def retrieve(self,text):
bi = BookInfo()
bi.authors, bi.title = Retriever.get_authors_and_title(text)
bi.pagelink = self.link
bi.links['txt'] = self.link
tag = Retriever.get_tag_by_link(self.link)
bi.tags = [tag] if tag else []
return bi
def execute(self,html):
soup = get_soup(html)
book_info = BookInfo()
book_info.title = self.description['title']
book_info.authors = [ "%s %s %s" % (self.description['firstname'],self.description['middlename'], self.description['lastname']) ]
book_info.pagelink = self.link
book_info.language = self.description['language']
book_info.summary = Retriever.get_summary(soup)
book_info.links = Retriever.get_links(soup, self.link)
book_info.tags = Retriever.get_tags(soup)
book_info.image = Retriever.get_picture(soup, self.link, self.description['ID'])
self.tasks = [ BookSavingTask(book_info) ]
return True
def get_book_info(soup):
div = soup.find('div', {'class' : 'book_body'})
book_info = BookInfo()
field = Retriever.get_field(div, u'Название:')
if field:
match = re.match(u"Название:(.+)", field.text)
if match and match.groups():
book_info.title = match.groups(0)[0]
#author
field = Retriever.get_field(div, u'Автор:')
book_info.authors = [ anchor.text for anchor in field.findAll('a')] if field else []
#summary
field = Retriever.get_field(div, u'Описание книги:')
if field and field.p:
book_info.summary = field.p.text
#images
img = soup.find('img', {'class' : 'thumb'})
book_info.image = img['src'] if img else None
#tags
field = Retriever.get_field(div, u'Жанр:')
if field:
book_info.tags = [ tag.text for tag in field.findAll('a')]
#links
field = Retriever.get_field(div, u'Скачать книгу бесплатно:')
if field:
for link_anchor in field.findAll('a'):
book_info.links [link_anchor.text] = link_anchor['href']
return book_info
def get_bookinfo(entry):
book_info = BookInfo()
book_info.title = entry.title.text
book_info.authors = [entry.author.findChild().text]
# language
language = entry.find("dc:language") or entry.find("dcterms:language")
book_info.language = language.text if language else "?"
# links
for format in Retriever.known_formats:
link_to_book_tag = entry.find("link", type="application/" + format)
if link_to_book_tag:
book_info.links[format] = link_to_book_tag["href"]
if not book_info.links:
return None
# summary
summary = entry.find("content") or entry.find("summary")
book_info.summary = summary.text if summary else None
# tags
categories = entry.findAll("category")
if categories:
for category in categories:
label = None
if category.has_key("label"):
label = category["label"]
elif category.has_key("term"):
label = category["term"]
if label:
book_info.tags.append(label)
return book_info
def get_bookinfo_from_db(id):
bookinfo = BookInfo()
book = Book.objects.get(id=id)
bookinfo.title = book.title
bookinfo.authors = [ author.name for author in book.author.all() ]
bookinfo.pagelink = book.pagelink
bookinfo.language = book.language.short
annotations = book.annotation_set.all()
if annotations:
bookinfo.summary = annotations[0]
for bookfile in book.book_file.all():
bookinfo.links[bookfile.type] = bookfile.link
bookinfo.tags = [ tag.name for tag in book.tag.all()]
bookinfo.image = book.image.name if book.image else None
return bookinfo
def get_book_info(soup):
book_info = BookInfo()
book_info.title = Retriever.get_field(soup, u'Название:')
authors = Retriever.get_field(soup, u'Автор\(ы\):')
if authors:
book_info.authors = [ authors ]
book_info.summary = Retriever.get_field(soup, u'Описание:')
book_info.language = Retriever.get_field(soup, u'Язык:')
format = Retriever.get_field(soup, u'Формат:')
link = Retriever.get_field(soup, u'Ссылка 1:', False).a['href']
book_info.links = {format : link}
return book_info
def get_bookinfo_from_tag_dl(dl):
bookinfo = BookInfo()
anchors = dl.dt.li.findAll("a")
author_anchor = anchors[0]
title_anchor = anchors[1]
bookinfo.links["shtml"] = title_anchor["href"]
bookinfo.authors = [author_anchor.text]
bookinfo.title = title_anchor.text
bookinfo.language = "ru"
dd = dl.findAll("dd")
if dd:
bookinfo.summary = dd[0].text
return bookinfo