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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
|
#!/bin/python3
from contextlib import contextmanager
import colorama
import time
import datetime
import dateutil.tz
import bs4
import urllib.parse
import re
import lxml.etree as ET
@contextmanager
def init_colorama():
"""Set global foreground modifying ANSI codes.
BLACK, BLUE, CYAN, GREEN, MAGENTA, RED, WHITE, YELLOW, and RESET.
"""
# pylint: disable=exec-used,invalid-name
colorama.init()
for color, ansi in colorama.Fore.__dict__.items():
exec("global {0}; {0} = '{1}'".format(color, ansi))
yield
for color in colorama.Fore.__dict__:
exec("global {0}; {0} = ''".format(color))
colorama.deinit()
def current_datetime():
"""Return the current datetime, complete with tzinfo.
Precision is one second. Timezone is the local timezone.
"""
return datetime.datetime.fromtimestamp(round(time.time()),
dateutil.tz.tzlocal())
def absolutify_links(soup, baseurl):
"""Make links in an article absolute.
Parameters
----------
soup : bs4.BeautifulSoup
baseurl : str
"""
for tag in soup.find_all(lambda tag: tag.has_attr("href")):
tag["href"] = urllib.parse.urljoin(baseurl, tag["href"])
for tag in soup.find_all(lambda tag: tag.has_attr("src")):
tag["src"] = urllib.parse.urljoin(baseurl, tag["src"])
# MARKDOWN EXTENSION!
#
# See docstring of process_image_sizes for documentation.
# If matched, 1st group is width, 3rd group (optional) is height, and
# 4th group is actual text.
IMAGESIZE_EXTRACTOR = re.compile(r'\|(\d+)(x(\d+))?\|\s*(.*)')
def process_image_sizes(soup):
"""Process the image size Markdown extension.
Allows specifying image size in a Markdown image construct
![](). The syntax is:
where width and height are positive integers (xheight is optional),
and alt is the regular alt string (either plain or with some
Markdown formatting). alt string, as usual, is optional.
Examples:
"""
if not soup.article:
return
for img_tag in soup.article.find_all("img"):
if img_tag.has_attr("alt"):
match = IMAGESIZE_EXTRACTOR.match(img_tag["alt"])
if match:
width, _, height, realalt = match.groups()
img_tag["width"] = width
if height:
img_tag["height"] = height
img_tag["alt"] = realalt
# strip image specs from captions, if any
for caption in soup.article.select(".figure .caption"):
if hasattr(caption, "contents") and isinstance(caption.contents[0], str):
match = IMAGESIZE_EXTRACTOR.match(caption.contents[0])
if match:
caption.contents[0].replace_with(match.group(4))
def make_sitemap_url_element(link, updated=None, changefreq=None, priority=None):
"""Make a sitemap <url> element.
Parameters
----------
link : str or xml.etree.ElementTree.Element
If using an xml.etree.ElementTree.Element element, then it shall
be an atom:link element, e.g., <link href="http://zmwangx.github.io/"/>.
updated : datetime or xml.etree.ElementTree.Element, optional
If using an xml.etree.ElementTree.Element element, then it shall
be an atom:updated element, e.g.,
<updated>2015-05-05T22:38:42-07:00</updated>.
changefreq : {"always", "hourly", "daily", "weekly", "monthly", "yearly", "never"}, optional
priority : {1.0, 0.9, 0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1}, optional
"""
urlelem = ET.Element("url")
loc = ET.Element("loc")
loc.text = link.attrib["href"] if isinstance(link, ET._Element) else link
urlelem.append(loc)
if updated is not None:
lastmod = ET.Element("lastmod")
lastmod.text = (updated.text if isinstance(updated, ET._Element)
else updated.isoformat())
urlelem.append(lastmod)
if changefreq is not None:
changefreq_elem = ET.Element("changefreq")
changefreq_elem.text = changefreq
urlelem.append(changefreq_elem)
if priority is not None:
priority_elem = ET.Element("priority")
priority_elem.text = "%.1f" % priority
urlelem.append(priority_elem)
return urlelem
def link_img_tags(soup):
"""Convert each <img> tag in <article> to a link to its original."""
if not soup.article:
return
for img_tag in soup.article.find_all("img"):
a_tag = soup.new_tag("a", href=img_tag["src"], target="_blank")
a_tag.insert(0, copy.copy(img_tag))
img_tag.replace_with(a_tag)
def _pre_tag_insert_line_numbers(soup, pre_tag):
"""Insert line numbers to a pre tag."""
num_lines = len(pre_tag.text.split("\n"))
for line_number in range(1, num_lines + 1):
# line number divs will look like:
# <span class="line-number" data-line="1" style="top: 0em"><!----></span>
# <span class="line-number" data-line="2" style="top: 1.35em"><!----></span>
ln_tag = soup.new_tag("span")
ln_tag["class"] = "line-number"
ln_tag["data-line"] = line_number
ln_tag["style"] = "top: %.2fem" % ((line_number - 1) * 1.35)
# add a comment to the content of the span to suppress tidy5
# empty <span> tag warning
ln_tag.append(soup.new_string("", bs4.Comment))
pre_tag.code.append(ln_tag)
def process_footnote_backlinks(soup):
"""Add class attribute "footnotes-backlink" to each footnote backlink."""
for footnotes in soup.find_all("div", attrs={"class": "footnotes"}):
for fn_a_tag in footnotes.find_all(lambda tag:
tag.name == "a" and
tag.has_attr("href") and
tag["href"].startswith("#fnref") and
tag.string == "\u21A9"): # U+21A9: LEFTWARDS ARROW WITH HOOK
fn_a_tag["class"] = "footnotes-backlink"
fn_a_tag.string = "\u21A9\uFE0E" # U+FE0E: VARIATION SELECTOR-15
def postprocess_html_file(htmlfilepath):
"""Perform a series of postprocessing to an HTML file."""
with open(htmlfilepath, "r+", encoding="utf-8") as htmlfileobj:
soup = bs4.BeautifulSoup(htmlfileobj.read(), "lxml")
# a series of postprocessing (extensible)
process_image_sizes(soup)
link_img_tags(soup)
process_footnote_backlinks(soup)
# write back
htmlfileobj.seek(0)
htmlfileobj.write(str(soup))
htmlfileobj.truncate()
def static_vars(**kwargs):
def decorate(func):
for k in kwargs:
setattr(func, k, kwargs[k])
return func
return decorate
def sanitize(string):
"""Sanitize string (title) for URI consumption."""
if isinstance(string, bytes):
string = string.decode('utf-8')
# to lowercase
string = string.lower()
# strip all non-word, non-hyphen and non-whitespace characters
string = re.sub(r"[^\w\s-]", "", string)
# replace consecutive whitespaces with a single hyphen
string = re.sub(r"\s+", "-", string)
# percent encode the result
return urllib.parse.quote(string)
|
