def main(rootpage, saveto):
wptools = WikiProjectTools()
bot = pywikibot.Site('en', 'wikipedia')
projects = []
output = 'These WikiProjects are not in any WikiProject meta-categories:\n\n'
# Generating category whitelist
wpcats = WikiProjectCategories()
tree = wpcats.generate()
whitelist = list(treegen(tree)) # Run through a simple generator function to produce a flat list
whitelist = tuple(set(whitelist)) # De-duplicating and making into a tuple
page = pywikibot.Page(bot, rootpage + '/All')
contents = mwph.parse(page.text)
contents = contents.filter_templates()
for t in contents:
if t.name.strip() == "WikiProject directory entry":
project = str(t.get('project').value).strip().replace(' ', '_')
# Give me a list of all the categories, as long as it's on the whitelist
query = wptools.query('wiki', "select distinct cl_to from categorylinks join page on categorylinks.cl_from=page.page_id where page_namespace in (4, 14) and page_title = {0} and cl_to in {1};".format('"' + project + '"', whitelist), None)
if len(query) == 0: # If page is in none of the whitelisted categories
output += "# [[Wikipedia:{0}|{0}]]\n".format(project.replace('_', ' '))
page = pywikibot.Page(bot, saveto)
page.text = output
page.save('Updating', minor=False)
def main(rootpage, saveto):
wptools = WikiProjectTools()
bot = pywikibot.Site('en', 'wikipedia')
projects = []
output = 'These WikiProjects are not in any WikiProject meta-categories:\n\n'
# Generating category whitelist
wpcats = WikiProjectCategories()
tree = wpcats.generate()
whitelist = list(treegen(tree)) # Run through a simple generator function to produce a flat list
whitelist = tuple(set(whitelist)) # De-duplicating and making into a tuple
page = pywikibot.Page(bot, rootpage + '/All')
contents = mwph.parse(page.text)
contents = contents.filter_templates()
for t in contents:
if t.name.strip() == "WikiProject directory entry small":
project = str(t.get('project').value).strip().replace(' ', '_')
# Give me a list of all the categories, as long as it's on the whitelist
query = wptools.query('wiki', "select distinct cl_to from categorylinks join page on categorylinks.cl_from=page.page_id where page_namespace in (4, 14) and page_title = {0} and cl_to in {1};".format('"' + project + '"', whitelist), None)
if len(query) == 0: # If page is in none of the whitelisted categories
output += "# [[Wikipedia:{0}|{0}]]\n".format(project.replace('_', ' '))
page = pywikibot.Page(bot, saveto)
page.text = output
page.save('Updating', minor=False)
def main(rootpage):
d = WikiProjectDirectory()
wptools = WikiProjectTools()
wpcats = WikiProjectCategories()
tree = wpcats.generate()
bot = pywikibot.Site('en', 'wikipedia')
directories = {}
directoryrow = {}
projects = []
# Generate directoryrows and projects lists based on the /All directory:
page = pywikibot.Page(bot, rootpage + '/All')
contents = mwph.parse(page.text)
contents = contents.filter_templates()
for t in contents:
if t.name.strip() == "WikiProject directory entry small":
name = str(t.get('project').value).strip().replace(' ', '_')
projects.append(name)
directoryrow[name] = str(t).replace('entry small', 'entry') + "\n"
# The rest of this stuff is copied from directory.py
index_primary = sorted([key for key in tree.keys()])
index_secondary = {}
indextext = "'''[[{0}/All|All WikiProjects]]'''\n\n".format(rootpage)
for firstlevel in tree.keys():
directories[firstlevel] = "={0}=\n".format(firstlevel.replace('_', ' '))
directories[firstlevel] += d.listpull(wptools, projects, directoryrow, firstlevel) # For immmedate subcats of WikiProjects_by_area
directories[firstlevel] += d.treeiterator(wptools, tree[firstlevel], projects, directoryrow, firstlevel) # For descendants of those immediate subcats.
