. It shouldn't - -## replace gallery - not yet there - diff --git a/prototype_page.py b/prototype_page.py index b7985c7..1e26abe 100755 --- a/prototype_page.py +++ b/prototype_page.py @@ -20,48 +20,36 @@ from mmdc_modules import api_request, api_page, api_thumb_url, pandoc2html, pars template = open("web/page-template.html", "r") template = template.read() -# download +# download mw work page pageid='15965'#Qq #'16025' #'15986'Jozeph #'16025'Mina work = 'Q' #'Mina'#'User:Joak/graduation/catalog1' workpage_mw = api_page(pageid, 'content') -print '------------------- workpage_mw' -if re.search(gallery_exp, workpage_mw): - print 'FOUND GALLERY' - workpage_mw = replace_gallery(workpage_mw) -if re.search(video_exp, workpage_mw): - workpage_mw = replace_video(workpage_mw) - print 'FOUND VIDEO' -''' -# parsing workpage_mw -workdict = parse_work(work, workpage_mw) +# parse workpage_mw +workpage_mw = replace_gallery(workpage_mw) +workpage_mw = replace_video(workpage_mw) +workdict = parse_work(work, workpage_mw) # create dictionary workpage_mw template for key in workdict.keys(): if key in ['Extra', 'Description', 'Bio']: workdict[key] = pandoc2html(workdict[key].encode('utf-8')) +# fill template with dictionary/mw_page values workpage_html = 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'] ) -# Process html +# 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) -# print 'new src', newsrc if newsrc: img.set('src', newsrc) - #print 'IMG', ET.tostring(img) - - +# save workpage_html workpage_html = ET.tostring(tree) -#print 'TREE', workpage_html - - -# # save work_filename = 'web/{}-{}-{}.html'.format(workdict['Date'], (workdict['Creator'].encode('ascii', 'ignore')).replace(' ','_'), pageid) work_file = open(work_filename, "w") work_file.write(workpage_html) work_file.close() -''' +