diff --git a/mmdc_modules.py b/mmdc_modules.py
index 5cbe30f..85b353d 100644
--- a/mmdc_modules.py
+++ b/mmdc_modules.py
@@ -4,6 +4,7 @@
import urllib2, json, pprint, re
import xml.etree.ElementTree as ET
import subprocess, shlex, urllib
+from mwclient import Site
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&"
@@ -22,18 +23,18 @@ def api_request(action, pagename): #get page: content, metadata, images, imageif
page_content = json_dic.get(page_id)
return page_content
-def api_page(pageid, query):
+def api_page(title, query):
if query == 'content':
- api_response = api_request('action=query&pageids={}&prop=revisions&rvprop=content', pageid)
+ api_response = api_request('action=query&titles={}&prop=revisions&rvprop=content', title)
response = ((api_response.get('revisions'))[0])['*']
elif query == 'metadata':
- response = api_request('action=query&pageids={}&prop=info', pageid)
+ response = api_request('action=query&titles={}&prop=info', title)
elif query == 'articleimgs':
- response = api_request('action=query&pageids={}&prop=images', pageid)
+ response = api_request('action=query&titles={}&prop=images', title)
elif query == 'file':
- response = api_request('action=query&titles=File:{}&prop=imageinfo&iiprop=url',pageid)
+ response = api_request('action=query&titles=File:{}&prop=imageinfo&iiprop=url',title)
elif query == 'imageinfo':
- pagename = pageid # in imageinfo titles are used instead of id
+ pagename = title # 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
@@ -43,6 +44,24 @@ def api_page(pageid, query):
################
# * MUST BE REPLACE BY SMARTER CODE (USING PY MD LIB)
##############################
+def mw_cats(args):
+ site = Site(args.host, path=args.path)
+ last_names = None
+ for cats in args.category:
+ for ci, cname in enumerate(cats):
+ cat = site.Categories[cname]
+ pages = list(cat.members())
+ # for p in pages:
+ # pages_by_name[p.name] = p
+ if last_names == None:
+ results = pages
+ else:
+ results = [p for p in pages if p.name in last_names]
+ last_names = set([p.name for p in pages])
+ results = list(results)
+ return [p.name for p in results]
+
+
def api_pagecategories(pageid):
'''Find all the categories, and their parent category of a page '''
query = 'action=query&pageids={}&prop=categories'.format(pageid)
diff --git a/prototype_page.py b/prototype_page.py
index 81352cf..66e06e7 100755
--- a/prototype_page.py
+++ b/prototype_page.py
@@ -17,8 +17,15 @@
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, index_addwork, write_html_file
-
+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, index_addwork, write_html_file, mw_cats
+from argparse import ArgumentParser
+
+p = ArgumentParser()
+p.add_argument("--host", default="pzwiki.wdka.nl")
+p.add_argument("--path", default="/mw-mediadesign/", help="nb: should end with /")
+p.add_argument("--category", "-c", nargs="*", default=[], action="append", help="category to query, use -c foo -c bar to intersect multiple categories")
+args = p.parse_args()
+print args
########
# QUERY API
########
@@ -29,12 +36,16 @@ endpoint = "http://pzwiki.wdka.nl/mw-mediadesign/api.php?format=json&"
########
# CREATE INDEX
########
-memberpages = api_pagesincategories('Graduation work', '2015') #list, containing dictionary of all pages 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=mw_cats(args)
+print 'memberpages', memberpages
+
+#memberpages = api_pagesincategories('Graduation work', '2015') #list, containing dictionary of all pages 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': 15982, u'title': u'The Aesthetics of Ethics'}]
#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'}]
#memberpages = [{u'ns': 0, u'pageid': 15965, u'title': u'Qq'}]
-print 'memberpages', memberpages
+## output: memberpages [{u'ns': 0, u'pageid': 15982, u'title': u'The Aesthetics of Ethics'}]
+
########
# Templates
@@ -53,14 +64,14 @@ index_container = index_tree.find(".//div[@class='isotope']") #maybe id is impor
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')
+# pageid=member['pageid']
+# pagetitle=(member['title'].encode('utf-8'))
+ workpage_mw = api_page(member, '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
+ workdict = parse_work(member, 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]:
@@ -96,7 +107,7 @@ for member in memberpages:
workpage_html = ET.tostring(tree)
creator = workdict['Creator'].decode('ascii', 'ignore')
creator = creator.replace(' ','_')
- work_filename = 'web/{}-{}-{}.html'.format(workdict['Date'], creator, pageid)
+ work_filename = 'web/{}-{}.html'.format(workdict['Date'], creator)
work_file = open(work_filename, "w")
work_file.write(workpage_html)
work_file.close()
diff --git a/web/2015-Artyom-16005.html b/web/2015-Artyom.html
similarity index 100%
rename from web/2015-Artyom-16005.html
rename to web/2015-Artyom.html
diff --git a/web/2015-Henk-Jelle_de_Groot-16007.html b/web/2015-Henk-Jelle_de_Groot.html
similarity index 100%
rename from web/2015-Henk-Jelle_de_Groot-16007.html
rename to web/2015-Henk-Jelle_de_Groot.html
diff --git a/web/2015-Lucia_Dossin-16025.html b/web/2015-Lucia_Dossin.html
similarity index 100%
rename from web/2015-Lucia_Dossin-16025.html
rename to web/2015-Lucia_Dossin.html
diff --git a/web/2015-Luther_Blisset-15965.html b/web/2015-Luther_Blisset.html
similarity index 100%
rename from web/2015-Luther_Blisset-15965.html
rename to web/2015-Luther_Blisset.html
diff --git a/web/2015-Max_Dovey-15999.html b/web/2015-Max_Dovey.html
similarity index 100%
rename from web/2015-Max_Dovey-15999.html
rename to web/2015-Max_Dovey.html
diff --git a/web/index.html b/web/index.html
index ac3dc43..1e34050 100644
--- a/web/index.html
+++ b/web/index.html
@@ -102,7 +102,7 @@
<div class="item video flash"><img src="img/project_roel2.png"></div>
<div class="item narrative"><img src="img/project_andre.jpeg"></div-->
-
+
