lectito 0.2.0

Article extraction and readability parsing for Lectito.
Documentation 
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

name = "wikipedia"
hosts = ["wikipedia.org"]
subdomains = true
content_roots = [
  "//div[contains(@class, 'mw-parser-output')]",
  "//div[@id='mw-content-text']",
  "//div[@id='bodyContent']",
]
remove_id_or_class = [
  "editsection",
  "mw-editsection",
  "jump-to-nav",
  "navbox",
  "catlinks",
  "printfooter",
  "infobox",
  "metadata",
  "ambox",
  "ombox",
  "tmbox",
  "siteSub",
  "contentSub",
  "mw-indicators",
  "hatnote",
  "navigation-not-searchable",
  "shortdescription",
  "noprint",
  "mw-empty-elt",
]
remove = [
  "//*[@id='toc']",
  "//div[@class='navbox']",
  "//div[@id='mw-content-text']//style",
  "//span[@class='mw-editsection']",
  "//span[@class='mw-editsection-bracket']",
  "//a[@class='mw-editsection']",
  "//div[contains(@class, 'infobox')]",
  "//table[contains(@class, 'infobox')]",
  "//table[contains(@class, 'navbox')]",
]

[metadata]
title = ["//h1[@id='firstHeading']"]
author = ["//div[@class='printfooter']//a[@rel='author']"]
date = ["//span[@id='mw-indicator-mw-dateformat']"]
site_name = "Wikipedia"
title_suffixes = [" - Wikipedia", " – Wikipedia"]

[cleanup]
enabled = false
prune = false

[fallback]
generic_on_empty = true