class Parser(object):
""" A Wikipedia parser. Captures a parsed Wikipedia page. """
def __init__(self, url):
self.html = Html(url = url)
self.html_lines = self.html.lines()
self.name = self.get_name()
self.tables = {}
def get_name(self):
""" Returns the name of the Wikipedia page. """
for line in self.html_lines:
if line.has(r'<h1.*?>(.*?)</h1>'):
return line.strip_tags()
def table_at_line(self, n):
""" Returns the table at line n. """
assert self.html_lines[n].has(r'<table.*?>')
table_lines = self.html_lines[n].string
n += 1
while not self.html_lines[n].has(r'</table>'):
table_lines += '\n' + self.html_lines[n].string
n += 1
table_lines += '\n' + self.html_lines[n].string
return Html(table_lines)
def name_of_table_at_line(self, n):
""" Returns the title of the table at line n. """
assert self.html_lines[n].has(r'<table.*?>')
while not self.html_lines[n].has(r'<h.*?>(.*?)</h.*?>'):
n -= 1
return self.html_lines[n].strip_tags().replace('[edit]', '')
def all_tables(self):
tables, i = [], 0
while i < len(self.html_lines):
if self.html_lines[i].has(r'<table.*?>'):
name = self.name_of_table_at_line(i)
table = self.table_at_line(i)
if name not in ['Bibliography', 'See also']:
tables.append(Table(name, table))
i += len(table.lines())
i += 1
return tables
def __init__(self, url):
self.html = Html(url = url)
self.html_lines = self.html.lines()
self.name = self.get_name()
self.tables = {}