Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 18:54:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Make amazon EU store plugins more robust against amazon reporting zero books found.

Browse Source
This commit is contained in:
Charles Haley 2013-04-01 10:44:35 +02:00
parent 40dbdc75ae
commit 7169ffed0a
5 changed files with 290 additions and 230 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

104
src/calibre/gui2/store/stores/amazon_de_plugin.py
View File

@ -7,7 +7,7 @@ __license__ = 'GPL 3'
__copyright__ = '2011, John Schember <john@nachtimwald.com>' __copyright__ = '2011, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
import re import re, time
from contextlib import closing from contextlib import closing
from lxml import html from lxml import html
@ -29,6 +29,9 @@ class AmazonEUBase(StorePlugin):
For comments on the implementation, please see amazon_plugin.py For comments on the implementation, please see amazon_plugin.py
''' '''
MAX_SEARCH_ATTEMPTS = 5
SLEEP_BETWEEN_ATTEMPTS = 3
def open(self, parent=None, detail_item=None, external=False): def open(self, parent=None, detail_item=None, external=False):
store_link = self.store_link % self.aff_id store_link = self.store_link % self.aff_id
@ -42,62 +45,71 @@ class AmazonEUBase(StorePlugin):
br = browser() br = browser()
counter = max_results counter = max_results
with closing(br.open(url, timeout=timeout)) as f: loops = 0
doc = html.fromstring(f.read())#.decode('latin-1', 'replace')) while counter == max_results and loops < self.MAX_SEARCH_ATTEMPTS:
br = browser()
if loops > 0:
print ("Retry getbooks search", self.__class__.__name__, counter,
max_results, loops)
time.sleep(self.SLEEP_BETWEEN_ATTEMPTS)
loops += 1
data_xpath = '//div[contains(@class, "prod")]' with closing(br.open(url, timeout=timeout)) as f:
format_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()' doc = html.fromstring(f.read())#.decode('latin-1', 'replace'))
asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and contains(@class, "bld")]/text()'
for data in doc.xpath(data_xpath): data_xpath = '//div[contains(@class, "prod")]'
if counter <= 0: format_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()'
break asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and contains(@class, "bld")]/text()'
# Even though we are searching digital-text only Amazon will still for data in doc.xpath(data_xpath):
# put in results for non Kindle books (authors pages). Se we need if counter <= 0:
# to explicitly check if the item is a Kindle book and ignore it break
# 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 # Even though we are searching digital-text only Amazon will still
# book later. # put in results for non Kindle books (authors pages). Se we need
asin = data.xpath(asin_xpath) # to explicitly check if the item is a Kindle book and ignore it
if asin: # if it isn't.
asin = asin[0] format_ = ''.join(data.xpath(format_xpath))
else: if 'kindle' not in format_.lower():
continue continue
cover_url = ''.join(data.xpath(cover_xpath)) # We must have an asin otherwise we can't easily reference the
# book later.
asin = data.xpath(asin_xpath)
if asin:
asin = asin[0]
else:
continue
title = ''.join(data.xpath(title_xpath)) cover_url = ''.join(data.xpath(cover_xpath))
authors = ''.join(data.xpath(author_xpath)) title = ''.join(data.xpath(title_xpath))
authors = re.sub('^' + self.author_article, '', authors)
authors = re.sub(self.and_word, ' & ', authors)
mo = re.match(r'(.*)(\(\d.*)$', authors)
if mo:
authors = mo.group(1).strip()
price = ''.join(data.xpath(price_xpath)) authors = ''.join(data.xpath(author_xpath))
authors = re.sub('^' + self.author_article, '', authors)
authors = re.sub(self.and_word, ' & ', authors)
mo = re.match(r'(.*)(\(\d.*)$', authors)
if mo:
authors = mo.group(1).strip()
counter -= 1 price = ''.join(data.xpath(price_xpath))
s = SearchResult() counter -= 1
s.cover_url = cover_url.strip()
s.title = title.strip()
s.author = authors.strip()
s.price = price.strip()
s.detail_item = asin.strip()
s.drm = SearchResult.DRM_UNKNOWN
s.formats = 'Kindle'
yield s s = SearchResult()
s.cover_url = cover_url.strip()
s.title = title.strip()
s.author = authors.strip()
s.price = price.strip()
s.detail_item = asin.strip()
s.drm = SearchResult.DRM_UNKNOWN
s.formats = 'Kindle'
yield s
def get_details(self, search_result, timeout): def get_details(self, search_result, timeout):
pass pass

