option --local; documentation

README.md

@@ -1,5 +1,3 @@
-# Wiki to HTML pages script
-![](https://pzwiki.wdka.nl/mw-mediadesign/images/8/82/Workflow-wiki2html.svg)
 
 ## Depencencies
 * python3
@@ -20,7 +18,9 @@
     * Install:
         * Debian/Ubuntu: `sudo apt install pandoc`
         * Mac: `brew install pandoc`
-
+* [html5lib](https://github.com/html5lib/html5lib-python)
+    * Install:
+        * `pip3 install html5lib`
 
 ## login.txt
 `login.txt` is a local and individual file, ignored by git, where you place you itch wiki username and password, in separate lines.
@@ -31,7 +31,32 @@ myusername
 mypassword
 ```
 
+## Create archive from wiki:
+
+### on sandbox server
+`python dumpwiki.py`
+
+### locally on your own machine:
+create archive folder: `mkdir archive`
+
+run script outputting to archive folder and displaying the images from the wiki:
+
+`python dumpwiki.py --output archive --local`
+
 
+### Categories and Templates:
+For each Wiki Category in [Category Publish](https://hub.xpub.nl/sandbox/itchwiki/index.php/Category:Publish) 
+there should be an HTML [jinja2 template](https://jinja.palletsprojects.com/en/2.11.x/) 
+, with the same name of the category this repository `templates/`
+ 
+If not the `templates/default.html` will be used to render the pages under that Category.
+
+
+
+---
+
+
+# query2html.py
 ## Run
 
 `cd special-issue-11-wiki2html/`
@@ -100,3 +125,5 @@ It is
 to convert pdfs to jpgs:
 convert -quality 100 -density 300 [name-of-pdf] %02d.jpg
 
+# Wiki to HTML pages script
+![](https://pzwiki.wdka.nl/mw-mediadesign/images/8/82/Workflow-wiki2html.svg)

dumpwiki.py

@@ -16,6 +16,7 @@ p.add_argument("--host",  metavar='', default="hub.xpub.nl/sandbox", help='wiki
 p.add_argument("--path", metavar='', default="/itchwiki/", help="Wiki path. Should end with /")
 p.add_argument("--output", default="/var/www/html/archive", help="Output path for pages")
 p.add_argument("--one", default=False, action="store_true", help="Output one page from each category only")
+p.add_argument("--local", default=False, action="store_true", help="When creating a local archives. Add full URL to images")
 
 args = p.parse_args()
 
@@ -58,6 +59,11 @@ def rewritelinks (html):
         if href.startswith("/sandbox/itchwiki/index.php/"):
             new_href = filenameforlink(href)
             a.attrib['href'] = new_href
+    if args.local is True:
+        for img in t.findall(".//img[@src]"):
+            src = img.attrib.get("src")
+            if not src.startswith('http'):
+                img.attrib['src'] = 'https://hub.xpub.nl' + src
     html = ET.tostring(t, method="html", encoding="unicode")
     return html