ask broken down into several arguments; --dry run

README.md

@@ -45,8 +45,12 @@ Run scripts together with `./run.sh`
 
 `python3 publication2html.py`
 * with ask API perform a query: 
-    * default query is: `[[File:+]][[Title::+]][[Date::+]]|?Title|?Date|?Part|sort=Date,Title,Part|order=asc,asc,asc`  
-    * custom query `python3 publication2html.py --ask '[[File:+]][[Title::+]][[Date::+]]|?Date|order=desc'`
+    * help `python3 publication2html.py --help`
+    * run dry `python3 publication2html.py --dry` only printing request, not executing it
+    * build custom query with arguments `--conditions  --printouts  --sort  --order`
+    * default query is: `[[File:+]][[Title::+]][[Part::+]][[Date::+]]|?Title|?Date|?Part|?Partof|sort=Date,Title,Part|order=asc,asc,asc`  
+    * custom query `python3 publication2html.py -c '[[Date::>=1970/01/01]][[Date::<=1979/12/31]]' -p '?Title|?Date|?Part|?Partof' -s 'Date,Title,Part' -o 'asc,asc,asc'`
+
 * The results, with the same Title, are stored
     * into 1 single HTML
     * sorted by Part
@@ -54,4 +58,4 @@ Run scripts together with `./run.sh`
 
 
 ## TODO
-* Fix issue with PANDOC conversion MW -> HTML
+* remove HTML files at each new query

functions.py

@@ -83,4 +83,15 @@ def update_json(imgsjson_fn, img_dict, img_fn):
     with open(imgsjson_fn, 'w') as imgsjson_file:
         json.dump(imgsjson_dict, imgsjson_file, indent=4)
 
-    return download
+    return download
+
+
+class Colors:
+    HEADER = '\033[95m'
+    BLUE = '\033[94m'
+    GREEN = '\033[92m'
+    WARNING = '\033[93m'
+    FAIL = '\033[91m'
+    ENDC = '\033[0m'
+    BOLD = '\033[1m'
+    UNDERLINE = '\033[4m'

publication2html.py

@@ -1,19 +1,51 @@
-import os, json
+import os, json, sys, urllib
 from mwclient import Site
 from pprint import pprint
 from jinja2 import Template
 from functions import pandoc, page_props, unpack_response
-from argparse import ArgumentParser
 
-p = ArgumentParser(description="From smw ask string generate HTML pages with resulting results.")
-p.add_argument("--host",  metavar='', default="hub.xpub.nl/sandbox")
+from functions import Colors
+import argparse
+
+p = argparse.ArgumentParser(description="From smw ask string generate HTML pages with resulting results.",
+                            formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+p.add_argument("--host",  metavar='', default="hub.xpub.nl/sandbox", help='wiki host')
 p.add_argument("--path", metavar='', default="/itchwiki/", help="Wiki path. Should end with /")
-p.add_argument("--ask", "-a", metavar='',
-               default='[[File:+]][[Title::+]][[Date::+]]|?Title|?Date|?Part|?Partof|sort=Title,Part|order=asc,asc',
-               help="Ask query to be sent to the wiki API.")
+p.add_argument("--conditions", "-c", metavar='',
+               default='[[File:+]][[Title::+]][[Part::+]][[Date::+]]',
+               help='The query conditions')
+p.add_argument("--printouts", "-p", metavar='',
+               default='?Title|?Date|?Part|?Partof',
+               help='Selection of properties to printout')
+p.add_argument("--sort", "-s", metavar='',
+               default='Date,Title,Part',
+               help='Sorting according to conditions')
+p.add_argument("--order", "-o", metavar='', 
+               default='asc,asc,asc',
+               help='Order of sorting conditions. Should same amount as the --sort properties')
+p.add_argument('--dry', '-d', action='store_true',
+               help='dry-run: will only show the query but not run it')
 
 args = p.parse_args()
 
+if len(args.sort.split(',')) != len(args.order.split(',')):
+    print(Colors.FAIL, 'Invalid query:',
+          Colors.WARNING, '--sort and --order do not have the same amount of elements', Colors.ENDC)
+    print('Script exiting now')
+    sys.exit()
+
+query = f'{args.conditions}|{args.printouts}|sort={args.sort}|order={args.order}'
+print('query:', Colors.GREEN, query, Colors.ENDC)
+query_unquoted = urllib.parse.quote(query)
+query_url = f'https://{args.host}{args.path}api.php?action=ask&query={query_unquoted}&format=json'
+print('query URL:', query_url)
+
+if args.dry is True:
+    sys.exit()
+
+
+# site and login
+
 site = Site(host=args.host, path=args.path)
 
 wd = os.path.dirname(os.path.abspath(__file__)) # working directory
@@ -29,15 +61,16 @@ with open(os.path.join(wd, 'login.txt'), 'r') as login:  # read login user & pwd
     user, pwd = loginlines.split('\n')
     site.login(username=user, password=pwd)  # login to wiki
 
+# read template files
 with open(os.path.join(wd, 'templates/publication.html')) as pub_html:
     pub_template = Template(pub_html.read())
 
 with open(os.path.join(wd, 'templates/publication_part.html')) as pub_html:
     pub_part_template = Template(pub_html.read())
 
-pub_parts_html = '' # to append all content
+pub_parts_html = ''  # to append all content
 
-for answer in site.ask(args.ask):
+for answer in site.ask(query):
     publication_title = ''
     print(answer, answer.keys())
     printout_dict = unpack_response(answer)
@@ -76,4 +109,4 @@ for answer in site.ask(args.ask):
 
 # TODO: address Dates:
 # * date values coming from mw with timestamp, the missing valus are one
-# This a MW issue!
+# This a MW issue!