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.
168 lines
6.3 KiB
Python
168 lines
6.3 KiB
Python
#! /usr/bin/env python
|
|
# -*- coding: utf-8 -*-
|
|
|
|
##############
|
|
# FROM THE JSON DICTIONARY CREATE AN INDEX PAGE
|
|
#####
|
|
import xml.etree.ElementTree as ET
|
|
import html5lib, urllib2, json, pprint, re
|
|
from mmdc_modules import api_thumb_url, pandoc2html, img_fullurl, api_file_url, write_html_file
|
|
#import mmdc_create_json import api_thumb_url
|
|
json_allworks_file = open('allworks_mmdc.json', 'r') # save json
|
|
json_allworks = json.loads(json_allworks_file.read())
|
|
pages_path = 'web/work'
|
|
|
|
#def generate_xml():
|
|
gallery_exp=re.compile('<gallery>.*?</gallery>')
|
|
file_exp=re.compile('File:(.*?)(?=File:|<\/gallery>)')
|
|
img_exp=re.compile('(File:|Image:)((.*?)\.(gif|jpg|jpeg|png))(?=\||File:|Image:|<\/gallery>)', re.I)
|
|
video_exp=re.compile('\{\{(.*?)\|(.*?)\}\}')
|
|
|
|
def replace_gallery(content):
|
|
# from <gallery>.*</gallery> imgs, return list of img ET elements
|
|
# replace <gallery>.*</gallery> with ''
|
|
gallery_imgs = []
|
|
gallery_found = re.findall(gallery_exp, content)
|
|
content = re.sub(gallery_exp, '', content)
|
|
for gallery in gallery_found: # in case there is more than 1 <gallery>
|
|
allfiles =re.findall(img_exp, gallery)
|
|
for imgfile in allfiles:
|
|
imgfile = imgfile[1]
|
|
imgsrc = api_file_url(imgfile) # search for original image
|
|
gallery_imgs.append(imgsrc)
|
|
return content, gallery_imgs
|
|
|
|
def replace_video(content):
|
|
videos = []
|
|
videos_found = re.findall(video_exp, content)
|
|
for video in videos_found:
|
|
video_provider = str(video[0])
|
|
video_hash = str(video[1])
|
|
video_src = None
|
|
if (video_provider.lower()) == 'youtube':
|
|
video_src="https://www.youtube.com/embed/" + video_hash
|
|
elif (video_provider.lower()) == 'vimeo':
|
|
video_src="https://player.vimeo.com/video/" + video_hash
|
|
if video_src:
|
|
videos.append(video_src)
|
|
content = re.sub(video_exp, '', content)
|
|
return content, videos
|
|
|
|
def create_workpage( work, work_key, tree): # replace text content in dict with html nodes, holding the content
|
|
pprint.pprint( work)
|
|
for key in work.keys():
|
|
print work[key]
|
|
|
|
div_header = (tree.findall(".//div[@class='header']"))[0]
|
|
div_body = (tree.findall(".//div[@class='body']"))[0]
|
|
div_av = (tree.findall(".//div[@class='av']"))[0]
|
|
|
|
if key in ['Description', 'Extra']:
|
|
mw_content = work[key]
|
|
if re.search(gallery_exp, mw_content):
|
|
mw_content, gallery_imgs = replace_gallery(mw_content)
|
|
work['Images'] = gallery_imgs
|
|
for imgsrc in gallery_imgs:
|
|
img_el = ET.SubElement(div_av, 'img', attrib={'src': imgsrc})
|
|
elif re.search(video_exp, mw_content):
|
|
mw_content, videos = replace_video(mw_content)
|
|
work['Video'] = videos
|
|
for video in videos:
|
|
iframe_el = ET.SubElement(div_av, 'iframe', attrib={'src': video, 'width':'600px', 'height':'450px'})
|
|
print 'VIDEO', ET.tostring(iframe_el)
