class WikiProvider(LookupProvider):
'''Concrete provider which provides web results from Wikipedia.
'''
def __init__(self):
'''Initialize WikiProvider with a MediaWiki instance.
'''
self._wiki = MediaWiki(
user_agent="word_tools (https://github.com/ncdulo/word_tools")
LookupProvider.__init__(self)
def lookup(self, word, limit=0):
'''Yield str results for `word` up to `limit`. When `limit <= 0`,
default to `limit = 3`.
'''
# Default to a limit of three results. Once the re-write of CLI
# is complete, this should be updated, and likely removed
if limit <= 0:
limit = 3
try:
for result in self._wiki.opensearch(word, results=limit):
title, _, url = result
summary = self._wiki.page(title).summarize(chars=200)
output = title + ' (' + url + ')\n' + summary
yield output
except exceptions.DisambiguationError as e:
print('''Search term disambiguous. There are some issues in the way
results are returned. Wikipedia suggests the following page
names. These may not be correct. This is a known issue.
''')
print(e)
def lookup_wiktionary(word):
logger = logging.getLogger(__name__)
try:
wikipedia = MediaWiki()
wikipedia.set_api_url('https://en.wiktionary.org/w/api.php')
matches = {}
search_results = wikipedia.opensearch(word)
if len(search_results) > 0:
page_title = search_results[0][0]
page = wikipedia.page(page_title)
parts = page.content.split("\n")
i = 0
while i < len(parts):
definition = ""
part = parts[i].strip()
if part.startswith("=== Verb ===") or part.startswith(
"=== Noun ===") or part.startswith(
"=== Adjective ==="):
#print(part)
# try to skip the first two lines after the marker
if (i + 1) < len(parts):
definition = parts[i + 1]
if (i + 2) < len(parts) and len(parts[i + 2].strip()) > 0:
definition = parts[i + 2]
if (i + 3) < len(parts) and len(parts[i + 3].strip()) > 0:
definition = parts[i + 3]
if part.startswith(
"=== Adjective ===") and not 'adjective' in matches:
matches['adjective'] = definition
if part.startswith("=== Noun ===") and not 'noun' in matches:
matches['noun'] = definition
if part.startswith("=== Verb ===") and not 'verb' in matches:
matches['verb'] = definition
i = i + 1
final = ""
# prefer verb, noun then adjective
if matches.get('adjective', False):
final = matches.get('adjective')
if matches.get('noun', False):
final = matches.get('noun')
if matches.get('verb', False):
final = matches.get('verb')
# strip leading bracket comment
if final[0] == '(':
close = final.index(")") + 1
final = final[close:]
matches['definition'] = final
return matches
except:
e = sys.exc_info()
logger.debug(e)
def lookup(self, word):
wikipedia = MediaWiki()
#wikipedia.set_api_url('https://en.wikpedia.org/w/api.php')
summary = ''
search_results = wikipedia.opensearch(word)
if len(search_results) > 0:
page_title = search_results[0][0]
page = wikipedia.page(page_title)
parts = page.summary.split('. ')
summary = parts[0]
return summary
def find_short_meaning(search):
try:
wikipedia = MediaWiki()
meaning = wikipedia.page(search.title())
except DisambiguationError:
return find_alter_meaning(search)
else:
if search.lower() != meaning.title.lower():
return find_alter_meaning(search)
def_meaning = meaning.summarize()
return str(def_meaning + "link for further read: " +
wikipedia.opensearch(f'{meaning.title}', results=1)[0][2])
def wiki_search(query: str, lang='ru', unquote_percent_encoded=False) -> str:
# Default using wikipedia
from mediawiki import MediaWiki
wikipedia = MediaWiki(lang=lang)
result = wikipedia.opensearch(query, results=1)
if not result:
return ''
_, text, url = result[0]
if unquote_percent_encoded:
from urllib.parse import unquote
url = unquote(url)
return '{} ({})'.format(text, url)
def lookup_wikipedia(word):
logger = logging.getLogger(__name__)
try:
wikipedia = MediaWiki()
#wikipedia.set_api_url('https://en.wikpedia.org/w/api.php')
final = {}
search_results = wikipedia.opensearch(word, results=1)
logger.debug('WIKI SEARCH RESTULS')
logger.debug(search_results)
if len(search_results) > 0:
logger.debug('WIKI SEARCH RESTULS2')
page_title = search_results[0][0]