index_secondary[firstlevel] = sorted([key for key in tree[firstlevel].keys()])
# Updating the directory index
for firstlevel in index_primary:
firstlevel_normalized = firstlevel.replace('_', ' ')
indextext += ";[[{0}/{1}|{1}]]".format(rootpage, firstlevel_normalized)
if len(tree[firstlevel]) > 0:
indextext += " : "
for secondlevel in index_secondary[firstlevel]:
indextext += "[[{0}/{1}#{2}|{2}]] – ".format(rootpage, firstlevel_normalized, secondlevel.replace('_', ' '))
indextext = indextext[:-3] # Truncates trailing dash and is also a cute smiley face
indextext += "\n\n"
saveindex = pywikibot.Page(bot, 'Template:WikiProject directory index')
saveindex.text = indextext
saveindex.save('Updating', minor=False, async=True)
# Generate directories and save!
for directory in directories.keys():
contents = directories[directory]
page = pywikibot.Page(bot, rootpage + "/" + directory)
if contents != page.text: # Checking to see if a change was made to cut down on API save queries
oldcontents = page.text
page.text = contents
page.save('Updating', minor=False, async=True)
def main(self, rootpage):
# Initializing...
bot = pywikibot.Site('en', 'wikipedia')
wptools = WikiProjectTools()
config = json.loads(wptools.query('index', 'select json from config;', None)[0][0])
# Get list of people who opted out
optout = pywikibot.Page(bot, 'User:Reports bot/Opt-out')
blacklist = []
regexes =[re.findall('\[\[User:(.*?)\|',optout.text,re.I), re.findall('\{\{user\|(.*?)\}\}',optout.text,re.I), re.findall('\[\[:User:(.*?)\]',optout.text,re.I), re.findall('\[\[:User talk:(.*?)\]',optout.text,re.I)]
for results in regexes:
for user in results:
blacklist.append(user)
# Bots are to be excluded
for result in wptools.query('wiki', "select user_name from user_groups left join user on user_id = ug_user where ug_group = 'bot';", None):
blacklist.append(result[0].decode('utf-8'))
# List of projects we are working on
# Methodology: List from Project Index + List from Formal Definition, minus duplicates
# This will cover all of our bases.
articles = {}
counter = 0
while True: # I am a bad man for doing this
query = wptools.query('index', 'select pi_page, pi_project from projectindex where pi_id > {0} and pi_id <= {1};'.format(counter, counter+1000000), None)
if len(query) == 0:
break
for pair in query:
# Normalizing by getting rid of namespace
page = pair[0]
page = page.replace('Draft_talk:', '')
page = page.replace('Talk:', '')
proj = pair[1][10:] # Normalizing by getting rid of "Wikipedia:"
try:
articles[proj].append(page)
except KeyError:
articles[proj] = [page]
counter += 1000000
projects = [project for project in articles.keys()]
q = ('select distinct page.page_title from page '
'join categorylinks on page.page_id = categorylinks.cl_from '
'left join redirect on page.page_id = redirect.rd_from '
'where page_namespace = 4 '
'and page_title not like "%/%" '
'and rd_title is null '
'and (cl_to in '
'(select page.page_title from page '
'where page_namespace = 14 and '
'page_title like "%\_WikiProjects" '
'and page_title not like "%\_for\_WikiProjects" '
'and page_title not like "%\_of\_WikiProjects") '
'or page_title like "WikiProject\_%");')
formaldefinition = wptools.query('wiki', q, None) # http://quarry.wmflabs.org/query/3509
for row in formaldefinition:
row = row[0].decode('utf-8')
if row not in projects:
projects.append(row)
projects.sort()
directories = {'All': ''} # All projects, plus subdirectories to be defined below.
