def reset(self):
ArticleParser.reset(self)
self.issue = None
self.text_frame = None
self.a_text = self.append_text
self.issue_text = self.append_text
self.issues = {}
def end_div(self):
if self.text_frame == "author":
self.get_text()
self.text_frame = "blank"
elif self.text_frame == "blank":
self.get_text()
self.text_frame = "pages"
self.a_frame = "pages"
elif self.text_frame == "pages":
text = self.get_text()
match = re.compile("(\d+.*)PDF", re.DOTALL).search(text)
if not match: #just ignore this
self.article = None
self.a_frame = None
self.text_frame = None
ArticleParser.end_div(self)
return
text = match.groups()[0]
match = map(Page, re.compile("\d+").findall(text))
if len(match) == 1:
page = match[0]
self.article.set_pages(page, page)
elif len(match) == 2:
start, end = match
self.article.set_pages(start, end)
else:
raise HTMLException("%s is not valid text input for APS parser" % text)
self.text_frame = None
self.a_frame = None
ArticleParser.end_div(self)
def reset(self):
ArticleParser.reset(self)
#treat paragraph breaks as divisions
self.start_p = self.start_div
self.end_p = self.end_div
self.title_text = self.append_text
self.citation_text = self.append_text
def reset(self):
ArticleParser.reset(self)
#treat paragraph breaks as divisions
self.start_p = self.start_div
self.end_p = self.end_div
self.citation = []
self.title = []
def reset(self):
ArticleParser.reset(self)
#treat paragraph breaks as divisions
self.start_p = self.start_div
self.end_p = self.end_div
self.pages_text = self.append_text
self.title_text = self.append_text
self.author_text = self.append_text
self.blank_text = self.append_text
def reset(self):
ArticleParser.reset(self)
self.url = None
def reset(self):
ArticleParser.reset(self)
self.title_text = self.append_text
self.pages_text = self.append_text
self.citation_text = self.append_text
def reset(self):
ArticleParser.reset(self)
self.page_text = self.append_text
self.a_text = self.append_text
self.url = None
