace(' ','_'), pageid) work_file = open(work_filename, "w") work_file.write(template) work_file.close() #template = template.read() #print(template) #for section in [extra, description, bio]: # section = pandoc2html(section.encode('utf-8')) # print section # print '------------' #print template #for key in workdict.keys(): # print key, workdict[key].encode('utf-8') #print '----------- html -----' #print html_description #print html_extra #print template