def _parse_tooltip_info(self, book_data, book_id, image_url):
'''Takes information retried from goodreads tooltips link and parses it'''
title = book_data.xpath('//a[contains(@class, "readable")]')
title = title[0].text if len(title) > 0 else None
authors = book_data.xpath('//a[contains(@class, "authorName")]')
authors = [authors[0].text] if len(authors) > 0 else None
rating_info = book_data.xpath(
'//div[@class="bookRatingAndPublishing"]/span[@class="minirating"]'
)
if len(rating_info) > 0:
rating_string = rating_info[0].text_content().strip().replace(
',', '').split()
rating = float(rating_string[rating_string.index('avg') - 1])
num_of_reviews = int(rating_string[-2])
else:
rating = None
num_of_reviews = None
try:
asin_elements = book_data.xpath(
'//a[contains(@class, "kindlePreviewButtonIcon")]/@href')
book_asin = urllib.parse.parse_qs(
urllib.parse.urlsplit(asin_elements[0]).query)["asin"][0]
except (KeyError, IndexError):
book_asin = None
# We should get the ASIN from the tooltips file, but just in case we'll
# keep this as a fallback (though this only works in some regions - just USA?)
if not book_asin:
asin_data_page = open_url(self._connection,
'/buttons/glide/' + book_id)
book_asin = GOODREADS_ASIN_PAT.search(asin_data_page)
if not book_asin:
return None
book_asin = book_asin.group(1)
desc = book_data.xpath(
'//div[@class="addBookTipDescription"]//span[not(contains(@id, "freeTextContainer"))]'
)
desc_backup = book_data.xpath(
'//div[@class="addBookTipDescription"]//span[contains(@id, "freeTextContainer")]'
)
if len(desc) > 0:
desc = re.sub(r'\s+', ' ', desc[0].text).strip()
elif len(desc_backup) > 0:
desc = re.sub(r'\s+', ' ', desc_backup[0].text).strip()
else:
return None
return {
'class': 'featuredRecommendation',
'asin': book_asin,
'title': title,
'authors': authors,
'imageUrl': image_url,
'description': desc,
'hasSample': False,
'amazonRating': rating,
'numberOfReviews': num_of_reviews
}
def _parse_tooltip_info(self, book_data, book_id, image_url):
'''Takes information retried from goodreads tooltips link and parses it'''
title = book_data.xpath('//a[contains(@class, "readable")]')
title = title[0].text if len(title) > 0 else None
authors = book_data.xpath('//a[contains(@class, "authorName")]')
authors = [authors[0].text] if len(authors) > 0 else None
rating_info = book_data.xpath('//div[@class="bookRatingAndPublishing"]/span[@class="minirating"]')
if len(rating_info) > 0:
rating_string = rating_info[0].text_content().strip().replace(',', '').split()
rating = float(rating_string[rating_string.index('avg')-1])
num_of_reviews = int(rating_string[-2])
else:
rating = None
num_of_reviews = None
try:
asin_elements = book_data.xpath('//a[contains(@class, "kindlePreviewButtonIcon")]/@href')
book_asin = urlparse.parse_qs(urlparse.urlsplit(asin_elements[0]).query)["asin"][0]
except (KeyError, IndexError):
book_asin = None
# We should get the ASIN from the tooltips file, but just in case we'll
# keep this as a fallback (though this only works in some regions - just USA?)
if not book_asin:
asin_data_page = open_url(self._connection, '/buttons/glide/' + book_id)
book_asin = GOODREADS_ASIN_PAT.search(asin_data_page)
if not book_asin:
return None
book_asin = book_asin.group(1)
desc = book_data.xpath('//div[@class="addBookTipDescription"]//span[not(contains(@id, "freeTextContainer"))]')
desc_backup = book_data.xpath('//div[@class="addBookTipDescription"]//span[contains(@id, "freeTextContainer")]')
if len(desc) > 0:
desc = re.sub(r'\s+', ' ', desc[0].text).strip()
elif len(desc_backup) > 0:
desc = re.sub(r'\s+', ' ', desc_backup[0].text).strip()
else:
return None
return {'class': 'featuredRecommendation',
'asin': book_asin,
'title': title,
'authors': authors,
'imageUrl': image_url,
'description': desc,
'hasSample': False,
'amazonRating': rating,
'numberOfReviews': num_of_reviews}
def search_for_asin_on_goodreads(self, url):
'''Searches for ASIN of book at given url'''
book_id_search = BOOK_ID_PAT.search(url)
if not book_id_search:
return None
book_id = book_id_search.group(1)
try:
response = open_url(self._connections['goodreads'], '/buttons/glide/' + book_id)
except PageDoesNotExist:
return None
book_asin_search = GOODREADS_ASIN_PAT.search(response)
if not book_asin_search:
return None
return book_asin_search.group(1)