mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
Handle column and grid layouts in amazon EU stores
This commit is contained in:
parent
de0c864159
commit
89a5375f57
@ -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, time
|
import re
|
||||||
from contextlib import closing
|
from contextlib import closing
|
||||||
from lxml import html
|
from lxml import html
|
||||||
|
|
||||||
@ -29,9 +29,6 @@ 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
|
||||||
@ -42,73 +39,71 @@ class AmazonEUBase(StorePlugin):
|
|||||||
|
|
||||||
def search(self, query, max_results=10, timeout=60):
|
def search(self, query, max_results=10, timeout=60):
|
||||||
url = self.search_url + query.encode('ascii', 'backslashreplace').replace('%', '%25').replace('\\x', '%').replace(' ', '+')
|
url = self.search_url + query.encode('ascii', 'backslashreplace').replace('%', '%25').replace('\\x', '%').replace(' ', '+')
|
||||||
|
br = browser()
|
||||||
|
|
||||||
counter = max_results
|
counter = max_results
|
||||||
loops = 0
|
with closing(br.open(url, timeout=timeout)) as f:
|
||||||
while counter == max_results and loops < self.MAX_SEARCH_ATTEMPTS:
|
doc = html.fromstring(f.read())#.decode('latin-1', 'replace'))
|
||||||
br = browser()
|
|
||||||
if loops > 0:
|
|
||||||
print ("Retry getbooks search", self.__class__.__name__, counter,
|
|
||||||
max_results, loops)
|
|
||||||
time.sleep(self.SLEEP_BETWEEN_ATTEMPTS)
|
|
||||||
loops += 1
|
|
||||||
|
|
||||||
with closing(br.open(url, timeout=timeout)) as f:
|
data_xpath = '//div[contains(@class, "prod")]'
|
||||||
doc = html.fromstring(f.read())#.decode('latin-1', 'replace'))
|
# Results can be in a grid (table) or a column
|
||||||
|
format_xpath = (
|
||||||
|
'.//ul[contains(@class, "rsltL") or contains(@class, "rsltGridList")]'
|
||||||
|
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
|
||||||
|
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()'
|
||||||
|
# Results can be in a grid (table) or a column
|
||||||
|
price_xpath = (
|
||||||
|
'.//ul[contains(@class, "rsltL") or contains(@class, "rsltGridList")]'
|
||||||
|
'//span[contains(@class, "lrg") and contains(@class, "bld")]/text()')
|
||||||
|
|
||||||
data_xpath = '//div[contains(@class, "prod")]'
|
for data in doc.xpath(data_xpath):
|
||||||
format_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()'
|
if counter <= 0:
|
||||||
asin_xpath = '@name'
|
break
|
||||||
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):
|
# Even though we are searching digital-text only Amazon will still
|
||||||
if counter <= 0:
|
# put in results for non Kindle books (authors pages). Se we need
|
||||||
break
|
# 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
|
||||||
|
|
||||||
# Even though we are searching digital-text only Amazon will still
|
# We must have an asin otherwise we can't easily reference the
|
||||||
# put in results for non Kindle books (authors pages). Se we need
|
# book later.
|
||||||
# to explicitly check if the item is a Kindle book and ignore it
|
asin = data.xpath(asin_xpath)
|
||||||
# if it isn't.
|
if asin:
|
||||||
format_ = ''.join(data.xpath(format_xpath))
|
asin = asin[0]
|
||||||
if 'kindle' not in format_.lower():
|
else:
|
||||||
continue
|
continue
|
||||||
|
|
||||||
# We must have an asin otherwise we can't easily reference the
|
cover_url = ''.join(data.xpath(cover_xpath))
