| 1 | import os
|
|---|
| 2 |
|
|---|
| 3 | from urllib.parse import urljoin
|
|---|
| 4 |
|
|---|
| 5 | import pywikibot
|
|---|
| 6 | import re
|
|---|
| 7 |
|
|---|
| 8 | from pywikibot.bot import QuitKeyboardInterrupt
|
|---|
| 9 | from pywikibot import pagegenerators
|
|---|
| 10 | from pywikibot.tools.formatter import color_format
|
|---|
| 11 | from pywikibot.comms.http import fetch
|
|---|
| 12 | from pywikibot.specialbots import UploadRobot
|
|---|
| 13 | from bs4 import BeautifulSoup
|
|---|
| 14 |
|
|---|
| 15 | # Parallel arrays based on https://wiki.oni2.net/Special:Interwiki
|
|---|
| 16 | interwiki_prefixes = ('acronym', 'cache', 'commons', 'dictionary', 'google', 'metawikimedia', 'mw', 'wikibooks', 'wikidata', 'wikimedia', 'wikinews', 'wikipedia', 'wikiquote', 'wikisource', 'wikispecies', 'wikiversity', 'wikivoyage', 'wikt', 'wiktionary', 'wp')
|
|---|
| 17 |
|
|---|
| 18 | interwiki_urls = ('http://www.acronymfinder.com/~/search/af.aspx?string=exact&Acronym=', 'http://www.google.com/search?q=cache:', 'https://commons.wikimedia.org/wiki/', 'http://www.dict.org/bin/Dict?Database=*&Form=Dict1&Strategy=*&Query=', 'http://www.google.com/search?q=', 'https://meta.wikimedia.org/wiki/', 'https://www.mediawiki.org/wiki/', 'https://en.wikibooks.org/wiki/', 'https://www.wikidata.org/wiki/', 'https://foundation.wikimedia.org/wiki/', 'https://en.wikinews.org/wiki/', 'https://en.wikipedia.org/wiki/', 'https://en.wikiquote.org/wiki/', 'https://wikisource.org/wiki/', 'https://species.wikimedia.org/wiki/', 'https://en.wikiversity.org/wiki/', 'https://en.wikivoyage.org/wiki/', 'https://en.wiktionary.org/wiki/', 'https://en.wiktionary.org/wiki/', 'https://en.wikipedia.org/wiki/')
|
|---|
| 19 |
|
|---|
| 20 | pages_checked = 0
|
|---|
| 21 | iw_found = 0
|
|---|
| 22 | problems_found = 0
|
|---|
| 23 |
|
|---|
| 24 | # Searches the given page text for interwiki links
|
|---|
| 25 | def scan_for_iw_links(page_text):
|
|---|
| 26 | global pages_checked
|
|---|
| 27 | global iw_found
|
|---|
| 28 | global problems_found
|
|---|
| 29 | pages_checked = pages_checked + 1
|
|---|
| 30 | cur = 0
|
|---|
| 31 |
|
|---|
| 32 | for prefix in interwiki_prefixes:
|
|---|
| 33 | # Isolate strings that start with "[[prefix:" and end with "|" or "]"
|
|---|
| 34 | iw_link = "\[\[" + prefix + ":[^|\]]*(\||\])"
|
|---|
| 35 | for match in re.finditer(iw_link, page_text):
|
|---|
| 36 | # Extract just the page title from this regex match
|
|---|
| 37 | s = match.start() + 2 + len(prefix) + 1
|
|---|
| 38 | e = match.end() - 1
|
|---|
| 39 |
|
|---|
| 40 | # Sometimes we used a space char. instead of a '_', so fix that before querying
|
|---|
| 41 | page_title = page_text[s:e].replace(' ', '_')
|
|---|
| 42 |
|
|---|
| 43 | # Construct full URL for the particular wiki
|
|---|
| 44 | iw_url = interwiki_urls[cur] + page_title
|
|---|
| 45 | pywikibot.output('Found {0} link {1}.'.format(prefix, page_title))
|
|---|
| 46 | iw_found = iw_found + 1
|
|---|
| 47 |
|
|---|
| 48 | # Adjust URL if this is a foreign-language WP link
|
|---|
| 49 | if re.match("^[a-zA-Z]{2}:", page_title):
|
|---|
| 50 | lang_code = page_title[0:2] + "."
