-
Notifications
You must be signed in to change notification settings - Fork 2
/
html-clean.vim
286 lines (272 loc) · 6.17 KB
/
html-clean.vim
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
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
" to be placed in ~/.vim/plugin/
nnoremap <leader>k :call KindleGenPrep()<CR>
function! KindleGenPrep()
" Remove tags we know we don't want.
" Do this first, less other regex step on tag endings.
while search('<iframe')
execute 'normal dat'
endwhile
while search('<noscript')
execute 'normal dat'
endwhile
while search('<style')
execute 'normal dat'
endwhile
while search('<aside')
execute 'normal dat'
endwhile
" Only turn on for wikipedia
" while search('<sup ')
" execute 'normal dat'
" endwhile
while search('<figure')
execute 'normal dat'
endwhile
while search('<picture')
execute 'normal dat'
endwhile
" WARNING: This fails horribly against some sites, deleting everything.
while search('<script')
execute 'normal dat'
endwhile
" Handle some unicode and other oddities
if search('“')
execute '%s/“/\“/g'
endif
if search('”')
execute '%s/”/\”/g'
endif
if search('‘')
execute '%s/‘/\‘/g'
endif
if search('’')
execute '%s/’/\’/g'
endif
if search('—')
execute '%s/\s*—\s*/\—/g'
endif
if search('–')
execute '%s/–/\–/g'
endif
if search('…')
execute '%s/…/\…/g'
endif
if search(' ')
execute '%s/ / /g'
endif
if search('à')
execute '%s/à/\à/g'
endif
if search('á')
execute '%s/á/\á/g'
endif
if search('è')
execute '%s/è/\è/g'
endif
if search('é')
execute '%s/é/\é/g'
endif
if search('ì')
execute '%s/ì/\ì/g'
endif
if search('í')
execute '%s/í/\í/g'
endif
if search('ò')
execute '%s/ò/\ò/g'
endif
if search('ó')
execute '%s/ó/\ó/g'
endif
if search('ù')
execute '%s/ù/\ù/g'
endif
if search('ú')
execute '%s/ú/\ú/g'
endif
if search('À')
execute '%s/À/\À/g'
endif
if search('Á')
execute '%s/Á/\Á/g'
endif
if search('È')
execute '%s/È/\È/g'
endif
if search('É')
execute '%s/É/\É/g'
endif
if search('Ì')
execute '%s/Ì/\Ì/g'
endif
if search('Í')
execute '%s/Í/\Í/g'
endif
if search('Ò')
execute '%s/Ò/\Ò/g'
endif
if search('Ó')
execute '%s/Ó/\Ó/g'
endif
if search('Ù')
execute '%s/Ù/\Ù/g'
endif
if search('Ú')
execute '%s/Ú/\Ú/g'
endif
if search('ç')
execute '%s/ç/\ç/g'
endif
"" Convert Macrons for Romanized Japanese.
if search('ā')
execute '%s/ā/aa/g'
endif
if search('ē')
execute '%s/ē/ee/g'
endif
if search('ī')
execute '%s/ī/ii/g'
endif
if search('ō')
execute '%s/ō/ou/g'
endif
if search('ū')
execute '%s/ū/uu/g'
endif
if search('Ā')
execute '%s/Ā/Aa/g'
endif
if search('Ē')
execute '%s/Ē/Ee/g'
endif
if search('Ī')
execute '%s/Ī/Ii/g'
endif
if search('Ō')
execute '%s/Ō/Ou/g'
endif
if search('Ū')
execute '%s/Ū/Uu/g'
endif
" These don't display properly with the current kindlegen script
" :%s/ā/\ā/g
" :%s/ē/\ē/g
" :%s/ī/\ī/g
" :%s/ō/\ō/g
" :%s/ū/\ū/g
" :%s/Ā/\Ā/g
" :%s/Ē/\Ē/g
" :%s/Ī/\Ī/g
" :%s/Ō/\Ō/g
" :%s/Ū/\Ū/g
" TODO Search for more non-ASCII with /[^\x00-\x7F]
"" Clean up HTML Tags
if search('<body[^>]*>')
execute '%s/<body[^>]*>/<body>\r/g'
endif
if search('<h1 [^>]*>')
execute '%s/<h1 [^>]*>/\r<h1>/g'
endif
if search('<h2 [^>]*>')
execute '%s/<h2 [^>]*>/\r<h2>/g'
endif
if search('<h3 [^>]*>')
execute '%s/<h3 [^>]*>/\r<h3>/g'
endif
if search('<p [^>]*>')
execute '%s/<p [^>]*>/\r<p>/g'
endif
if search('<a [^>]*>')
execute '%s/<a [^>]*>//g'
endif
if search('</a>')
execute '%s#</a>##g'
endif
if search('<span[^>]*>')
execute '%s/<span[^>]*>//g'
endif
if search('</span>')
execute '%s#</span>##g'
endif
if search(' style="[^"]*"')
execute '%s/ style="[^"]*"//g'
endif
if search('<!--.\{-}-->')
execute '%s/<!--.\{-}-->//g'
endif
if search('<img .\{-}>')
execute '%s/<img .\{-}>//g'
endif
while search('<meta name="twitter')
execute '%s/<meta name="twitter[^>]*>//'
endwhile
while search('<meta property="fb')
execute '%s/<meta property="fb[^>]*>//'
endwhile
while search('<meta name="msapplication-')
execute '%s/<meta name="msapplication-[^>]*>//'
endwhile
while search('<meta name="apple-mobile-web-')
execute '%s/<meta name="apple-mobile-web-[^>]*>//'
endwhile
while search('<div class="ad-unit')
execute 'normal dat'
endwhile
" Strip references to external stylesheets.
if search('<link[^>]*>')
execute '%s/<link[^>]*>//g'
endif
" Japan Times
while search('<div class="teads-adCall')
execute 'normal dat'
endwhile
while search('div class="jt_content_ad')
execute 'normal dat'
endwhile
if search('ul class="single-sns-area"')
execute 'normal dat'
endif
" Remove everything after the article body.
if search('<div class="jtarticle_related"/')
execute '/<div class="jtarticle_related"/,/<\/body/-d'
endif
if search('[あ-を]')
execute '%s/<html.\{-}>/<html lang="ja">/'
endif
" New Yorker
while search('<div class="Callout')
execute 'normal dat'
endwhile
while search('<div id="RecircCarousel')
execute 'normal dat'
endwhile
while search('<ul class="ArticleSocial')
execute 'normal dat'
endwhile
while search('<div class="bxc')
execute 'normal dat'
endwhile
" Longreads
while search('<div class="featured-image-container">')
execute 'normal dat'
endwhile
if search('<div class="member-promo slim">')
execute 'normal dat'
endif
while search('<div class="in-story">')
execute 'normal dat'
endwhile
while search('<div data-shortcode="caption"')
execute 'normal dat'
endwhile
execute 'g/^\s*$/d'
if search('</body')
execute 's#</body#\r&#'
endif
" Risky, but almost always right. Disrespects tags, so run last.
execute '/<body/+,/<h1/-d'
call 1G<CR>
if search('<title')
" Just leave the focus on the <title> tag when we're done.
endif
endfunction