|
|
|
|
work[key] = pandoc2html( mw_content if key in work.keys() else '' ) # convert to HTML
|
|
text_el = html5lib.parseFragment(work[key], namespaceHTMLElements=False)
|
|
text_imgs = text_el.findall('.//img')
|
|
if text_imgs:
|
|
for img in text_imgs:
|
|
src = api_file_url(img.get('src'))
|
|
img.set('src', src)
|
|
|
|
print 'IMG', img, src
|
|
|
|
div_body.append( text_el )
|
|
|
|
|
|
|
|
|
|
|
|
elif key in ['Thumbnail']:
|
|
thumb = api_file_url(work[key])
|
|
img_el = ET.SubElement(div_av, 'img', attrib={'src': thumb})
|
|
|
|
elif key in ['Website']:
|
|
work_el = ET.SubElement(div_header, 'a', attrib={'href': work[key], 'id':key})
|
|
work_el.text = work[key]
|
|
elif key in ['Title']:
|
|
work_el = ET.SubElement(div_header, 'h1', attrib={'id': key})
|
|
work_el.text = (work[key]).replace('_', ' ')
|
|
|
|
elif key in ['Creator', 'Date', 'Bio']:
|
|
work_el =ET.SubElement(div_header, 'p', attrib={'id': key})
|
|
work_el.text = work[key]
|
|
|
|
|
|
|
|
# for key in work.keys():
|
|
|
|
# # p = ET.Element('p')
|
|
# # p.text = " oooo oooo oo"
|
|
# # print 'ELEMENTS', ET.tostring(div_header)
|
|
# # print 'ELEMENTS', ET.tostring(div_body)
|
|
# # print 'ELEMENTS', ET.tostring(div_av)
|
|
# # ET.SubElement(div_header, 'p' )
|
|
|
|
|
|
|
|
|
|
# print "****************************"
|
|
# print ET.tostring(div_body)
|
|
# print "****************************"
|
|
|
|
# # elif key in ['Thumbnail_url']:
|
|
# # print Thumbnail_url, work[key]
|
|
|
|
|
|
# elif key in ['Thumbnail_url']:
|
|
# print 'THUMBNAIL_URL', work[key]
|
|
# # ERROR - Thumbnail url is None
|
|
# # work_el = ET.SubElement(div_header, 'img', attrib={'src': work[key], 'id': key})
|
|
# else:
|
|
# work_el = None # remove keys with None value?
|
|
# work[key] = work_el
|
|
# work.pop('Thumbnail_url', None) #remove Thumbnail_url
|
|
# pprint.pprint(work)
|
|
|
|
|
|
def edit_index(filepath, json_allworks_dict):
|
|
input_file = open(filepath, 'r')
|
|
tree = html5lib.parse(input_file, namespaceHTMLElements=False)
|
|
div_section02 = (tree.findall(".//div[@id='section02']"))[0]
|
|
for key in json_allworks_dict.keys():
|
|
graduation_work=json_allworks_dict[key]
|
|
insert_work(div_section02, 'Graduation_work thumbnail', graduation_work, key )
|
|
return tree
|
|
|
|
|
|
worktemplate = open('web/work-template.html', 'r')
|
|
for key in json_allworks.keys():
|
|
work=json_allworks[key]
|
|
title = work['Title']
|
|
date = work['Date']
|
|
creator = (work['Creator'].encode('ascii', 'ignore')).replace(' ','_')
|
|
work_file = 'web/{}-{}-{}.html'.format(date, key, creator)
|
|
print work_file
|
|
work_tree = html5lib.parse(worktemplate, namespaceHTMLElements=False)
|
|
create_workpage(work, key, work_tree )
|
|
write_html_file(work_tree, work_file)
|
|
|
|
|
|
### ISSSUES
|
|
# Gallaries, Files, videos, in orginal places correct place
|
|
# Specificy positions in template
|
|
# rm <DOCUMENT_FRAGMENT> from pandoc output
|
|
# separate Extra and Description
|
|
|
|
|