directoryrow = {}
# Alright! Let's run some reports!
for project in projects:
# Seeding directory row and profile page
if project not in articles:
articles[project] = []
project_normalized = project.replace('_', ' ')
# List of active project participants (less blacklist)
wp_editors = []
start_date = time.strftime('%Y%m%d000000',time.gmtime(time.time()-(60*60*24*90))) # 90 days
end_date = time.strftime('%Y%m%d000000',time.gmtime(time.time())) # Today
query = "select rev_user_text from page left join revision on page_id = rev_page where (page_namespace = 4 OR page_namespace = 5) and (page_title like \"{0}/%%\" OR page_title = \"{0}\") and rev_timestamp > {1} and rev_timestamp < {2} group by rev_user_text HAVING count(*) > 1;".format(project, start_date, end_date)
for result in wptools.query('wiki', query, None):
if result[0] is not None:
user = result[0].decode('utf-8')
if user not in blacklist:
wp_editors.append(user)
wp_editors.sort()
# List of active subject area editors (less blacklist)
start_date = time.strftime('%Y%m%d000000',time.gmtime(time.time()-(60*60*24*30))) # 30 days
end_date = time.strftime('%Y%m%d000000',time.gmtime(time.time())) # Today
if len(articles[project]) > 0:
subject_editors = []
packages = []
for i in range(0, len(articles[project]), 10000):
packages.append(articles[project][i:i+10000])
counter = 0
for package in packages:
counter += 1
if len(package) > 1:
query_builder = 'select rev_user_text from page left join revision on page_id = rev_page where page_namespace in (0, 1, 118, 119) and page_title in {0} and rev_timestamp > {1} and rev_timestamp < {2} order by rev_user_text;'.format(tuple(package), start_date, end_date)
else:
query_builder = 'select rev_user_text from page left join revision on page_id = rev_page where page_namespace in (0, 1, 118, 119) and page_title = "{0}" and rev_timestamp > {1} and rev_timestamp < {2} order by rev_user_text;'.format(package[0], start_date, end_date)
for result in wptools.query('wiki', query_builder, None):
if result[0] is not None:
subject_editors.append(result[0].decode('utf-8'))
subject_editors = dict(Counter(subject_editors)) # Convert the list to a dictionary with username as key and edit count as value
subject_editors_filtered = []
for user in subject_editors.keys():
if user not in blacklist:
if subject_editors[user] > 4:
subject_editors_filtered.append(user)
subject_editors = subject_editors_filtered # And now assigned back.
subject_editors.sort()
else:
subject_editors = []
# Generate and Save Profile Page
wp_editors_formatted = ""
subject_editors_formatted = ""
if len(wp_editors) > 0:
for editor in wp_editors:
wp_editors_formatted += "\n* [[User:{0}|{0}]] ([[User talk:{0}|talk]])".format(editor)
else:
wp_editors_formatted = ""
if len(subject_editors) > 0 and len(subject_editors) < 3200:
for editor in subject_editors:
subject_editors_formatted += "\n* [[User:{0}|{0}]] ([[User talk:{0}|talk]])".format(editor)
else:
subject_editors_formatted = ""
profilepage = "{{{{WikiProject description page | project = {0} | list_of_active_wikiproject_participants = {1} | list_of_active_subject_area_editors = {2}}}}}".format(project_normalized, wp_editors_formatted, subject_editors_formatted)
page = pywikibot.Page(bot, rootpage + '/Description/' + project_normalized)
if profilepage != page.text: # Checking to see if a change was made to cut down on API queries
page.text = profilepage
page.save('Updating', minor=False, async=True, quiet=True)
# Construct directory entry
directoryrow[project] = "{{{{WikiProject directory entry | project = {0} | number_of_articles = {1} | wp_editors = {2} | scope_editors = {3}}}}}\n".format(project_normalized, len(articles[project]), len(wp_editors), len(subject_editors))
# Assign directory entry to relevant directory pages ("All entries" and relevant subdirectory pages)
for entry in sorted(directoryrow.items(), key=operator.itemgetter(1)): # Sorting into alphabetical order
directories['All'] += entry[1]
directories['All'] = "{{WikiProject directory top}}\n" + directories['All'] + "|}"
wpcats = WikiProjectCategories()
tree = wpcats.generate()
index_primary = sorted([key for key in tree.keys()])
index_secondary = {}
indextext = "'''[[{0}/All|All WikiProjects]]'''\n\n".format(rootpage)
for firstlevel in tree.keys():
directories[firstlevel] = "={0}=\n".format(firstlevel.replace('_', ' ' ))
directories[firstlevel] += self.listpull(wptools, projects, directoryrow, firstlevel) # For immmedate subcats of WikiProjects_by_area
directories[firstlevel] += self.treeiterator(wptools, tree[firstlevel], projects, directoryrow, firstlevel) # For descendants of those immediate subcats.