|
|---|
| 51 | # "wp:" is the Wikipedia: namespace, not a language
|
|---|
| 52 | if lang_code != "wp." and lang_code != "WP.":
|
|---|
| 53 | iw_url = iw_url.replace('en.', lang_code)
|
|---|
| 54 | iw_url = iw_url.replace(page_title[0:3], '')
|
|---|
| 55 |
|
|---|
| 56 | # Test the URL
|
|---|
| 57 | #pywikibot.output('Testing URL {}...'.format(iw_url))
|
|---|
| 58 | response = fetch(iw_url)
|
|---|
| 59 |
|
|---|
| 60 | # Redirects are followed automatically by fetch() and treated as "200"s, so the
|
|---|
| 61 | # way we tell that a redirect occurred is by checking the history
|
|---|
| 62 | if response.history != []:
|
|---|
| 63 | pywikibot.output('WARNING: Redirected from {}.'.format(response.history))
|
|---|
| 64 | problems_found = problems_found + 1
|
|---|
| 65 | elif response.status_code != 200:
|
|---|
| 66 | #pywikibot.output('WARNING: Got response code {}.'.format(response.status_code)) # commented out because fetch() already prints such a msg
|
|---|
| 67 | problems_found = problems_found + 1
|
|---|
| 68 | elif '#' in page_title:
|
|---|
| 69 | # Isolate section link
|
|---|
| 70 | pywikibot.output('Detected section link on page {0}.'.format(page_title))
|
|---|
| 71 | page_name, anchor_name = page_title.split('#')
|
|---|
| 72 |
|
|---|
| 73 | # Convert dot-notation hex entities to proper characters
|
|---|
| 74 | anchor_name = anchor_name.replace('.22', '"')
|
|---|
| 75 | anchor_name = anchor_name.replace('.27', '\'')
|
|---|
| 76 | anchor_name = anchor_name.replace('.28', '(')
|
|---|
| 77 | anchor_name = anchor_name.replace('.29', ')')
|
|---|
| 78 |
|
|---|
| 79 | # Read linked page to see if it really has this anchor link
|
|---|
| 80 | soup = BeautifulSoup(response.text, 'html.parser')
|
|---|
| 81 | found_section = False
|
|---|
| 82 | for tag in soup.findAll('a'):
|
|---|
| 83 | link = tag.get('href', None)
|
|---|
| 84 | if not link:
|
|---|
| 85 | #pywikibot.output('It is not a link.')
|
|---|
| 86 | continue
|
|---|
| 87 | #pywikibot.output('Got link {0}.'.format(link))
|
|---|
| 88 | if not link.startswith('#'):
|
|---|
| 89 | continue
|
|---|
| 90 |
|
|---|
| 91 | if link == '#' + anchor_name:
|
|---|
| 92 | pywikibot.output('Found section link!')
|
|---|
| 93 | found_section = True
|
|---|
| 94 | break
|
|---|
| 95 | if found_section == False:
|
|---|
| 96 | pywikibot.output('Could not find section {0} on page {1}.'.format(anchor_name, page_name))
|
|---|
| 97 | problems_found = problems_found + 1
|
|---|
| 98 | cur = cur + 1
|
|---|
| 99 |
|
|---|
| 100 | def main(*args):
|
|---|
| 101 | cat_name = ''
|
|---|
| 102 | page_name = ''
|
|---|
| 103 |
|
|---|
| 104 | local_args = pywikibot.handle_args(args)
|
|---|
| 105 | genFactory = pagegenerators.GeneratorFactory()
|
|---|
| 106 |
|
|---|
| 107 | for arg in local_args:
|
|---|
| 108 | if arg.startswith('-cat:'):
|
|---|
| 109 | cat_name = arg[5:]
|
|---|
| 110 | elif arg.startswith('-page:'):
|
|---|
| 111 | page_name = arg[6:]
|
|---|
| 112 |
|
|---|
| 113 | site = pywikibot.Site()
|
|---|
| 114 |
|
|---|
| 115 | # This line of code enumerates the methods in the 'page' class
|
|---|
| 116 | #pywikibot.stdout(format(dir(page)))
|
|---|
| 117 |
|
|---|
| 118 | if cat_name != '':
|
|---|
| 119 | cat_obj = pywikibot.Category(site, cat_name)
|
|---|
| 120 | generator = pagegenerators.CategorizedPageGenerator(cat_obj, recurse=True)
|
|---|
| 121 | for page in pagegenerators.PreloadingGenerator(generator, 100):
|
|---|
| 122 | pywikibot.stdout('Checking page {0}'.format(page.title()))
|
|---|
| 123 | scan_for_iw_links(page.text)
|
|---|
| 124 | elif page_name != '':
|
|---|
| 125 | page = pywikibot.Page(site, page_name)
|
|---|
| 126 | pywikibot.stdout('Checking page {0}'.format(page.title()))
|
|---|
| 127 | scan_for_iw_links(page.text)
|
|---|
| 128 |
|
|---|
| 129 | global pages_checked
|
|---|
| 130 | global iw_found
|
|---|
| 131 | global problems_found
|
|---|
| 132 | pywikibot.stdout('Checked {0} page(s) and found {1} interwiki link(s) with {2} problem(s).'.format(pages_checked, iw_found, problems_found))
|
|---|
| 133 |
|
|---|
| 134 | if __name__ == '__main__':
|
|---|
| 135 | main()
|
|---|
