def get_date(self): # Meta is often foobar because of proxy bugs
pre, po = self.get_permalink().split('?title=')
citelink = pre + '?title=Special:Cite&page=' + po
_, _, cite_HTML_u, resp = get_HTML(citelink)
day, month, year = re.search('''<li> Date of last revision: (\d{1,2}) (\w+) (\d\d\d\d)''', cite_HTML_u).groups()
month = fe.MONTH2DIGIT[month[0:3].lower()]
return '%d%02d%02d' %(int(year), int(month), int(day))
def __init__(self, url, comment):
print("Scraping default Web page;"),
self.url = url
self.comment = comment
try:
self.html_b, self.HTML_p, self.html_u, self.resp = get_HTML(
url, cache_control = 'no-cache')
except IOError:
self.html_b, self.HTML_p, self.html_u, self.resp = (None, None,
None, None)
self.text = None
if self.html_b:
self.text = get_text(url)
def get_date(self):
'''find date within <span id="mw-revision-date">19:09, 1 April 2008</span>'''
_, _, versioned_HTML_u, resp = get_HTML(self.get_permalink())
time, day, month, year = re.search('''<span id="mw-revision-date">(.*?), (\d{1,2}) (\w+) (\d\d\d\d)</span>''', versioned_HTML_u).groups()
month = fe.MONTH2DIGIT[month[0:3].lower()]
return '%d%02d%02d' %(int(year), int(month), int(day))
