class Paragraph(Tagger):
remove_this = [
re.compile(r"[\s]*opis zawarto.ci[\s]*", re.I),
- re.compile(r"^[\s]*$")
+ re.compile(r"^[\s]*$"),
+ re.compile(r"http://pad.nowoczesnapolska.org.pl/p/slowniczek")
]
podrozdzial = [
re.compile(r"[\s]*(przebieg zaj..|opcje dodatkowe)[\s]*", re.I),
}
+class NotFound(Exception):
+ pass
+
+
def find_block(content, title_re, begin=-1, end=-1):
title_re = re.compile(title_re, re.I | re.UNICODE)
break
if rb >= 0:
return rb, i
+ raise NotFound()
def remove_block(content, title_re, removed=None):
rb, re = find_block(content, title_re)
-
if removed is not None and isinstance(removed, list):
removed += content[rb:re][:]
content[rb:re] = []
# some transformations
content = mark_activities(content)
content = mark_dictionary(content)
- content = remove_block(content, r"wykorzyst(yw)?ane metody[+ PA\[\].]*")
- content = remove_block(content, r"(pomoce|potrzebne materia.y)[+ PA\[\]]*")
+ try:
+ content = remove_block(content, r"wykorzyst(yw)?ane metody[+ PA\[\].]*")
+ except NotFound:
+ pass
+ try:
+ content = remove_block(content, r"(pomoce|potrzebne materia.y)[+ PA\[\]]*")
+ except NotFound:
+ pass
content = move_evaluation(content)
info = content.pop(0)