index_secondary[firstlevel] = sorted([key for key in tree[firstlevel].keys()])
# Updating the directory index
for firstlevel in index_primary:
firstlevel_normalized = firstlevel.replace('_', ' ')
indextext += ";[[{0}/{1}|{1}]]".format(rootpage, firstlevel_normalized)
if len(tree[firstlevel]) > 0:
indextext += " : "
for secondlevel in index_secondary[firstlevel]:
indextext += "[[{0}/{1}#{2}|{2}]] – ".format(rootpage, firstlevel_normalized, secondlevel.replace('_', ' '))
indextext = indextext[:-3] # Truncates trailing dash and is also a cute smiley face
indextext += "\n\n"
saveindex = pywikibot.Page(bot, 'Template:WikiProject directory index')
saveindex.text = indextext
saveindex.save('Updating', minor=False, async=True, quiet=True)
# Generate directories and save!
for directory in directories.keys():
contents = directories[directory]
page = pywikibot.Page(bot, rootpage + "/" + directory)
if contents != page.text: # Checking to see if a change was made to cut down on API save queries
oldcontents = page.text
page.text = contents
page.save('Updating', minor=False, async=True, quiet=True)
# Cleanup of obsolete description pages and "Related WikiProjects" pages
if directory == 'All':
oldcontents = mwph.parse(oldcontents)
oldcontents = oldcontents.filter_templates()
oldprojectlist = []
for t in oldcontents:
if t.name.strip() == "WikiProject directory entry":
oldprojectlist.append(str(t.get('project').value))
for oldproject in oldprojectlist:
oldproject = oldproject.strip().replace(' ', '_') # Normalizing
if oldproject not in projects:
deletethis = pywikibot.Page(bot, rootpage + '/Description/' + oldproject)
deletethis.text = "{{db-g6|rationale=A bot has automatically tagged this page as obsolete. This means that the WikiProject described on this page has been deleted or made into a redirect}}\n"
deletethis.save('Nominating page for deletion', minor=False, async=True, quiet=True)
deletethis = pywikibot.Page(bot, 'Wikipedia:Related WikiProjects/' + oldproject)
if deletethis.text != "":
deletethis.text = "{{db-g6|rationale=A bot has automatically tagged this page as obsolete. This means that the WikiProject described on this page has been deleted or made into a redirect}}\n"
deletethis.save('Nominating page for deletion', minor=False, async=True, quiet=True)
def main(rootpage):
d = WikiProjectDirectory()
wptools = WikiProjectTools()
wpcats = WikiProjectCategories()
tree = wpcats.generate()
bot = pywikibot.Site('en', 'wikipedia')
directories = {}
directoryrow = {}
projects = []
# Generate directoryrows and projects lists based on the /All directory:
page = pywikibot.Page(bot, rootpage + '/All')
contents = mwph.parse(page.text)
contents = contents.filter_templates()
for t in contents:
if t.name.strip() == "WikiProject directory entry":
name = str(t.get('project').value).strip().replace(' ', '_')
projects.append(name)
directoryrow[name] = str(t) + "\n"
# The rest of this stuff is copied from directory.py
index_primary = sorted([key for key in tree.keys()])
index_secondary = {}
indextext = "'''[[{0}/All|All WikiProjects]]'''\n\n".format(rootpage)
for firstlevel in tree.keys():
directories[firstlevel] = "={0}=\n".format(firstlevel.replace(
'_', ' '))
directories[firstlevel] += d.listpull(
wptools, projects, directoryrow,
firstlevel) # For immmedate subcats of WikiProjects_by_area
directories[firstlevel] += d.treeiterator(
wptools, tree[firstlevel], projects, directoryrow,
firstlevel) # For descendants of those immediate subcats.
