ViewVC Help

View File | Revision Log | View Changeset | Root Listing

root/Oni2/ValBot/Python/check_interwiki_links.py

Comparing ValBot/Python/check_interwiki_links.py (file contents):
Revision 1185 by iritscen, Tue Aug 15 02:03:16 2023 UTC vs.
Revision 1192 by iritscen, Mon Sep 16 23:08:26 2024 UTC

#	Line 62 | Line 62 | def find_section(page_text, page_name, p
62		# Read linked page to see if it really has this anchor link
63		soup = BeautifulSoup(page_text, 'html.parser')
64		found_section = False
65	<	for span_tag in soup.findAll('span'): # search for span with ID matching the section name
66	<	span_name = span_tag.get('id', None)
67	<	if span_name == anchor_name:
65	>	for the_tag in soup.findAll('span'): # search for span with ID matching the section name
66	>	tag_name = the_tag.get('id', None)
67	>	if tag_name == anchor_name:
68		found_section = True
69		break
70		if found_section == False:
71	<	for span_tag in soup.findAll('div'): # search for div with ID matching the section name
72	<	span_name = span_tag.get('id', None)
73	<	if span_name == anchor_name:
71	>	for the_tag in soup.findAll('div'): # search for div with ID matching the section name
72	>	tag_name = the_tag.get('id', None)
73	>	if tag_name == anchor_name:
74	>	found_section = True
75	>	break
76	>	if found_section == False:
77	>	for the_tag in soup.findAll('h2'): # search for h2 with ID matching the section name
78	>	tag_name = the_tag.get('id', None)
79	>	if tag_name == anchor_name:
80	>	found_section = True
81	>	break
82	>	if found_section == False:
83	>	for the_tag in soup.findAll('h3'): # search for h3 with ID matching the section name
84	>	tag_name = the_tag.get('id', None)
85	>	if tag_name == anchor_name:
86	>	found_section = True
87	>	break
88	>	if found_section == False:
89	>	for the_tag in soup.findAll('h4'): # search for h4 with ID matching the section name
90	>	tag_name = the_tag.get('id', None)
91	>	if tag_name == anchor_name:
92		found_section = True
93		break
94		if found_section == False:
#	Line 161 | Line 179 | def scan_for_interwiki_links(page_text,
179
180		for prefix in interwiki_prefixes:
181		# Isolate strings that start with "[[prefix:" and end with "|" or "]"
182	<	iw_link = "\[\[" + prefix + ":[^|\]]*(\||\])"
182	>	iw_link = r"\[\[" + prefix + r":[^|\]]*(\||\])"
183		for match in re.finditer(iw_link, page_text):
184		# Extract just the page title from this regex match
185		s = match.start() + 2 + len(prefix) + 1

Diff Legend

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