from mwclient import Site
language = 'is'
SITE = Site(f'{language}.wikipedia.org')
ALL_PAGES = SITE.allpages()
for page in ALL_PAGES:
print(page.name)
import re
from simple_salesforce import Salesforce
api = ConfluenceAPI('admin', '123@qwe', 'http://127.0.0.1:8090')
FileOut = open('PagesBUSList.txt', 'w')
UserAgent = 'Wiki_parser/0.1 run by DremSama'
site = Site(('http', 'wiki.support.veeam.local'),
path='/',
clients_useragent=UserAgent)
sf = Salesforce(username='******',
password='******',
security_token='dNr44yHsFXaSuRmKXunWPlzS')
PagesList = []
PagesBUGSList = []
for page in site.allpages():
PagesList.append(page)
if page.name.startswith('Bug') or page.name.startswith('bug'):
print('----------------------------------')
BugID = re.match(r'[A-z,a-z]ug\b.(\d*)[-|\s]*(.*)', page.page_title)
if BugID:
BugID_NUM = BugID.group(1)
BugID_SUBJECT = BugID.group(2)
textALL = page.text(0)
if not textALL:
print('ERROR: Page "' + page.name + '" has no text')
elif textALL.startswith('#REDIRECT'):
print('Page "' + page.name + '" is only a redirect page, skipping')
else:
print(page.name)
BugCaseID = re.findall(r"'''Case ID: '''(\d*)", textALL)
def Hikes():
site = Site(('http', 'www.oregonhikers.org/'))
counter = 0
hikes = []
for item in site.allpages():
page_text = item.text()
if '[[Category:Hikes]]' in page_text:
if '[[Category:Portland Area]]' in page_text:
counter += 1
if (counter == 30):
break
m = re.search('(?<=latitude=).{6}', page_text)
n = re.search('(?<=longitude=).{7}', page_text)
p = re.search('(?<=Distance\|)(.*)(?=miles}})', page_text)
q = re.search('(?<=Difficulty\|)(.*)(?=}})', page_text)
lat = 0.0
long = 0.0
distance = 0.0
difficulty = "None given"
if (m):
try:
lat = float(m.group())
except:
print("no lat given")
if (n):
try:
long = float(n.group())
except:
print("no long given")
if (p):
try:
distance = float(p.group())
except:
print("invalid distance")
if (q):
difficulty = str(q.group())
hike = Hike(lat, long)
l = re.search('Description ===(?s)(.*?)===\s', page_text,
re.MULTILINE)
entry = ""
if l:
page_text = l.group()
by_line = []
by_line = page_text.splitlines()
for line in by_line:
try:
line = str(line)
line = re.sub('[\[]', '', line)
line = re.sub('[\]]', '', line)
line = re.sub('[\}]', '', line)
line = re.sub('[\{]', '', line)
except:
print("page not cast")
#print(line)
if line:
if not line.startswith(
('Description', '===', 'TripReports',
'RelatedDiscussions', '*', 'Source', '(', '=',
'<')):
entry = entry + "\n" + line
hike.desc = entry
hike.name = item.page_title
hike.distance = distance
hike.difficulty = difficulty
if entry:
hikes.append(hike)
print("added: " + hike.name)
print("lat: " + str(hike.lat))
print("long: " + str(hike.long))
return hikes