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 1192 by iritscen, Mon Sep 16 23:08:26 2024 UTC vs.
Revision 1194 by iritscen, Mon Nov 18 04:00:08 2024 UTC

#	Line 58 | Line 58 | def possibly_print(page_name):
58		# Search a page for the section specified in the link
59		def find_section(page_text, page_name, page_slug, print_result):
60		global errors_issued
61	<
62	<	# Isolate section link
61	>	found_section = False
62	>
63	>	# Isolate section link or text fragment link
64		target_page_name, anchor_name = page_slug.split('#', 1)
65		target_page_name_human = target_page_name.replace('_', ' ')
66	<	if debug: pywikibot.stdout('         Searching for section link {} on page.'.format(anchor_name))
67	<
68	<	# Read linked page to see if it really has this anchor link
69	<	soup = BeautifulSoup(page_text, 'html.parser')
70	<	found_section = False
71	<	for span_tag in soup.findAll('span'):
72	<	span_name = span_tag.get('id', None)
73	<	if span_name == anchor_name:
74	<	if debug and not print_result: pywikibot.stdout('         Found section in a span!')
66	>
67	>	# First check if this is a text fragment directive, and look for it if so
68	>	if anchor_name.startswith(':~:text='):
69	>	if debug: pywikibot.stdout('         Found text fragment directive {} from URL {}.'.format(anchor_name, page_slug))
70	>	anchor_name = anchor_name[8:]
71	>	# We're only checking the first text directive, so strip add'l ones if present
72	>	addl_fragment = anchor_name.find('&text=')
73	>	if addl_fragment != -1:
74	>	anchor_name = anchor_name[:addl_fragment]
75	>	search_terms = anchor_name.split(',')
76	>	# Delete prefix and suffix terms because they aren't needed
77	>	if search_terms[0].endswith('-'):
78	>	search_terms.pop(0)
79	>	if search_terms[-1].startswith('-'):
80	>	search_terms.pop()
81	>	# Remake text directive with the terms separated by spaces as they should be in the page text
82	>	newSep = ' '
83	>	search_string = newSep.join(search_terms)
84	>	if debug: pywikibot.stdout('         Converted text fragment to string "{}".'.format(search_string))
85	>	if search_string in page_text:
86		found_section = True
87	<	break
87	>	if debug and not print_result: pywikibot.stdout('         Found text fragment!')
88	>
89	>	# If we're still here, it's a section link; read linked page to see if it really has this
90	>	# anchor link
91	>	if found_section == False:
92	>	if debug: pywikibot.stdout('         Searching for section link {} on page.'.format(anchor_name))
93	>	soup = BeautifulSoup(page_text, 'html.parser')
94	>	# Search for a span with this ID
95	>	for span_tag in soup.findAll('span'):
96	>	span_name = span_tag.get('id', None)
97	>	if span_name == anchor_name:
98	>	if debug and not print_result: pywikibot.stdout('         Found section in a span!')
99	>	found_section = True
100	>	break
101		if found_section == False:
102		# Search for a div with this ID
103		for span_tag in soup.findAll('div'):
#	Line 127 | Line 152 | def test_intrawiki_link(iw_url, page_nam
152		# automatically follows redirects. This will catch formal redirects which come from pages
153		# such as Special:PermanentLink.
154		if response.history != []:
130	–
155		permalink1 = 'Special:PermanentLink/'.lower()
156		permalink2 = 'Special:Permalink/'.lower()
157		page_slug_lower = page_slug.lower()

Diff Legend

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