|
||||||
# book later.
|
|
||||||
asin = data.xpath(asin_xpath)
|
|
||||||
if asin:
|
|
||||||
asin = asin[0]
|
|
||||||
else:
|
|
||||||
continue
|
|
||||||
|
|
||||||
cover_url = ''.join(data.xpath(cover_xpath))
|
title = ''.join(data.xpath(title_xpath))
|
||||||
|
|
||||||
title = ''.join(data.xpath(title_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()
|
||||||
|
|
||||||
authors = ''.join(data.xpath(author_xpath))
|
price = ''.join(data.xpath(price_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))
|
counter -= 1
|
||||||
|
|
||||||
counter -= 1
|
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'
|
||||||
|
|
||||||
s = SearchResult()
|
yield s
|
||||||
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
|
||||||
|
@ -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, time
|
import re
|
||||||
from contextlib import closing
|
from contextlib import closing
|
||||||
from lxml import html
|
from lxml import html
|
||||||
|
|
||||||
@ -28,9 +28,6 @@ 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
|
||||||
@ -41,73 +38,71 @@ class AmazonEUBase(StorePlugin):
|
|||||||
|
|
||||||
def search(self, query, max_results=10, timeout=60):
|
def search(self, query, max_results=10, timeout=60):
|
||||||
url = self.search_url + query.encode('ascii', 'backslashreplace').replace('%', '%25').replace('\\x', '%').replace(' ', '+')
|
url = self.search_url + query.encode('ascii', 'backslashreplace').replace('%', '%25').replace('\\x', '%').replace(' ', '+')
|
||||||
|
br = browser()
|
||||||
|
|
||||||
counter = max_results
|
counter = max_results
|
||||||
loops = 0
|
with closing(br.open(url, timeout=timeout)) as f:
|
||||||
while counter == max_results and loops < self.MAX_SEARCH_ATTEMPTS:
|
doc = html.fromstring(f.read())#.decode('latin-1', 'replace'))
|
||||||
br = browser()
|
|
||||||
if loops > 0:
|
|
||||||
print ("Retry getbooks search", self.__class__.__name__, counter,
|
|
||||||
max_results, loops)
|
|
||||||
time.sleep(self.SLEEP_BETWEEN_ATTEMPTS)
|
|
||||||
loops += 1
|
|
||||||
|
|
||||||
with closing(br.open(url, timeout=timeout)) as f:
|
data_xpath = '//div[contains(@class, "prod")]'
|
||||||
doc = html.fromstring(f.read())#.decode('latin-1', 'replace'))
|
# Results can be in a grid (table) or a column
|
||||||
|
format_xpath = (
|
||||||
|
'.//ul[contains(@class, "rsltL") or contains(@class, "rsltGridList")]'
|
||||||
|
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
|
||||||
|
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()'
|
||||||
|
# Results can be in a grid (table) or a column
|
||||||
|
price_xpath = (
|
||||||
|
'.//ul[contains(@class, "rsltL") or contains(@class, "rsltGridList")]'
|
||||||
|
'//span[contains(@class, "lrg") and contains(@class, "bld")]/text()')
|
||||||
|
|
||||||
data_xpath = '//div[contains(@class, "prod")]'
|
for data in doc.xpath(data_xpath):
|
||||||
format_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()'
|
if counter <= 0:
|
||||||
asin_xpath = '@name'
|
break
|
||||||
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):
|
# Even though we are searching digital-text only Amazon will still
|
||||||
if counter <= 0:
|
# put in results for non Kindle books (authors pages). Se we need
|
||||||
break
|
# 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
|
||||||
|
|
||||||
# Even though we are searching digital-text only Amazon will still
|
# We must have an asin otherwise we can't easily reference the
|
||||||
# put in results for non Kindle books (authors pages). Se we need
|
# book later.
|
||||||
# to explicitly check if the item is a Kindle book and ignore it
|
asin = data.xpath(asin_xpath)
|
||||||
# if it isn't.
|
if asin:
|
||||||
format_ = ''.join(data.xpath(format_xpath))
|
asin = asin[0]
|
||||||
if 'kindle' not in format_.lower():
|
else:
|
||||||
continue
|
continue
|
||||||
|
|
||||||
# We must have an asin otherwise we can't easily reference the
|
cover_url = ''.join(data.xpath(cover_xpath))