index_secondary[firstlevel] = sorted(
[key for key in tree[firstlevel].keys()])
# Updating the directory index
for firstlevel in index_primary:
firstlevel_normalized = firstlevel.replace('_', ' ')
indextext += ";[[{0}/{1}|{1}]]".format(rootpage, firstlevel_normalized)
if len(tree[firstlevel]) > 0:
indextext += " : "
for secondlevel in index_secondary[firstlevel]:
indextext += "[[{0}/{1}#{2}|{2}]] – ".format(
rootpage, firstlevel_normalized,
secondlevel.replace('_', ' '))
indextext = indextext[:
-3] # Truncates trailing dash and is also a cute smiley face
indextext += "\n\n"
saveindex = pywikibot.Page(bot, 'Template:WikiProject directory index')
saveindex.text = indextext
saveindex.save('Updating', minor=False, async=True)
# Generate directories and save!
for directory in directories.keys():
contents = directories[directory]
page = pywikibot.Page(bot, rootpage + "/" + directory)
if contents != page.text: # Checking to see if a change was made to cut down on API save queries
oldcontents = page.text
page.text = contents
page.save('Updating', minor=False, async=True)
def main(self, rootpage):
# Initializing...
bot = pywikibot.Site('en', 'wikipedia')
wptools = WikiProjectTools()
config = json.loads(
wptools.query('index', 'select json from config;', None)[0][0])
# Get list of people who opted out
optout = pywikibot.Page(bot, 'User:Reports bot/Opt-out')
blacklist = []
regexes = [
re.findall('\[\[User:(.*?)\|', optout.text, re.I),
re.findall('\{\{user\|(.*?)\}\}', optout.text, re.I),
re.findall('\[\[:User:(.*?)\]', optout.text, re.I),
re.findall('\[\[:User talk:(.*?)\]', optout.text, re.I)
]
for results in regexes:
for user in results:
blacklist.append(user)
# Bots are to be excluded
for result in wptools.query(
'wiki',
"select user_name from user_groups left join user on user_id = ug_user where ug_group = 'bot';",
None):
blacklist.append(result[0].decode('utf-8'))
# List of projects we are working on
# Methodology: List from Project Index + List from Formal Definition, minus duplicates
# This will cover all of our bases.
articles = {}
counter = 0
while True: # I am a bad man for doing this
query = wptools.query(
'index',
'select pi_page, pi_project from projectindex where pi_id > {0} and pi_id <= {1};'
.format(counter, counter + 1000000), None)
if len(query) == 0:
break
for pair in query:
# Normalizing by getting rid of namespace
page = pair[0]
page = page.replace('Draft_talk:', '')
page = page.replace('Talk:', '')
proj = pair[1][
10:] # Normalizing by getting rid of "Wikipedia:"
try:
articles[proj].append(page)
except KeyError:
articles[proj] = [page]
counter += 1000000
projects = [project for project in articles.keys()]
q = ('select distinct page.page_title from page '
'join categorylinks on page.page_id = categorylinks.cl_from '
'left join redirect on page.page_id = redirect.rd_from '
'where page_namespace = 4 '
'and page_title not like "%/%" '
'and rd_title is null '
'and (cl_to in '
'(select page.page_title from page '
'where page_namespace = 14 and '
'page_title like "%\_WikiProjects" '
'and page_title not like "%\_for\_WikiProjects" '
'and page_title not like "%\_of\_WikiProjects") '
'or page_title like "WikiProject\_%");')
formaldefinition = wptools.query(
'wiki', q, None) # http://quarry.wmflabs.org/query/3509
for row in formaldefinition:
row = row[0].decode('utf-8')
if row not in projects:
projects.append(row)
projects.sort()
directories = {
'All': ''
} # All projects, plus subdirectories to be defined below.