104
src/calibre/gui2/store/stores/amazon_es_plugin.py
View File

@ -7,7 +7,7 @@ __license__ = 'GPL 3'
__copyright__ = '2011, John Schember <john@nachtimwald.com>' __copyright__ = '2011, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
import re import re, time
from contextlib import closing from contextlib import closing
from lxml import html from lxml import html
@ -28,6 +28,9 @@ class AmazonEUBase(StorePlugin):
For comments on the implementation, please see amazon_plugin.py For comments on the implementation, please see amazon_plugin.py
''' '''
MAX_SEARCH_ATTEMPTS = 5
SLEEP_BETWEEN_ATTEMPTS = 3
def open(self, parent=None, detail_item=None, external=False): def open(self, parent=None, detail_item=None, external=False):
store_link = self.store_link % self.aff_id store_link = self.store_link % self.aff_id
@ -41,62 +44,71 @@ class AmazonEUBase(StorePlugin):
br = browser() br = browser()
counter = max_results counter = max_results
with closing(br.open(url, timeout=timeout)) as f: loops = 0
doc = html.fromstring(f.read())#.decode('latin-1', 'replace')) while counter == max_results and loops < self.MAX_SEARCH_ATTEMPTS:
br = browser()
if loops > 0:
print ("Retry getbooks search", self.__class__.__name__, counter,
max_results, loops)
time.sleep(self.SLEEP_BETWEEN_ATTEMPTS)
loops += 1
data_xpath = '//div[contains(@class, "prod")]' with closing(br.open(url, timeout=timeout)) as f:
format_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()' doc = html.fromstring(f.read())#.decode('latin-1', 'replace'))
asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and contains(@class, "bld")]/text()'
for data in doc.xpath(data_xpath): data_xpath = '//div[contains(@class, "prod")]'
if counter <= 0: format_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()'
break asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and contains(@class, "bld")]/text()'
# Even though we are searching digital-text only Amazon will still for data in doc.xpath(data_xpath):
# put in results for non Kindle books (authors pages). Se we need if counter <= 0:
# to explicitly check if the item is a Kindle book and ignore it break
# 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 # Even though we are searching digital-text only Amazon will still
# book later. # put in results for non Kindle books (authors pages). Se we need
asin = data.xpath(asin_xpath) # to explicitly check if the item is a Kindle book and ignore it
if asin: # if it isn't.
asin = asin[0] format_ = ''.join(data.xpath(format_xpath))
else: if 'kindle' not in format_.lower():
continue continue
cover_url = ''.join(data.xpath(cover_xpath)) # We must have an asin otherwise we can't easily reference the
# book later.
asin = data.xpath(asin_xpath)
if asin:
asin = asin[0]
else:
continue
title = ''.join(data.xpath(title_xpath)) cover_url = ''.join(data.xpath(cover_xpath))
authors = ''.join(data.xpath(author_xpath)) title = ''.join(data.xpath(title_xpath))
authors = re.sub('^' + self.author_article, '', authors)
authors = re.sub(self.and_word, ' & ', authors)
mo = re.match(r'(.*)(\(\d.*)$', authors)
if mo:
authors = mo.group(1).strip()
price = ''.join(data.xpath(price_xpath)) authors = ''.join(data.xpath(author_xpath))
authors = re.sub('^' + self.author_article, '', authors)
authors = re.sub(self.and_word, ' & ', authors)
mo = re.match(r'(.*)(\(\d.*)$', authors)
if mo:
authors = mo.group(1).strip()
counter -= 1 price = ''.join(data.xpath(price_xpath))
s = SearchResult() counter -= 1
s.cover_url = cover_url.strip()
s.title = title.strip()
s.author = authors.strip()
s.price = price.strip()
s.detail_item = asin.strip()
s.drm = SearchResult.DRM_UNKNOWN
s.formats = 'Kindle'
yield s s = SearchResult()
s.cover_url = cover_url.strip()
s.title = title.strip()
s.author = authors.strip()
s.price = price.strip()
s.detail_item = asin.strip()
s.drm = SearchResult.DRM_UNKNOWN
s.formats = 'Kindle'
yield s
def get_details(self, search_result, timeout): def get_details(self, search_result, timeout):
pass pass