|
||||||
# book later.
|
|
||||||
asin = data.xpath(asin_xpath)
|
|
||||||
if asin:
|
|
||||||
asin = asin[0]
|
|
||||||
else:
|
|
||||||
continue
|
|
||||||
|
|
||||||
cover_url = ''.join(data.xpath(cover_xpath))
|
title = ''.join(data.xpath(title_xpath))
|
||||||
|
|
||||||
title = ''.join(data.xpath(title_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()
|
||||||
|
|
||||||
authors = ''.join(data.xpath(author_xpath))
|
price = ''.join(data.xpath(price_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))
|
counter -= 1
|
||||||
|
|
||||||
counter -= 1
|
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'
|
||||||
|
|
||||||
s = SearchResult()
|
yield s
|
||||||
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
|
||||||
|
@ -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, time
|
import re
|
||||||
from contextlib import closing
|
from contextlib import closing
|
||||||
from lxml import html
|
from lxml import html
|
||||||
|
|
||||||
@ -29,9 +29,6 @@ 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
|
||||||
@ -42,73 +39,71 @@ class AmazonEUBase(StorePlugin):
|
|||||||
|
|
||||||
def search(self, query, max_results=10, timeout=60):
|
def search(self, query, max_results=10, timeout=60):
|
||||||
url = self.search_url + query.encode('ascii', 'backslashreplace').replace('%', '%25').replace('\\x', '%').replace(' ', '+')
|
url = self.search_url + query.encode('ascii', 'backslashreplace').replace('%', '%25').replace('\\x', '%').replace(' ', '+')
|
||||||
|
br = browser()
|
||||||
|
|
||||||
counter = max_results
|
counter = max_results
|
||||||
loops = 0
|
with closing(br.open(url, timeout=timeout)) as f:
|
||||||
while counter == max_results and loops < self.MAX_SEARCH_ATTEMPTS:
|
doc = html.fromstring(f.read())#.decode('latin-1', 'replace'))
|
||||||
br = browser()
|
|
||||||
if loops > 0:
|
|
||||||
print ("Retry getbooks search", self.__class__.__name__, counter,
|
|
||||||
max_results, loops)
|
|
||||||
time.sleep(self.SLEEP_BETWEEN_ATTEMPTS)
|
|
||||||
loops += 1
|
|
||||||
|
|
||||||
with closing(br.open(url, timeout=timeout)) as f:
|
data_xpath = '//div[contains(@class, "prod")]'
|
||||||
doc = html.fromstring(f.read())#.decode('latin-1', 'replace'))
|
# Results can be in a grid (table) or a column
|
||||||
|
format_xpath = (
|
||||||
|
'.//ul[contains(@class, "rsltL") or contains(@class, "rsltGridList")]'
|
||||||
|
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
|
||||||
|
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()'
|
||||||
|
# Results can be in a grid (table) or a column
|
||||||
|
price_xpath = (
|
||||||
|
'.//ul[contains(@class, "rsltL") or contains(@class, "rsltGridList")]'
|
||||||
|
'//span[contains(@class, "lrg") and contains(@class, "bld")]/text()')
|
||||||
|
|
||||||
data_xpath = '//div[contains(@class, "prod")]'
|
for data in doc.xpath(data_xpath):
|
||||||
format_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()'
|
if counter <= 0:
|
||||||
asin_xpath = '@name'
|
break
|
||||||
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):
|
# Even though we are searching digital-text only Amazon will still
|
||||||
if counter <= 0:
|
# put in results for non Kindle books (authors pages). Se we need
|
||||||
break
|
# 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
|
||||||
|
|
||||||
# Even though we are searching digital-text only Amazon will still
|
# We must have an asin otherwise we can't easily reference the
|
||||||
# put in results for non Kindle books (authors pages). Se we need
|
# book later.
|
||||||
# to explicitly check if the item is a Kindle book and ignore it
|
asin = data.xpath(asin_xpath)
|
||||||
# if it isn't.
|
if asin:
|
||||||
format_ = ''.join(data.xpath(format_xpath))
|
asin = asin[0]
|
||||||
if 'kindle' not in format_.lower():
|
else:
|
||||||
continue
|
continue
|
||||||
|
|
||||||
# We must have an asin otherwise we can't easily reference the
|
cover_url = ''.join(data.xpath(cover_xpath))
