ViewVC Help

View File | Revision Log | View Changeset | Root Listing

root/Oni2/ValBot/Python/check_intrawiki_section_links.py

Comparing ValBot/Python/check_intrawiki_section_links.py (file contents):
Revision 1194 by iritscen, Mon Nov 18 04:00:08 2024 UTC vs.
Revision 1205 by iritscen, Mon Feb 9 03:24:16 2026 UTC

#	Line 15 | Line 15 | import re
15
16		from pywikibot.bot import QuitKeyboardInterrupt
17		from pywikibot import pagegenerators
18	–	from pywikibot.tools.formatter import color_format
18		from pywikibot.comms.http import fetch
19		from pywikibot.specialbots import UploadRobot
20		from bs4 import BeautifulSoup
#	Line 78 | Line 77 | def find_section(page_text, page_name, p
77		search_terms.pop(0)
78		if search_terms[-1].startswith('-'):
79		search_terms.pop()
80	<	# Remake text directive with the terms separated by spaces as they should be in the page text
80	>	# Remake text directive with the terms separated by spaces as they should be in the page
81	>	# text
82		newSep = ' '
83		search_string = newSep.join(search_terms)
84		if debug: pywikibot.stdout('         Converted text fragment to string "{}".'.format(search_string))
#	Line 113 | Line 113 | def find_section(page_text, page_name, p
113		elif debug and print_result:
114		pywikibot.stdout('   The section "{0}" was found on page "{1}".'.format(anchor_name, target_page_name_human))
115
116	<	# For a link that redirected us to another page, extract the name of the target page from
117	<	# the target page's source
116	>	# For a link that redirected us to another page, extract the name of the target page from the
117	>	# target page's source
118		def find_canonical_link(page_text, page_name, page_slug):
119		# Extract link from this markup which contains name of redirected-to page:
120		# <link rel="canonical" href="https://en.wikipedia.org/wiki/Page_name"/>
#	Line 128 | Line 128 | def find_canonical_link(page_text, page_
128		else:
129		canonical_name = canonical_name[:tag_end]
130		if len(canonical_name) > 100:
131	<	# Certain things can cause the trim to fail; report error and avoid slamming the
132	<	# output with massive page source from a failed trim
131	>	# Certain things can cause the trim to fail; report error and avoid slamming the output
132	>	# with massive page source from a failed trim
133		pywikibot.stdout('   ERROR: The link "{}" is a redirect to "{2}…" (string overflow).'.format(page_slug, canonical_name[:100]))
134		errors_issued = errors_issued + 1
135		else:
#	Line 151 | Line 151 | def test_intrawiki_link(iw_url, page_nam
151		# One way we tell that a redirect occurred is by checking fetch's history, as it
152		# automatically follows redirects. This will catch formal redirects which come from pages
153		# such as Special:PermanentLink.
154	<	if response.history != []:
155	<	permalink1 = 'Special:PermanentLink/'.lower()
156	<	permalink2 = 'Special:Permalink/'.lower()
157	<	page_slug_lower = page_slug.lower()
158	<	if page_slug_lower.startswith(permalink1) or page_slug_lower.startswith(permalink2):
159	<	if debug:
160	<	possibly_print(page_name)
161	<	pywikibot.stdout('   Got redirection code "{0}" for permanent revision link "{1}". Checking the target page….'.format(response.history[0], page_slug))
162	<	find_canonical_link(response.text, page_name, page_slug)
163	<	else:
154	>	permalink1 = 'Special:PermanentLink/'.lower()
155	>	permalink2 = 'Special:Permalink/'.lower()
156	>	page_slug_lower = page_slug.lower()
157	>	if response.history != [] and (page_slug_lower.startswith(permalink1) or page_slug_lower.startswith(permalink2)):
158	>	if debug:
159		possibly_print(page_name)
160	<	pywikibot.stdout('   ERROR: Unrecognized type of redirection (code "{0}") for link "{1}". You should check the link manually.'.format(response.history[0], page_slug))
161	<	advice_issued += 1
162	<	elif response.status_code != 200:
163	<	possibly_print(page_name)
164	<	pywikibot.stdout('   ERROR: Got response code {0} on URL {1}. The target page may not exist.'.format(response.status_code, iw_url))
165	<	errors_issued += 1
166	<	# However the usual way that a redirect occurs is that MediaWiki redirects us sneakily
172	<	# using JavaScript, while returning code OK 200 as if the link was correct; this happens
173	<	# when a redirect page is accessed. We must detect these soft redirects by looking at the
174	<	# page source to find the redirect note inserted at the top of the page for the reader.
160	>	pywikibot.stdout('   Got redirection code "{0}" for permanent revision link "{1}". Checking the target page….'.format(response.history[0], page_slug))
161	>	find_canonical_link(response.text, page_name, page_slug)
162	>	# However the usual way that a redirect occurs is that a redirect page is visited and
163	>	# MediaWiki sends us to the new page using JavaScript while returning code 301. Formerly it
164	>	# used to return 200 as if the link was correct, so rather than looking for code 301 we
165	>	# detect these soft redirects by looking at the page source to find the redirect note that
166	>	# gets inserted at the top of the page for the reader.
167		elif 'Redirected from <a' in response.text:
168		if debug:
169		possibly_print(page_name)
170		pywikibot.stdout('   Got silently redirected by link "{}". Checking the target page….'.format(page_slug))
171		find_canonical_link(response.text, page_name, page_slug)
172	+	# This handles response codes other than 200 and 301 (301 is returned in the above case of a
173	+	# silent redirect)
174	+	elif response.status_code != 200:
175	+	possibly_print(page_name)
176	+	pywikibot.stdout('   ERROR: Got response code {0} on URL {1}. The target page may not exist.'.format(response.status_code, iw_url))
177	+	errors_issued += 1
178		else: # URL is OK, so proceed
179		find_section(response.text, page_name, page_slug, False)
180

Diff Legend

–	Removed lines
+	Added lines
<	Changed lines (old)
>	Changed lines (new)