104
src/calibre/gui2/store/stores/amazon_fr_plugin.py
View File

@ -7,7 +7,7 @@ __license__ = 'GPL 3'
__copyright__ = '2011, John Schember <john@nachtimwald.com>' __copyright__ = '2011, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
import re import re, time
from contextlib import closing from contextlib import closing
from lxml import html from lxml import html
@ -29,6 +29,9 @@ class AmazonEUBase(StorePlugin):
For comments on the implementation, please see amazon_plugin.py For comments on the implementation, please see amazon_plugin.py
''' '''
MAX_SEARCH_ATTEMPTS = 5
SLEEP_BETWEEN_ATTEMPTS = 3
def open(self, parent=None, detail_item=None, external=False): def open(self, parent=None, detail_item=None, external=False):
store_link = self.store_link % self.aff_id store_link = self.store_link % self.aff_id
@ -42,62 +45,71 @@ class AmazonEUBase(StorePlugin):
br = browser() br = browser()
counter = max_results counter = max_results
with closing(br.open(url, timeout=timeout)) as f: loops = 0
doc = html.fromstring(f.read())#.decode('latin-1', 'replace')) while counter == max_results and loops < self.MAX_SEARCH_ATTEMPTS:
br = browser()
if loops > 0:
print ("Retry getbooks search", self.__class__.__name__, counter,
max_results, loops)
time.sleep(self.SLEEP_BETWEEN_ATTEMPTS)
loops += 1
data_xpath = '//div[contains(@class, "prod")]' with closing(br.open(url, timeout=timeout)) as f:
format_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()' doc = html.fromstring(f.read())#.decode('latin-1', 'replace'))
asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and contains(@class, "bld")]/text()'
for data in doc.xpath(data_xpath): data_xpath = '//div[contains(@class, "prod")]'
if counter <= 0: format_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()'
break asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and contains(@class, "bld")]/text()'
# Even though we are searching digital-text only Amazon will still for data in doc.xpath(data_xpath):
# put in results for non Kindle books (authors pages). Se we need if counter <= 0:
# to explicitly check if the item is a Kindle book and ignore it break
# 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 # Even though we are searching digital-text only Amazon will still
# book later. # put in results for non Kindle books (authors pages). Se we need
asin = data.xpath(asin_xpath) # to explicitly check if the item is a Kindle book and ignore it
if asin: # if it isn't.
asin = asin[0] format_ = ''.join(data.xpath(format_xpath))
else: if 'kindle' not in format_.lower():
continue continue
cover_url = ''.join(data.xpath(cover_xpath)) # We must have an asin otherwise we can't easily reference the
# book later.
asin = data.xpath(asin_xpath)
if asin:
asin = asin[0]
else:
continue
title = ''.join(data.xpath(title_xpath)) cover_url = ''.join(data.xpath(cover_xpath))
authors = ''.join(data.xpath(author_xpath)) title = ''.join(data.xpath(title_xpath))
authors = re.sub('^' + self.author_article, '', authors)
authors = re.sub(self.and_word, ' & ', authors)
mo = re.match(r'(.*)(\(\d.*)$', authors)
if mo:
authors = mo.group(1).strip()
price = ''.join(data.xpath(price_xpath)) authors = ''.join(data.xpath(author_xpath))
authors = re.sub('^' + self.author_article, '', authors)
authors = re.sub(self.and_word, ' & ', authors)
mo = re.match(r'(.*)(\(\d.*)$', authors)
if mo:
authors = mo.group(1).strip()
counter -= 1 price = ''.join(data.xpath(price_xpath))
s = SearchResult() counter -= 1
s.cover_url = cover_url.strip()
s.title = title.strip()
s.author = authors.strip()
s.price = price.strip()
s.detail_item = asin.strip()
s.drm = SearchResult.DRM_UNKNOWN
s.formats = 'Kindle'
yield s s = SearchResult()
s.cover_url = cover_url.strip()
s.title = title.strip()
s.author = authors.strip()
s.price = price.strip()
s.detail_item = asin.strip()
s.drm = SearchResult.DRM_UNKNOWN
s.formats = 'Kindle'
yield s
def get_details(self, search_result, timeout): def get_details(self, search_result, timeout):
pass pass