directoryrow = {}
# Alright! Let's run some reports!
for project in projects:
# Seeding directory row and profile page
if project not in articles:
articles[project] = []
project_normalized = project.replace('_', ' ')
# List of active project participants (less blacklist)
wp_editors = []
start_date = time.strftime(
'%Y%m%d000000',
time.gmtime(time.time() - (60 * 60 * 24 * 90))) # 90 days
end_date = time.strftime('%Y%m%d000000',
time.gmtime(time.time())) # Today
query = "select rev_user_text from page left join revision on page_id = rev_page where (page_namespace = 4 OR page_namespace = 5) and (page_title like \"{0}/%%\" OR page_title = \"{0}\") and rev_timestamp > {1} and rev_timestamp < {2} group by rev_user_text HAVING count(*) > 1;".format(
project, start_date, end_date)
for result in wptools.query('wiki', query, None):
if result[0] is not None:
user = result[0].decode('utf-8')
if user not in blacklist:
wp_editors.append(user)
wp_editors.sort()
# List of active subject area editors (less blacklist)
start_date = time.strftime(
'%Y%m%d000000',
time.gmtime(time.time() - (60 * 60 * 24 * 30))) # 30 days
end_date = time.strftime('%Y%m%d000000',
time.gmtime(time.time())) # Today
if len(articles[project]) > 0:
subject_editors = []
packages = []
for i in range(0, len(articles[project]), 10000):
packages.append(articles[project][i:i + 10000])
counter = 0
for package in packages:
counter += 1
if len(package) > 1:
query_builder = 'select rev_user_text from page left join revision on page_id = rev_page where page_namespace in (0, 1, 118, 119) and page_title in {0} and rev_timestamp > {1} and rev_timestamp < {2} order by rev_user_text;'.format(
tuple(package), start_date, end_date)
else:
query_builder = 'select rev_user_text from page left join revision on page_id = rev_page where page_namespace in (0, 1, 118, 119) and page_title = "{0}" and rev_timestamp > {1} and rev_timestamp < {2} order by rev_user_text;'.format(
package[0], start_date, end_date)
for result in wptools.query('wiki', query_builder, None):
if result[0] is not None:
subject_editors.append(result[0].decode('utf-8'))
subject_editors = dict(
Counter(subject_editors)
) # Convert the list to a dictionary with username as key and edit count as value
subject_editors_filtered = []
for user in subject_editors.keys():
if user not in blacklist:
if subject_editors[user] > 4:
subject_editors_filtered.append(user)
subject_editors = subject_editors_filtered # And now assigned back.