|
||||||
# book later.
|
|
||||||
asin = data.xpath(asin_xpath)
|
|
||||||
if asin:
|
|
||||||
asin = asin[0]
|
|
||||||
else:
|
|
||||||
continue
|
|
||||||
|
|
||||||
cover_url = ''.join(data.xpath(cover_xpath))
|
title = ''.join(data.xpath(title_xpath))
|
||||||
|
|
||||||
title = ''.join(data.xpath(title_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()
|
||||||
|
|
||||||
authors = ''.join(data.xpath(author_xpath))
|
price = ''.join(data.xpath(price_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))
|
counter -= 1
|
||||||
|
|
||||||
counter -= 1
|
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'
|
||||||
|
|
||||||
s = SearchResult()
|
yield s
|
||||||
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
|
||||||
|
@ -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, time
|
import re
|
||||||
from contextlib import closing
|
from contextlib import closing
|
||||||
from lxml import html
|
from lxml import html
|
||||||
|
|
||||||
@ -28,9 +28,6 @@ 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
|
||||||
@ -41,73 +38,71 @@ class AmazonEUBase(StorePlugin):
|
|||||||
|
|
||||||
def search(self, query, max_results=10, timeout=60):
|
def search(self, query, max_results=10, timeout=60):
|
||||||
url = self.search_url + query.encode('ascii', 'backslashreplace').replace('%', '%25').replace('\\x', '%').replace(' ', '+')
|
url = self.search_url + query.encode('ascii', 'backslashreplace').replace('%', '%25').replace('\\x', '%').replace(' ', '+')
|
||||||
|
br = browser()
|
||||||
|
|
||||||
counter = max_results
|
counter = max_results
|
||||||
loops = 0
|
with closing(br.open(url, timeout=timeout)) as f:
|
||||||
while counter == max_results and loops < self.MAX_SEARCH_ATTEMPTS:
|
doc = html.fromstring(f.read())#.decode('latin-1', 'replace'))
|
||||||
br = browser()
|
|
||||||
if loops > 0:
|
|
||||||
print ("Retry getbooks search", self.__class__.__name__, counter,
|
|
||||||
max_results, loops)
|
|
||||||
time.sleep(self.SLEEP_BETWEEN_ATTEMPTS)
|
|
||||||
loops += 1
|
|
||||||
|
|
||||||
with closing(br.open(url, timeout=timeout)) as f:
|
data_xpath = '//div[contains(@class, "prod")]'
|
||||||
doc = html.fromstring(f.read())#.decode('latin-1', 'replace'))
|
# Results can be in a grid (table) or a column
|
||||||
|
format_xpath = (
|
||||||
|
'.//ul[contains(@class, "rsltL") or contains(@class, "rsltGridList")]'
|
||||||
|
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
|
||||||
|
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()'
|
||||||
|
# Results can be in a grid (table) or a column
|
||||||
|
price_xpath = (
|
||||||
|
'.//ul[contains(@class, "rsltL") or contains(@class, "rsltGridList")]'
|
||||||
|
'//span[contains(@class, "lrg") and contains(@class, "bld")]/text()')
|
||||||
|
|
||||||
data_xpath = '//div[contains(@class, "prod")]'
|
for data in doc.xpath(data_xpath):
|
||||||
format_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()'
|
if counter <= 0:
|
||||||
asin_xpath = '@name'
|
break
|
||||||
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):
|
# Even though we are searching digital-text only Amazon will still
|
||||||
if counter <= 0:
|
# put in results for non Kindle books (authors pages). Se we need
|
||||||
break
|
# 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
|
||||||
|
|
||||||
# Even though we are searching digital-text only Amazon will still
|
# We must have an asin otherwise we can't easily reference the
|
||||||
# put in results for non Kindle books (authors pages). Se we need
|
# book later.
|
||||||
# to explicitly check if the item is a Kindle book and ignore it
|
asin = data.xpath(asin_xpath)
|
||||||
# if it isn't.
|
if asin:
|
||||||
format_ = ''.join(data.xpath(format_xpath))
|
asin = asin[0]
|
||||||
if 'kindle' not in format_.lower():
|
else:
|
||||||
continue
|
continue
|
||||||
|
|
||||||
# We must have an asin otherwise we can't easily reference the
|
cover_url = ''.join(data.xpath(cover_xpath))