104
src/calibre/gui2/store/stores/amazon_it_plugin.py
View File

@ -7,7 +7,7 @@ __license__ = 'GPL 3'
__copyright__ = '2011, John Schember <john@nachtimwald.com>' __copyright__ = '2011, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
import re import re, time
from contextlib import closing from contextlib import closing
from lxml import html from lxml import html
@ -28,6 +28,9 @@ class AmazonEUBase(StorePlugin):
For comments on the implementation, please see amazon_plugin.py For comments on the implementation, please see amazon_plugin.py
''' '''
MAX_SEARCH_ATTEMPTS = 5
SLEEP_BETWEEN_ATTEMPTS = 3
def open(self, parent=None, detail_item=None, external=False): def open(self, parent=None, detail_item=None, external=False):
store_link = self.store_link % self.aff_id store_link = self.store_link % self.aff_id
@ -41,62 +44,71 @@ class AmazonEUBase(StorePlugin):
br = browser() br = browser()
counter = max_results counter = max_results
with closing(br.open(url, timeout=timeout)) as f: loops = 0
doc = html.fromstring(f.read())#.decode('latin-1', 'replace')) while counter == max_results and loops < self.MAX_SEARCH_ATTEMPTS:
br = browser()
if loops > 0:
print ("Retry getbooks search", self.__class__.__name__, counter,
max_results, loops)
time.sleep(self.SLEEP_BETWEEN_ATTEMPTS)
loops += 1
data_xpath = '//div[contains(@class, "prod")]' with closing(br.open(url, timeout=timeout)) as f:
format_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()' doc = html.fromstring(f.read())#.decode('latin-1', 'replace'))
asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and contains(@class, "bld")]/text()'
for data in doc.xpath(data_xpath): data_xpath = '//div[contains(@class, "prod")]'
if counter <= 0: format_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()'
break asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and contains(@class, "bld")]/text()'
# Even though we are searching digital-text only Amazon will still for data in doc.xpath(data_xpath):
# put in results for non Kindle books (authors pages). Se we need if counter <= 0:
# to explicitly check if the item is a Kindle book and ignore it break
# 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 # Even though we are searching digital-text only Amazon will still
# book later. # put in results for non Kindle books (authors pages). Se we need
asin = data.xpath(asin_xpath) # to explicitly check if the item is a Kindle book and ignore it
if asin: # if it isn't.
asin = asin[0] format_ = ''.join(data.xpath(format_xpath))
else: if 'kindle' not in format_.lower():
continue continue
cover_url = ''.join(data.xpath(cover_xpath)) # We must have an asin otherwise we can't easily reference the
# book later.
asin = data.xpath(asin_xpath)
if asin:
asin = asin[0]
else:
continue
title = ''.join(data.xpath(title_xpath)) cover_url = ''.join(data.xpath(cover_xpath))
authors = ''.join(data.xpath(author_xpath)) title = ''.join(data.xpath(title_xpath))
authors = re.sub('^' + self.author_article, '', authors)
authors = re.sub(self.and_word, ' & ', authors)
mo = re.match(r'(.*)(\(\d.*)$', authors)
if mo:
authors = mo.group(1).strip()
price = ''.join(data.xpath(price_xpath)) authors = ''.join(data.xpath(author_xpath))
authors = re.sub('^' + self.author_article, '', authors)
authors = re.sub(self.and_word, ' & ', authors)
mo = re.match(r'(.*)(\(\d.*)$', authors)
if mo:
authors = mo.group(1).strip()
counter -= 1 price = ''.join(data.xpath(price_xpath))
s = SearchResult() counter -= 1
s.cover_url = cover_url.strip()
s.title = title.strip()
s.author = authors.strip()
s.price = price.strip()
s.detail_item = asin.strip()
s.drm = SearchResult.DRM_UNKNOWN
s.formats = 'Kindle'
yield s s = SearchResult()
s.cover_url = cover_url.strip()
s.title = title.strip()
s.author = authors.strip()
s.price = price.strip()
s.detail_item = asin.strip()
s.drm = SearchResult.DRM_UNKNOWN
s.formats = 'Kindle'
yield s
def get_details(self, search_result, timeout): def get_details(self, search_result, timeout):
pass pass

