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.
98 lines
3.5 KiB
Python
98 lines
3.5 KiB
Python
#! /usr/bin/env python
|
|
# -*- coding: utf-8 -*-
|
|
|
|
###########
|
|
# prototyping downloading and converting mw page content to html
|
|
###########
|
|
|
|
# OVERVIEW:
|
|
# * creating one single html page
|
|
# * replace {{youtube/vimeo}} with video tags
|
|
# * replace galleries with rows of images
|
|
# request all the pages
|
|
# build index
|
|
# build all pages
|
|
|
|
import xml.etree.ElementTree as ET
|
|
import html5lib, re, pprint
|
|
from mmdc_modules import api_request, api_page, api_thumb_url, pandoc2html, parse_work, api_file_url, replace_gallery, replace_video, gallery_exp, video_exp, api_pagesincategories
|
|
|
|
|
|
|
|
|
|
########
|
|
# QUERY API
|
|
########
|
|
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&"
|
|
|
|
|
|
########
|
|
# CREATE INDEX
|
|
########
|
|
memberpages = api_pagesincategories('Graduation work', '2015') #list, containing dictionary of all page ids. Example: [{u'ns': 0, u'pageid': 15974, u'title': u'Ahhhh'}, {u'ns': 0, u'pageid': 16005, u'title': u'Artyom-graduation-work'}]
|
|
#memberpages = [{u'ns': 0, u'pageid': 16005, u'title': u'Artyom-graduation-work'}]
|
|
#memberpages = [{u'ns': 0, u'pageid': 16007, u'title': u'U ntitled'}]
|
|
print 'memberpages', memberpages
|
|
|
|
########
|
|
# CREATE PAGE
|
|
########
|
|
page_template = open("web/page-template.html", "r")
|
|
page_template = page_template.read()
|
|
|
|
for member in memberpages:
|
|
#print member
|
|
# download mw work page
|
|
pageid=member['pageid']
|
|
pagetitle=(member['title'].encode('utf-8'))
|
|
workpage_mw = api_page(pageid, 'content')
|
|
|
|
# parse workpage_mw
|
|
workpage_mw = replace_gallery(workpage_mw)
|
|
workpage_mw = replace_video(workpage_mw)
|
|
workdict = parse_work(pagetitle, workpage_mw) # create dictionary workpage_mw template
|
|
|
|
for key in workdict.keys(): # convert Extra, Description, Bio to HTML
|
|
if key in ['Extra', 'Description', 'Bio'] and workdict[key]:
|
|
workdict[key] = pandoc2html( (workdict[key].decode('utf-8')) )
|
|
|
|
# fill template with dictionary/mw_page values
|
|
workpage_html = page_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']) )
|
|
|
|
# parse workpage_html # process html: img full url
|
|
tree = html5lib.parse(workpage_html, namespaceHTMLElements=False)
|
|
imgs = tree.findall('.//img')
|
|
for img in imgs:
|
|
src = img.get('src')
|
|
newsrc = api_file_url(src)
|
|
if newsrc:
|
|
img.set('src', newsrc)
|
|
website = tree.find('.//div[@id="website"]/a')
|
|
print 'website', ET.tostring(website)
|
|
|
|
if not website.get('href'):
|
|
#remove empty .//div[@id="website"]/a
|
|
# This can be applied to more fields
|
|
website_parent = tree.find('.//div[@id="website"]')
|
|
website_parent.remove(website)
|
|
|
|
# save workpage_html
|
|
workpage_html = ET.tostring(tree)
|
|
creator = workdict['Creator'].decode('ascii', 'ignore')
|
|
creator = creator.replace(' ','_')
|
|
work_filename = 'web/{}-{}-{}.html'.format(workdict['Date'], creator, pageid)
|
|
work_file = open(work_filename, "w")
|
|
work_file.write(workpage_html)
|
|
work_file.close()
|
|
|
|
|