subject_editors.sort()
else:
subject_editors = []
# Generate and Save Profile Page
wp_editors_formatted = ""
subject_editors_formatted = ""
if len(wp_editors) > 0:
for editor in wp_editors:
wp_editors_formatted += "\n* [[User:{0}|{0}]] ([[User talk:{0}|talk]])".format(
editor)
else:
wp_editors_formatted = ""
if len(subject_editors) > 0 and len(subject_editors) < 3200:
for editor in subject_editors:
subject_editors_formatted += "\n* [[User:{0}|{0}]] ([[User talk:{0}|talk]])".format(
editor)
else:
subject_editors_formatted = ""
profilepage = "{{{{WikiProject description page | project = {0} | list_of_active_wikiproject_participants = {1} | list_of_active_subject_area_editors = {2}}}}}".format(
project_normalized, wp_editors_formatted,
subject_editors_formatted)
page = pywikibot.Page(
bot, rootpage + '/Description/' + project_normalized)
if profilepage != page.text: # Checking to see if a change was made to cut down on API queries
page.text = profilepage
page.save('Updating', minor=False, async=True)
# Construct directory entry
directoryrow[
project] = "{{{{WikiProject directory entry | project = {0} | number_of_articles = {1} | wp_editors = {2} | scope_editors = {3}}}}}\n".format(
project_normalized, len(articles[project]),
len(wp_editors), len(subject_editors))
# Assign directory entry to relevant directory pages ("All entries" and relevant subdirectory pages)
for entry in sorted(
directoryrow.items(),
key=operator.itemgetter(1)): # Sorting into alphabetical order
directories['All'] += entry[1]
directories['All'] = "{{WikiProject directory top}}\n" + directories[
'All'] + "|}"
wpcats = WikiProjectCategories()
tree = wpcats.generate()
index_primary = sorted([key for key in tree.keys()])
index_secondary = {}
indextext = "'''[[{0}/All|All WikiProjects]]'''\n\n".format(rootpage)
for firstlevel in tree.keys():
directories[firstlevel] = "={0}=\n".format(
firstlevel.replace('_', ' '))
directories[firstlevel] += self.listpull(
wptools, projects, directoryrow,
firstlevel) # For immmedate subcats of WikiProjects_by_area
directories[firstlevel] += self.treeiterator(
wptools, tree[firstlevel], projects, directoryrow,
firstlevel) # For descendants of those immediate subcats.
index_secondary[firstlevel] = sorted(
[key for key in tree[firstlevel].keys()])
# Updating the directory index
for firstlevel in index_primary:
firstlevel_normalized = firstlevel.replace('_', ' ')
indextext += ";[[{0}/{1}|{1}]]".format(rootpage,
firstlevel_normalized)
if len(tree[firstlevel]) > 0:
indextext += " : "
for secondlevel in index_secondary[firstlevel]:
indextext += "[[{0}/{1}#{2}|{2}]] – ".format(
rootpage, firstlevel_normalized,
secondlevel.replace('_', ' '))
indextext = indextext[:
-3] # Truncates trailing dash and is also a cute smiley face
indextext += "\n\n"
saveindex = pywikibot.Page(bot, 'Template:WikiProject directory index')
saveindex.text = indextext
saveindex.save('Updating', minor=False, async=True)
# Generate directories and save!
for directory in directories.keys():
contents = directories[directory]
page = pywikibot.Page(bot, rootpage + "/" + directory)
if contents != page.text: # Checking to see if a change was made to cut down on API save queries
oldcontents = page.text
page.text = contents
page.save('Updating', minor=False, async=True)
# Cleanup of obsolete description pages and "Related WikiProjects" pages
if directory == 'All':
oldcontents = mwph.parse(oldcontents)
oldcontents = oldcontents.filter_templates()
oldprojectlist = []
for t in oldcontents:
if t.name.strip() == "WikiProject directory entry":
oldprojectlist.append(str(t.get('project').value))
for oldproject in oldprojectlist:
oldproject = oldproject.strip().replace(
' ', '_') # Normalizing
if oldproject not in projects:
deletethis = pywikibot.Page(
bot, rootpage + '/Description/' + oldproject)
deletethis.text = "{{db-g6|rationale=A bot has automatically tagged this page as obsolete. This means that the WikiProject described on this page has been deleted or made into a redirect}}\n"
deletethis.save('Nominating page for deletion',
minor=False,
async=True)
deletethis = pywikibot.Page(
bot,
'Wikipedia:Related WikiProjects/' + oldproject)
if deletethis.text != "":
deletethis.text = "{{db-g6|rationale=A bot has automatically tagged this page as obsolete. This means that the WikiProject described on this page has been deleted or made into a redirect}}\n"
deletethis.save('Nominating page for deletion',
minor=False,
async=True)