104
src/calibre/gui2/store/stores/amazon_uk_plugin.py
View File

@ -7,7 +7,7 @@ __license__ = 'GPL 3'
__copyright__ = '2011, John Schember <john@nachtimwald.com>' __copyright__ = '2011, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
import re import re, time
from contextlib import closing from contextlib import closing
from lxml import html from lxml import html
@ -28,6 +28,9 @@ class AmazonEUBase(StorePlugin):
For comments on the implementation, please see amazon_plugin.py For comments on the implementation, please see amazon_plugin.py
''' '''
MAX_SEARCH_ATTEMPTS = 5
SLEEP_BETWEEN_ATTEMPTS = 3
def open(self, parent=None, detail_item=None, external=False): def open(self, parent=None, detail_item=None, external=False):
store_link = self.store_link % self.aff_id store_link = self.store_link % self.aff_id
@ -41,62 +44,71 @@ class AmazonEUBase(StorePlugin):
br = browser() br = browser()
counter = max_results counter = max_results
with closing(br.open(url, timeout=timeout)) as f: loops = 0
doc = html.fromstring(f.read())#.decode('latin-1', 'replace')) while counter == max_results and loops < self.MAX_SEARCH_ATTEMPTS:
br = browser()
if loops > 0:
print ("Retry getbooks search", self.__class__.__name__, counter,
max_results, loops)
time.sleep(self.SLEEP_BETWEEN_ATTEMPTS)
loops += 1
data_xpath = '//div[contains(@class, "prod")]' with closing(br.open(url, timeout=timeout)) as f:
format_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()' doc = html.fromstring(f.read())#.decode('latin-1', 'replace'))
asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and contains(@class, "bld")]/text()'
for data in doc.xpath(data_xpath): data_xpath = '//div[contains(@class, "prod")]'
if counter <= 0: format_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()'
break asin_xpath = '@name'
cover_xpath = './/img[@class="productImage"]/@src'
title_xpath = './/h3[@class="newaps"]/a//text()'
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
price_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and contains(@class, "bld")]/text()'
# Even though we are searching digital-text only Amazon will still for data in doc.xpath(data_xpath):
# put in results for non Kindle books (authors pages). Se we need if counter <= 0:
# to explicitly check if the item is a Kindle book and ignore it break
# 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 # Even though we are searching digital-text only Amazon will still
# book later. # put in results for non Kindle books (authors pages). Se we need
asin = data.xpath(asin_xpath) # to explicitly check if the item is a Kindle book and ignore it
if asin: # if it isn't.
asin = asin[0] format_ = ''.join(data.xpath(format_xpath))
else: if 'kindle' not in format_.lower():
continue continue
cover_url = ''.join(data.xpath(cover_xpath)) # We must have an asin otherwise we can't easily reference the
# book later.
asin = data.xpath(asin_xpath)
if asin:
asin = asin[0]
else:
continue
title = ''.join(data.xpath(title_xpath)) cover_url = ''.join(data.xpath(cover_xpath))
authors = ''.join(data.xpath(author_xpath)) title = ''.join(data.xpath(title_xpath))
authors = re.sub('^' + self.author_article, '', authors)
authors = re.sub(self.and_word, ' & ', authors)
mo = re.match(r'(.*)(\(\d.*)$', authors)
if mo:
authors = mo.group(1).strip()
price = ''.join(data.xpath(price_xpath)) authors = ''.join(data.xpath(author_xpath))
authors = re.sub('^' + self.author_article, '', authors)
authors = re.sub(self.and_word, ' & ', authors)
mo = re.match(r'(.*)(\(\d.*)$', authors)
if mo:
authors = mo.group(1).strip()
counter -= 1 price = ''.join(data.xpath(price_xpath))
s = SearchResult() counter -= 1
s.cover_url = cover_url.strip()
s.title = title.strip()
s.author = authors.strip()
s.price = price.strip()
s.detail_item = asin.strip()
s.drm = SearchResult.DRM_UNKNOWN
s.formats = 'Kindle'
yield s s = SearchResult()
s.cover_url = cover_url.strip()
s.title = title.strip()
s.author = authors.strip()
s.price = price.strip()
s.detail_item = asin.strip()
s.drm = SearchResult.DRM_UNKNOWN
s.formats = 'Kindle'
yield s
def get_details(self, search_result, timeout): def get_details(self, search_result, timeout):
pass pass