def get_book_data_from_site(self, url):
"""
args:
url (String):
Google Books book url to be parsed
returns:
SiteBookData (List):
format (String):
book_title (String):
book_image:~
book_image_url (String):
isbn_13 (String):
description (String):
series (String):~
volume_number (String):~
subtitle (String):~
authors (String):
book_id (String):
site_slug (String):
parse_status (String):~
url (String):
content (String):
ready_for_sale (boolean):~
extra:~
synopsis:
The purpose of this function is to parse a url of the
Audiobooks website. The url should be a specific book's url, in
order for the following function to work.
"""
response = requests.get(url)
format = None
book_title = None
book_image = None
book_image_url = None
isbn_13 = None
description = None
series = None
volume_number = None
subtitle = None
authors = None
book_id = None
site_slug = None
parse_status = None
book_url = None
content = None
ready_for_sale = None
extra = None
# book_title
book_title = self._get_book_title(response.content)
# book_image_url
book_image_url = self._get_book_image_url(response.content)
# book_image
book_image = Par_Scrape.get_book_image_from_image_url(book_image_url)
# book_isbn_13
isbn_13 = self._get_book_isbn_13()
# description
description = self._get_book_description(response.content)
# series
series = self._get_book_series()
# volume_number
volume_number = self._get_book_volume()
# subtitle
subtitle = self._get_book_subtitle()
# authors
authors = self._get_book_authors(response.content)
# book_url
book_url = url
# site_slug
site_slug = self._get_book_site_slug()
# book_id
book_id = self._get_book_id(response.url)
# format
format = self._get_book_format()
# content
content = response.content
# ready_for_sale
ready_for_sale = self._get_book_sale_status(response.content)
# parse_status
parse_status = Par_Scrape.parse_status([format, book_title, book_image, book_image_url, description, authors, book_id, site_slug, url, content, ready_for_sale])
SiteBookData = [format, book_title, book_image, book_image_url, isbn_13, description, series, volume_number, subtitle, authors, book_id, site_slug, parse_status, url, content, ready_for_sale, extra]
return SiteBookData
def get_book_data_from_site(self, url):
"""
args:
url (String):
Kobo book url to be parsed
returns:
SiteBookData (List):
format (String):
book_title (String):
book_image:~
book_image_url (String):
isbn_13 (String):
description (String):
series (String):~
volume_number (Int):~
subtitle (String):~
authors (String):
book_id:
site_slug (String):
parse_status (String):~
url (String):
content (String):
ready_for_sale (boolean):~
extra:~
synopsis:
The purpose of this function is to parse a url of the Kobo
website. The url should be a specific book's url, in order
for the following function to work. This function works with
both digital books and audio books.
"""
response = requests.get(url)
extra = {}
# book_title
book_title = self._get_book_title(response.content)
# book_image_url
book_image_url = self._get_book_image_url(response.content)
# book_image
book_image = Par_Scrape.get_book_image_from_image_url(book_image_url)
# isbn_13
isbn_13 = self._get_book_isbn_13(response.content)
# description
description = self._get_book_description(response.content)
# series
series = self._get_book_series(response.content)
# volume_number
volume_number = self._get_book_volume_number(response.content)
# subtitle
subtitle = self._get_book_subtitle(response.content)
# authors
authors = self._get_book_authors(response.content)
# url
url = self._get_book_url(response.content)
# site_slug
site_slug = self._get_book_site_slug()
# book_id
book_id = self._get_book_id(response.content)
# format
book_format = self._get_book_format(response.content)
# content
content = response.content
# ready_for_sale
ready_for_sale = self._get_book_availability(response.content)
# parse_status
parse_status = Par_Scrape.parse_status([
book_format, book_title, book_image, book_image_url, isbn_13,
description, authors, book_id, site_slug, url, content,
ready_for_sale
])
SiteBookData = [
book_format, book_title, book_image, book_image_url, isbn_13,
description, series, volume_number, subtitle, authors, book_id,
site_slug, parse_status, url, content, ready_for_sale, extra
]
return SiteBookData
def get_book_data_from_site(self, url):
content = self.__fetch__(url)
format = None
book_title = None
book_image = None
book_image_url = None
isbn_13 = None
description = None
series = None
volume_number = None
subtitle = None
authors = None
book_id = None
site_slug = None
parse_status = None
url = None
ready_for_sale = None
extra = None
#format
format = 'DIGITAL'
#book_title
book_title = self.__get_title__(content)
#subtitle
subtitle = self.__get_subtitle__(content)
#book_image_url
book_image_url = self.__get_book_image_url__(content)
#book_image
book_image = Par_Scrape.get_book_image_from_image_url(book_image_url)
#isbn_13
isbn_13 = self.__get_isbn__(content)
#description
description = self.__get_description__(content)
#authors
authors = self.__get_authors__(content)
#book_id
book_id = self.__get_book_id__(content)
#site_slug
site_slug = 'LC'
#url
url = self.__get_url__(content)
#ready_for_sale
ready_for_sale = True
#price = None
if subtitle == None:
parse_list = [format, book_title, book_image, book_image_url, isbn_13, description, authors, book_id, site_slug, url, content, ready_for_sale]
else:
parse_list = [format, book_title, book_image, book_image_url, isbn_13, description, subtitle, authors, book_id, site_slug, url, content, ready_for_sale]
#parse_status
parse_status = Par_Scrape.parse_status(parse_list)
SiteBookData = [format, book_title, book_image, book_image_url, isbn_13, description, series, volume_number, subtitle, authors, book_id, site_slug, parse_status, url, content, ready_for_sale, extra]
return SiteBookData