|
||||||
# book later.
|
|
||||||
asin = data.xpath(asin_xpath)
|
|
||||||
if asin:
|
|
||||||
asin = asin[0]
|
|
||||||
else:
|
|
||||||
continue
|
|
||||||
|
|
||||||
cover_url = ''.join(data.xpath(cover_xpath))
|
title = ''.join(data.xpath(title_xpath))
|
||||||
|
|
||||||
title = ''.join(data.xpath(title_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()
|
||||||
|
|
||||||
authors = ''.join(data.xpath(author_xpath))
|
price = ''.join(data.xpath(price_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))
|
counter -= 1
|
||||||
|
|
||||||
counter -= 1
|
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'
|
||||||
|
|
||||||
s = SearchResult()
|
yield s
|
||||||
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
|
||||||
|
@ -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, time
|
import re
|
||||||
from contextlib import closing
|
from contextlib import closing
|
||||||
from lxml import html
|
from lxml import html
|
||||||
|
|
||||||
@ -28,9 +28,6 @@ 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
|
||||||
@ -41,73 +38,71 @@ class AmazonEUBase(StorePlugin):
|
|||||||
|
|
||||||
def search(self, query, max_results=10, timeout=60):
|
def search(self, query, max_results=10, timeout=60):
|
||||||
url = self.search_url + query.encode('ascii', 'backslashreplace').replace('%', '%25').replace('\\x', '%').replace(' ', '+')
|
url = self.search_url + query.encode('ascii', 'backslashreplace').replace('%', '%25').replace('\\x', '%').replace(' ', '+')
|
||||||
|
br = browser()
|
||||||
|
|
||||||
counter = max_results
|
counter = max_results
|
||||||
loops = 0
|
with closing(br.open(url, timeout=timeout)) as f:
|
||||||
while counter == max_results and loops < self.MAX_SEARCH_ATTEMPTS:
|
doc = html.fromstring(f.read())#.decode('latin-1', 'replace'))
|
||||||
br = browser()
|
|
||||||
if loops > 0:
|
|
||||||
print ("Retry getbooks search", self.__class__.__name__, counter,
|
|
||||||
max_results, loops)
|
|
||||||
time.sleep(self.SLEEP_BETWEEN_ATTEMPTS)
|
|
||||||
loops += 1
|
|
||||||
|
|
||||||
with closing(br.open(url, timeout=timeout)) as f:
|
data_xpath = '//div[contains(@class, "prod")]'
|
||||||
doc = html.fromstring(f.read())#.decode('latin-1', 'replace'))
|
# Results can be in a grid (table) or a column
|
||||||
|
format_xpath = (
|
||||||
|
'.//ul[contains(@class, "rsltL") or contains(@class, "rsltGridList")]'
|
||||||
|
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
|
||||||
|
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()'
|
||||||
|
# Results can be in a grid (table) or a column
|
||||||
|
price_xpath = (
|
||||||
|
'.//ul[contains(@class, "rsltL") or contains(@class, "rsltGridList")]'
|
||||||
|
'//span[contains(@class, "lrg") and contains(@class, "bld")]/text()')
|
||||||
|
|
||||||
data_xpath = '//div[contains(@class, "prod")]'
|
for data in doc.xpath(data_xpath):
|
||||||
format_xpath = './/ul[contains(@class, "rsltL")]//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()'
|
if counter <= 0:
|
||||||
asin_xpath = '@name'
|
break
|
||||||
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):
|
# Even though we are searching digital-text only Amazon will still
|
||||||
if counter <= 0:
|
# put in results for non Kindle books (authors pages). Se we need
|
||||||
break
|
# 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
|
||||||
|
|
||||||
# Even though we are searching digital-text only Amazon will still
|
# We must have an asin otherwise we can't easily reference the
|
||||||
# put in results for non Kindle books (authors pages). Se we need
|
# book later.
|
||||||
# to explicitly check if the item is a Kindle book and ignore it
|
asin = data.xpath(asin_xpath)
|
||||||
# if it isn't.
|
if asin:
|
||||||
format_ = ''.join(data.xpath(format_xpath))
|
asin = asin[0]
|
||||||
if 'kindle' not in format_.lower():
|
else:
|
||||||
continue
|
continue
|
||||||
|
|
||||||
# We must have an asin otherwise we can't easily reference the
|
cover_url = ''.join(data.xpath(cover_xpath))
|
||||||
# book later.
|
|
||||||
asin = data.xpath(asin_xpath)
|
|
||||||
if asin:
|
|
||||||
asin = asin[0]
|
|
||||||
else:
|
|
||||||
continue
|
|
||||||
|
|
||||||
cover_url = ''.join(data.xpath(cover_xpath))
|
title = ''.join(data.xpath(title_xpath))
|
||||||
|
|
||||||
title = ''.join(data.xpath(title_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()
|
||||||
|
|
||||||
authors = ''.join(data.xpath(author_xpath))
|
price = ''.join(data.xpath(price_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))
|
counter -= 1
|
||||||
|
|
||||||
counter -= 1
|
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'
|
||||||
|
|
||||||
s = SearchResult()
|
yield s
|
||||||
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
|
||||||
|
Loading…
x
Reference in New Issue
Block a user