page_link = search_results[0][2]
link_parts = page_link.split("/")
link_title = link_parts[-1]
logger.debug('WIKI SEARCH RESTULS3' + link_title)
# lookup summary/answer
wiki_wiki = wikipediaapi.Wikipedia('en')
page_py = wiki_wiki.page(link_title)
if page_py and page_py.exists():
logger.debug('WIKI PAGE SEARCH RESTULS')
logger.debug(page_py)
# fact fields
final['thing'] = page_title
final['answer'] = page_py.summary
# plus
final['url'] = page_py.canonicalurl
# page = wikipedia.page(link_title)
# logger.debug('WIKI SEARCH RESTULS single')
# logger.debug(page_py)
# parts = page.summary.split('. ')
# summary = parts[0]
#summary = page.summary
logger.debug('WIKI PAGE SEARCH RESTULS FINAL')
logger.debug(final)
return final
except:
e = sys.exc_info()
logger.debug(e)
async def send_to_wikipedia(word, site):
logger = logging.getLogger(__name__)
try:
# lookup in wiktionary and send display message
wikipedia = MediaWiki()
wikipedia.set_api_url('https://en.wiktionary.org/w/api.php')
matches = {}
search_results = wikipedia.opensearch(word)
# logger.debug(search_results)
if len(search_results) > 0:
page_title = search_results[0][0]
page_link = search_results[0][2]
# page = wikipedia.page(page_title)
# parts = page.content.split("\n")
# logger.debug([page_title,page_link])
await publish('hermod/' + site + '/display/show',
{'frame': page_link})
except:
e = sys.exc_info()
logger.debug(e)
class WikiApi:
def __init__(self):
self.wikipedia = MediaWiki(lang='ru')
self.wikiquote = CustomWikiEngine(url="https://{lang}.wikiquote.org/w/api.php",
lang='ru')
def quotes(self, *words):
results = []
for word in words:
titles = self.wikiquote.quotes(word, results=2)
results += titles
return results
def quote_page(self, title):
response = {}
try:
response = self.wikiquote.page(title=title)
except Exception as e:
logging.exception(e)
return response
def get_pages_by_categories(self, category, limit=10):
# https://en.wikipedia.org/w/api.php?a
# ction=query&
# generator=categorymembers&
# gcmlimit=100&
# gcmtitle=Category:American%20male%20film%20actors&
# prop=pageimages&
# pilimit=100
S = requests.Session()
URL = "https://ru.wikipedia.org/w/api.php"
PARAMS = {
'action': "query",
'generator': "categorymembers",
'gcmtitle': category,
'gcmlimit': limit,
'format': "json"
}
R = S.get(url=URL, params=PARAMS)
DATA = R.json()
titles = []
if 'query' in DATA and DATA['query'] and DATA['query']['pages']:
titles = [value['title'] for key, value in DATA['query']['pages'].items()]
return titles
def movies(self):
# https://ru.wikipedia.org/w/api.php?format=xml&action=query&list=embeddedin&einamespace=0&eilimit=500&eititle=Template:Infobox_film
pass
def search(self, *words):
results = []
for word in words:
response = self.wikipedia.search(word, results=4)
short_descriptions = response
results += short_descriptions
return results
def opensearch(self, *words):
results = []
for word in words:
response = self.wikipedia.opensearch(word)
results += response
return results
def parse(self, *pages):
results = []
for page in pages:
try:
response = self.wikipedia.page(title=page)
content = response.content
sections = re.split(r'==.+?==', content)
if sections:
summary = sections[0]
results.append(summary)
section_headers = re.findall(r'== \w+ ==', content)
if '== Сюжет ==' in section_headers:
index = section_headers.index('== Сюжет ==') + 1
if len(sections) > index:
plot = sections[index]
results.append(plot)
except Exception as e:
logging.error(e)
return results
class Plugin(PluginBase):
def __init__(self):
super().__init__()
from os import path
from json import loads
self.plugin_name = path.basename(__file__).rsplit('.')[0]
self.metadata = PluginUtilityService.process_metadata(f'plugins/extensions/{self.plugin_name}')
self.plugin_cmds = loads(self.metadata.get(C_PLUGIN_INFO, P_PLUGIN_CMDS))
self.osrs_wiki_url = self.metadata[C_PLUGIN_SET][P_WIKI_URL]
self.osrs_user_agent = self.metadata[C_PLUGIN_SET][P_USER_AGENT]
rprint(
f"{self.metadata[C_PLUGIN_INFO][P_PLUGIN_NAME]} v{self.metadata[C_PLUGIN_INFO][P_PLUGIN_VERS]} Plugin Initialized.")
