Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 10:44:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Amazon.co.uk and amazon.de completely their search results.

Browse Source
This commit is contained in:
Charles Haley 2011-07-25 12:15:25 +01:00
parent b18c7713c0
commit 5e2fc67b98
2 changed files with 53 additions and 54 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
src/calibre/gui2/store/stores/amazon_de_plugin.py
View File

@ -45,24 +45,26 @@ class AmazonDEKindleStore(StorePlugin):
doc = html.fromstring(f.read()) doc = html.fromstring(f.read())
# Amazon has two results pages. # Amazon has two results pages.
is_shot = doc.xpath('boolean(//div[@id="shotgunMainResults"])') # 20110725: seems that is_shot is gone.
# Horizontal grid of books. # is_shot = doc.xpath('boolean(//div[@id="shotgunMainResults"])')
if is_shot: # # Horizontal grid of books.
data_xpath = '//div[contains(@class, "result")]' # if is_shot:
format_xpath = './/div[@class="productTitle"]/text()' # data_xpath = '//div[contains(@class, "result")]'
cover_xpath = './/div[@class="productTitle"]//img/@src' # format_xpath = './/div[@class="productTitle"]/text()'
# Vertical list of books. # cover_xpath = './/div[@class="productTitle"]//img/@src'
else: # # Vertical list of books.
data_xpath = '//div[@class="productData"]' # else:
data_xpath = '//div[contains(@class, "result") and contains(@class, "product")]'
format_xpath = './/span[@class="format"]/text()' format_xpath = './/span[@class="format"]/text()'
cover_xpath = '../div[@class="productImage"]/a/img/@src' cover_xpath = './/img[@class="productImage"]/@src'
# end is_shot else
for data in doc.xpath(data_xpath): for data in doc.xpath(data_xpath):
if counter <= 0: if counter <= 0:
break break
# Even though we are searching digital-text only Amazon will still # Even though we are searching digital-text only Amazon will still
# put in results for non Kindle books (author pages). Se we need # put in results for non Kindle books (author pages). So we need
# to explicitly check if the item is a Kindle book and ignore it # to explicitly check if the item is a Kindle book and ignore it
# if it isn't. # if it isn't.
format = ''.join(data.xpath(format_xpath)) format = ''.join(data.xpath(format_xpath))
@ -71,27 +73,17 @@ class AmazonDEKindleStore(StorePlugin):
# We must have an asin otherwise we can't easily reference the # We must have an asin otherwise we can't easily reference the
# book later. # book later.
asin_href = None asin = ''.join(data.xpath("@name"))
asin_a = data.xpath('.//div[@class="productTitle"]/a[1]')
if asin_a:
asin_href = asin_a[0].get('href', '')
m = re.search(r'/dp/(?P<asin>.+?)(/|$)', asin_href)
if m:
asin = m.group('asin')
else:
continue
else:
continue
cover_url = ''.join(data.xpath(cover_xpath)) cover_url = ''.join(data.xpath(cover_xpath))
title = ''.join(data.xpath('.//div[@class="productTitle"]/a/text()')) title = ''.join(data.xpath('.//div[@class="title"]/a/text()'))
price = ''.join(data.xpath('.//div[@class="newPrice"]/span/text()')) price = ''.join(data.xpath('.//div[@class="newPrice"]/span/text()'))
if is_shot: # if is_shot:
author = format.split(' von ')[-1] # author = format.split(' von ')[-1]
else: # else:
author = ''.join(data.xpath('.//div[@class="productTitle"]/span[@class="ptBrand"]/text()')) author = ''.join(data.xpath('.//div[@class="title"]/span[@class="ptBrand"]/text()'))
author = author.split('von ')[-1] author = author.split('von ')[-1]
counter -= 1 counter -= 1

55
src/calibre/gui2/store/stores/amazon_uk_plugin.py
View File

@ -42,48 +42,55 @@ class AmazonUKKindleStore(StorePlugin):
doc = html.fromstring(f.read()) doc = html.fromstring(f.read())
# Amazon has two results pages. # Amazon has two results pages.
is_shot = doc.xpath('boolean(//div[@id="shotgunMainResults"])') # 20110725: seems that is_shot is gone.
# Horizontal grid of books. # is_shot = doc.xpath('boolean(//div[@id="shotgunMainResults"])')
if is_shot: # # Horizontal grid of books.
data_xpath = '//div[contains(@class, "result")]' # if is_shot:
cover_xpath = './/div[@class="productTitle"]//img/@src' # data_xpath = '//div[contains(@class, "result")]'
# Vertical list of books. # format_xpath = './/div[@class="productTitle"]/text()'
else: # cover_xpath = './/div[@class="productTitle"]//img/@src'
data_xpath = '//div[contains(@class, "product")]' # # Vertical list of books.
cover_xpath = './div[@class="productImage"]/a/img/@src' # else:
data_xpath = '//div[contains(@class, "result") and contains(@class, "product")]'
format_xpath = './/span[@class="format"]/text()'
cover_xpath = './/img[@class="productImage"]/@src'
# end is_shot else
for data in doc.xpath(data_xpath): for data in doc.xpath(data_xpath):
if counter <= 0: if counter <= 0:
break break
# Even though we are searching digital-text only Amazon will still
# put in results for non Kindle books (author pages). So we need
# to explicitly check if the item is a Kindle book and ignore it
# if it isn't.
format = ''.join(data.xpath(format_xpath))
if 'kindle' not in format.lower():
continue
# We must have an asin otherwise we can't easily reference the # We must have an asin otherwise we can't easily reference the
# book later. # book later.
asin = ''.join(data.xpath('./@name')) asin = ''.join(data.xpath("@name"))
if not asin:
continue
cover_url = ''.join(data.xpath(cover_xpath)) cover_url = ''.join(data.xpath(cover_xpath))
title = ''.join(data.xpath('.//div[@class="productTitle"]/a/text()')) title = ''.join(data.xpath('.//div[@class="title"]/a/text()'))
price = ''.join(data.xpath('.//div[@class="newPrice"]/span/text()')) price = ''.join(data.xpath('.//div[@class="newPrice"]/span/text()'))
# if is_shot:
# author = format.split(' von ')[-1]
# else:
author = ''.join(data.xpath('.//div[@class="title"]/span[@class="ptBrand"]/text()'))
author = author.split('by ')[-1]
counter -= 1 counter -= 1
s = SearchResult() s = SearchResult()
s.cover_url = cover_url.strip() s.cover_url = cover_url.strip()
s.title = title.strip() s.title = title.strip()
s.author = author.strip()
s.price = price.strip() s.price = price.strip()
s.detail_item = asin.strip() s.detail_item = asin.strip()
s.formats = ''
if is_shot:
# Amazon UK does not include the author on the grid layout
s.author = ''
self.get_details(s, timeout)
if s.formats != 'Kindle':
continue
else:
author = ''.join(data.xpath('.//div[@class="productTitle"]/span[@class="ptBrand"]/text()'))
s.author = author.split(' by ')[-1].strip()
s.formats = 'Kindle' s.formats = 'Kindle'
yield s yield s