aboutsummaryrefslogtreecommitdiff
path: root/engine/engine.py
blob: 7cb45e9068fb80d326955065e6ca80feb4787a4f (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
import os
import re
import yaml
import pypandoc
import logging
from lxml import etree
from pyatom import AtomFeed

def item_from_path(path):
    with open(path) as f:
        text = f.read()
    p = re.compile(r'---\n(.*?)\n---(.*)', re.DOTALL)
    matchres = p.search(text)
    res = yaml.load(matchres.group(1))
    x, ext = os.path.splitext(path)
    res.setdefault('name', os.path.basename(x))
    if ext in ['.md', '.markdown']:
        logging.info('Converting {}...'.format(path))
        res['body'] = pypandoc.convert_text(matchres.group(2), 'html', format='md')
    elif ext == '.wiki':
        logging.info('Converting {}...'.format(path))
        res['body'] = pypandoc.convert_text(matchres.group(2), 'html', format='vimwiki')
    elif ext == '.html':
        res['body'] = matchres.group(2)
    res.setdefault('synlen', 1)
    paras = etree.HTML(res['body']).xpath('//p')
    res['synopsis'] = ''.join([etree.tostring(p, encoding='unicode') for p in paras[:res['synlen']]])
    return res

def combine(item, template):
    resbody = template
    for k, v in item.items():
        resbody = resbody.replace('${}$'.format(k), str(v))
    res = dict(item)
    res['body'] = resbody
    return res
    
    
def main():
    basedir = os.path.dirname(os.path.realpath(__file__)) + '/../'
    pagesdir = basedir + 'pages/'
    postsdir = basedir + 'posts/'
    micropostsdir = basedir + 'microposts/'
    sitedir = basedir + 'site/'
    templatesdir = basedir + 'templates/'
    homepostnum = 5
    
    logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)s - %(message)s')
    
    posts = get_all_items(postsdir)
    posts.sort(key=lambda x: x['date'], reverse=True)
    for post in posts:
        post.setdefault('url', 'posts/{}.html'.format(post['name']))
        with open('{}{}.html'.format(templatesdir, post['template'])) as f:
            template = f.read()
        post = combine(post, template)
        save_to_html(post, sitedir)
    
    with open(templatesdir + 'barepost.html') as f:
        template = f.read()
    #headposts is the list of the first few posts, to be displayed on blog.html
    headposts = {'body' : ''.join([combine(post, template)['body'] for post in posts[:homepostnum]])}
    with open(templatesdir + 'blog.html') as f:
        template = f.read()
        headposts = combine(headposts, template)
        headposts['url'] = 'blog.html'
        save_to_html(headposts, sitedir)
    
    with open(templatesdir + 'postlistitem.html') as f:
        template = f.read()
    postlist = {'body': ''}
    for post in posts:
        postlist['body'] += combine(post, template)['body']
    with open(templatesdir + 'postlist.html') as f:
        template = f.read()
    postlist = combine(postlist, template)
    postlist['url'] = 'postlist.html'
    save_to_html(postlist, sitedir)
    
    pages = get_all_items(pagesdir)
    for page in pages:
        page.setdefault('url', page['name'] + '.html')
        with open('{}{}.html'.format(templatesdir, page['template'])) as f:
            template = f.read()
        page = combine(page, template)
        save_to_html(page, sitedir)
    
    microposts = get_all_items(micropostsdir)
    microposts.sort(key=lambda x: x['date'], reverse=True)
    with open(templatesdir + 'micropost.html') as f:
        template = f.read()
    allmposts = {'body':''}
    for micropost in microposts:
        allmposts['body'] += combine(micropost, template)['body']
    with open(templatesdir + 'microblog.html') as f:
        template = f.read()
    allmposts = combine(allmposts, template)
    allmposts['url'] = 'microblog.html'
    save_to_html(allmposts, sitedir)

    blog_feed = AtomFeed(title="Yuchen Pei's Blog",
                         feed_url="https://ypei.me/blog-feed.xml",
                         url="https://ypei.me",
                         author="Yuchen Pei")
    for post in posts:
        blog_feed.add(title=post["title"],
                      content=post["body"],
                      content_type="html",
                      author="Yuchen Pei",
                      url=post["url"],
                      updated=post["date"])
    blog_feed_item = {'body':blog_feed.to_string(), 'url': 'blog-feed.xml'}
    save_to_html(blog_feed_item, sitedir)

    microblog_feed = AtomFeed(title="Yuchen Pei's Microblog",
                         feed_url="https://ypei.me/microblog-feed.xml",
                         url="https://ypei.me",
                         author="Yuchen Pei")
    for micropost in microposts:
        microblog_feed.add(title=micropost["date"],
                      content=micropost["body"],
                      content_type="html",
                      author="Yuchen Pei",
                      url="microblog.html",
                      updated=micropost["date"])
    microblog_feed_item = {'body':microblog_feed.to_string(), 'url': 'microblog-feed.xml'}
    save_to_html(microblog_feed_item, sitedir)
        
def save_to_html(item, sitedir):
    path = sitedir + item['url']
    os.makedirs(os.path.dirname(path), exist_ok=True)
    logging.info('Saving to {}...'.format(path))
    with open(path, 'w') as f:
        f.write(item['body'])

def get_all_items(dir_):
    items = []
    for filename in os.listdir(dir_):
        ext = filename.split('.')[-1]
        path = dir_ + filename
        item = item_from_path(path)
        items.append(item)
    return items

if __name__ == "__main__":
    main()