try:
self.osrs_wiki = MediaWiki(url=self.osrs_wiki_url, user_agent=self.osrs_user_agent)
except Exception:
rprint(f"{self.plugin_name} Plugin could not be initialized.")
def quit(self):
dprint(f"Exiting {self.plugin_name} plugin...", origin=L_SHUTDOWN)
log(INFO, f"Exiting {self.plugin_name} plugin...", origin=L_SHUTDOWN)
def get_metadata(self):
return self.metadata
def process(self, text):
message = text.message.strip()
message_parse = message[1:].split(' ', 1)
command = message_parse[0]
if command == "price":
if not privileges.plugin_privilege_checker(text, command, self.plugin_name):
return
if self.osrs_wiki is None:
self.osrs_wiki = MediaWiki(url=self.metadata[C_PLUGIN_SETTINGS][P_WIKI_URL], user_agent=self.metadata[C_PLUGIN_SETTINGS][P_USER_AGENT])
parameter = message_parse[1]
search_criteria = self.manage_search_criteria(parameter)
all_item_data = self.pull_json(search_criteria)
if all_item_data is not None:
item_data_formatted = "<br><font color='{}'>Item:</font> {}<br>Avg. Price: {:,} coins.".format(global_settings.cfg[C_PGUI_SETTINGS][P_TXT_HEAD_COL], all_item_data['name'].title(), all_item_data['overall_average'])
item_data_formatted += "<br><font color='{}'>Buy Avg. Price:</font> {:,} coins.".format(global_settings.cfg[C_PGUI_SETTINGS][P_TXT_IND_COL], all_item_data['buy_average'])
item_data_formatted += "<br><font color='{}'>Sell Avg. Price:</font> {:,} coins.".format(global_settings.cfg[C_PGUI_SETTINGS][P_TXT_IND_COL], all_item_data['sell_average'])
global_settings.gui_service.quick_gui(item_data_formatted, text_type='header', box_align='left')
else:
global_settings.gui_service.quick_gui(f"Could not find '{search_criteria}' on the grand exchange.", text_type='header', box_align='left')
elif command == "osrs":
if not privileges.plugin_privilege_checker(text, command, self.plugin_name):
return
if self.osrs_wiki is None:
self.osrs_wiki = MediaWiki(url=self.metadata[C_PLUGIN_SETTINGS][P_WIKI_URL], user_agent=self.metadata[C_PLUGIN_SETTINGS][P_USER_AGENT])
parameter = message_parse[1]
global_settings.gui_service.quick_gui(f"Searching the OSRS Wiki for: {parameter}", text_type='header', box_align='left')
search_results = self.osrs_wiki.opensearch(parameter)
formatted_results = self.get_choices(search_results)
if formatted_results is None:
global_settings.gui_service.quick_gui("OSRS Wiki Results:<br>No search results found.", text_type='header', box_align='left')
return
global_settings.gui_service.quick_gui(f"OSRS Wiki Results:<br>{formatted_results}\n", text_type='header', box_align='left')
elif command == "quest":
if not privileges.plugin_privilege_checker(text, command, self.plugin_name):
return
if self.osrs_wiki is None:
self.osrs_wiki = MediaWiki(url=self.metadata[C_PLUGIN_SETTINGS][P_WIKI_URL], user_agent=self.metadata[C_PLUGIN_SETTINGS][P_USER_AGENT])
parameter = message_parse[1]
global_settings.gui_service.quick_gui(f"Searching the OSRS Wiki for: {parameter}", text_type='header', box_align='left')
try:
page = self.osrs_wiki.page(parameter)
except exceptions.PageError:
global_settings.gui_service.quick_gui("OSRS Wiki Results:<br>No search results found.", text_type='header', box_align='left')
return
if "Quests" not in page.categories and page is not None:
