images2html
Castro0o
5 years ago
parent
73d4df942a
commit
a76313c251
@ -0,0 +1,76 @@
|
|||||||
|
import os, json
|
||||||
|
from mwclient import Site
|
||||||
|
from pprint import pprint
|
||||||
|
from jinja2 import Template
|
||||||
|
from functions import pandoc, page_props
|
||||||
|
|
||||||
|
site = Site(host='hub.xpub.nl/sandbox', path='/itchwiki/')
|
||||||
|
wd = os.path.dirname(os.path.abspath(__file__)) # working directory
|
||||||
|
imgdir = os.path.join(wd, 'images')
|
||||||
|
imgsjson_fn = os.path.join(wd, 'images.json')
|
||||||
|
with open(imgsjson_fn, 'r') as imgsjson_file:
|
||||||
|
images_info = json.load(imgsjson_file)
|
||||||
|
|
||||||
|
static_html = os.path.join(wd, 'static_html')
|
||||||
|
os.makedirs(static_html, exist_ok=True) # create images/ dir
|
||||||
|
|
||||||
|
with open(os.path.join(wd, 'login.txt'), 'r') as login: # read login user & pwd
|
||||||
|
loginlines = login.read()
|
||||||
|
user, pwd = loginlines.split('\n')
|
||||||
|
site.login(username=user, password=pwd) # login to wiki
|
||||||
|
|
||||||
|
|
||||||
|
page_html_template = '''
|
||||||
|
<!DOCTYPE html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<link rel="stylesheet" href="../static/style.css" />
|
||||||
|
<title>{{title}}</title>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<h1>{{ title }}</h1>
|
||||||
|
<p><time datetime="{{date}}">{{date}}</time></p>
|
||||||
|
<div id="img">
|
||||||
|
<img src="{{ imgsrc }}" />
|
||||||
|
</div>
|
||||||
|
<div id="content">
|
||||||
|
{{ content }}
|
||||||
|
</div>
|
||||||
|
<footer>
|
||||||
|
Part {{part}} of {{partof}}
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
|
'''
|
||||||
|
page_template = Template(page_html_template)
|
||||||
|
|
||||||
|
|
||||||
|
for img_info in images_info.values():
|
||||||
|
print(img_info)
|
||||||
|
page_name = img_info['name']
|
||||||
|
page = site.pages[page_name]
|
||||||
|
# print(page)
|
||||||
|
# pprint(page.__dict__)
|
||||||
|
# print(dir(page))
|
||||||
|
pagetext = page.text()
|
||||||
|
pageproperties = page_props(wikicontent=pagetext)
|
||||||
|
print(pageproperties)
|
||||||
|
|
||||||
|
if pageproperties.get('Title'):
|
||||||
|
pagetext_html = pandoc(content=pagetext, format_in='mediawiki', format_out='html')
|
||||||
|
# print('pagetext', pagetext)
|
||||||
|
# print('pagetext_html', pagetext_html)
|
||||||
|
page_html = page_template.render(title=pageproperties.get('Title'),
|
||||||
|
date=pageproperties.get('Date'),
|
||||||
|
imgsrc=os.path.join(imgdir, img_info.get('filename')),
|
||||||
|
content=pagetext_html,
|
||||||
|
part=pageproperties.get('Part'),
|
||||||
|
partof=pageproperties.get('Partof'))
|
||||||
|
htmlpage_fn = "{}_{}.html".format(
|
||||||
|
pageproperties.get('Title').replace(" ", ""),
|
||||||
|
pageproperties.get('Part').zfill(3)
|
||||||
|
)
|
||||||
|
print(htmlpage_fn)
|
||||||
|
with open(os.path.join(static_html, htmlpage_fn), 'w') as htmlfile:
|
||||||
|
htmlfile.write(page_html)
|
||||||
@ -0,0 +1,70 @@
|
|||||||
|
import os, json
|
||||||
|
from mwclient import Site
|
||||||
|
from pprint import pprint
|
||||||
|
from functions import update_json
|
||||||
|
|
||||||
|
site = Site(host='hub.xpub.nl/sandbox', path='/itchwiki/')
|
||||||
|
wd = os.path.dirname(os.path.abspath(__file__)) # working directory
|
||||||
|
|
||||||
|
imgdir = os.path.join(wd, 'images')
|
||||||
|
os.makedirs(imgdir, exist_ok=True) # create images/ dir
|
||||||
|
|
||||||
|
imgsjson_fn = os.path.join(wd, 'images.json')
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
with open(os.path.join(wd, 'login.txt'), 'r') as login: # read login user & pwd
|
||||||
|
loginlines = login.read()
|
||||||
|
user, pwd = loginlines.split('\n')
|
||||||
|
site.login(username=user, password=pwd) # login to wiki
|
||||||
|
|
||||||
|
with open(imgsjson_fn, 'r') as imgsjson_file:
|
||||||
|
images_info = json.load(imgsjson_file)
|
||||||
|
|
||||||
|
img_info = images_info["File:CCF 003017.jpg"]
|
||||||
|
|
||||||
|
print(img_info)
|
||||||
|
page_name = img_info['name']
|
||||||
|
page = site.pages[page_name]
|
||||||
|
print(page)
|
||||||
|
pprint(page.__dict__)
|
||||||
|
print(dir(page))
|
||||||
|
text = page.text()
|
||||||
|
used_in = list(page.imageusage())
|
||||||
|
print(text, used_in)
|
||||||
|
# response = site.api(action='browsebysubject', subject=page_name)
|
||||||
|
# for q in response['query']['data']:
|
||||||
|
# print(q['property'], q['dataitem'])
|
||||||
|
# print(q)
|
||||||
|
# print('result:', response['query']['data'][0]['item'])
|
||||||
|
# print('keys', response['query'].keys())
|
||||||
|
|
||||||
|
response = site.ask(query='[[Date::+]]|?Date', title=page_name)
|
||||||
|
print(response)
|
||||||
|
# import pdb; pdb.set_trace()
|
||||||
|
for r in response:
|
||||||
|
print('response', r)
|
||||||
|
for title, data in r.items():
|
||||||
|
print(data)
|
||||||
|
# import pdb; pdb.set_trace()
|
||||||
|
print(type(data))
|
||||||
|
if type(data) not in [str, int]:
|
||||||
|
for k, item in data.items():
|
||||||
|
print('item', k, item[k])
|
||||||
|
for subitem in data.items():
|
||||||
|
print('subitem', subitem, )
|
||||||
|
# for k, v in data['printouts']:
|
||||||
|
# print(k,v)
|
||||||
|
# action=smwbrowse&browse=page¶ms={ "limit": 10, "offset": 0, "search": "Main", "fullText": true, "fullURL": true }
|
||||||
|
# for page in site.pages(page_name):
|
||||||
|
# print(page)
|
||||||
|
|
||||||
|
|
||||||
|
#
|
||||||
|
# for img_key, img_info in images_info.items():
|
||||||
|
# if n < 4:
|
||||||
|
# print(img_info)
|
||||||
|
# page_name = img_info['name']
|
||||||
|
# page = site.pages(page_name)
|
||||||
|
# print(page)
|
||||||
|
# print('\n')
|
||||||
@ -0,0 +1,3 @@
|
|||||||
|
body{font-size: 12pt;}
|
||||||
|
|
||||||
|
div#img img {width: 100%;}
|
||||||
Loading…
Reference in New Issue