global_settings.gui_service.quick_gui("OSRS Wiki Results:<br>No search results found.", text_type='header', box_align='left')
return
soup = BeautifulSoup(page.html, 'html.parser')
tds = soup.find_all('td', class_="questdetails-info")
final_text = f"<br><u><font color='{global_settings.cfg[C_PGUI_SETTINGS][P_TXT_IND_COL]}'>{page.title} Quest Summary</font></u><br><a href='{page.url}'>{page.url}</a>"
for i, item in enumerate(tds):
f_text = ""
if i == 0:
f_text = "<br><font color='{global_settings.cfg[C_PGUI_SETTINGS][P_TXT_HEAD_COL]}'>Start Point:</font><br>"
elif i == 1:
f_text = "<br><font color='{global_settings.cfg[C_PGUI_SETTINGS][P_TXT_HEAD_COL]}'>Difficulty:</font><br>"
elif i == 2:
f_text = "<br><font color='{global_settings.cfg[C_PGUI_SETTINGS][P_TXT_HEAD_COL]}'>Description:</font><br>"
elif i == 3:
f_text = "<br><font color='{global_settings.cfg[C_PGUI_SETTINGS][P_TXT_HEAD_COL]}'>Length:</font><br>"
elif i == 4:
f_text = "<br><font color='{global_settings.cfg[C_PGUI_SETTINGS][P_TXT_HEAD_COL]}'>Requirements:</font><br>"
elif i == 5:
f_text = "<br><font color='{global_settings.cfg[C_PGUI_SETTINGS][P_TXT_HEAD_COL]}'>Items Required:</font><br>"
elif i == 6:
f_text = "<br><font color='{global_settings.cfg[C_PGUI_SETTINGS][P_TXT_HEAD_COL]}'>Enemies To Defeat:</font><br>"
counter = 0
if i == 4 or i == 6:
uls = item.find_all('ul')
if uls is not None:
for ul in uls:
lis = ul.find_all('li')
for li in lis:
f_text += f"<font color='{global_settings.cfg[C_PGUI_SETTINGS][P_TXT_IND_COL]}'>-- </font>{li.text}<br>"
else:
f_text += "UNAVAILABLE"
elif i == 5:
uls = item.find_all('ul')
if uls is not None:
for ul in item.find_all('ul'):
lis = ul.find_all('li')
for li in lis:
f_text += f"<font color='{global_settings.cfg[C_PGUI_SETTINGS][P_TXT_IND_COL]}'>-- </font>{li.text}<br>"
if counter == 0:
f_text += f"<br><font color='{global_settings.cfg[C_PGUI_SETTINGS][P_TXT_HEAD_COL]}'>Recommended Items:</font><br>"
counter += 1
else:
f_text += "UNAVAILABLE"
else:
f_text += tds[i].text
final_text += f_text
global_settings.gui_service.quick_gui(final_text, text_type='header', box_align='left')
def get_choices(self, search_results):
list_urls = "<br>"
if search_results:
for i, item in enumerate(search_results):
completed_url = item[2]
list_urls += f"<font color='{global_settings.cfg[C_PGUI_SETTINGS][P_TXT_IND_COL]}'>[{i}]</font>: <a href='{completed_url}'>[{completed_url}]</a><br>"
else:
return None
return list_urls
def manage_search_criteria(self, search_criteria):
try:
return int(search_criteria)
except ValueError:
return search_criteria.lower()
def pull_json(self, search_criteria):
return_item = None
with urllib.request.urlopen(self.metadata[C_PLUGIN_SETTINGS][P_MAIN_URL]) as url:
json_data = json.loads(url.read().decode('utf-8').lower())
for section in json_data:
json_item = json_data[section]
if json_item.get('name') == search_criteria or json_item.get('id') == search_criteria:
return_item = json_item
return return_item
def make_opensearch(self, data):
wikipedia = MediaWiki()
wikipedia_opensearch_result = wikipedia.opensearch(str(data))
return wikipedia_opensearch_result
from mediawiki import MediaWiki
wikipedia = MediaWiki()
res = wikipedia.opensearch("ru:Малоохтинский парк")
print(res)
