Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 02:34:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

Get books: Update English language Amazon plugins for website changes

Browse Source
This commit is contained in:
Kovid Goyal 2022-04-02 15:39:24 +05:30
parent e46982f7df
commit 61b24aef56
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
6 changed files with 186 additions and 671 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

115
src/calibre/gui2/store/amazon_base.py Normal file
View File

@ -0,0 +1,115 @@
#!/usr/bin/env python
# vim:fileencoding=utf-8
# License: GPL v3 Copyright: 2022, Kovid Goyal <kovid at kovidgoyal.net>
from lxml import etree, html
from qt.core import QUrl
from urllib.parse import urlencode
from calibre.gui2 import open_url
from calibre.gui2.store.search_result import SearchResult
from calibre.scraper.simple import read_url
class AmazonStore:
minimum_calibre_version = (5, 40, 1)
SEARCH_BASE_URL = 'https://www.amazon.com/s/'
SEARCH_BASE_QUERY = {'i': 'digital-text'}
BY = 'by'
KINDLE_EDITION = 'Kindle Edition'
DETAILS_URL = 'https://amazon.com/dp/'
STORE_LINK = 'https://www.amazon.com/Kindle-eBooks'
DRM_SEARCH_TEXT = 'Simultaneous Device Usage'
DRM_FREE_TEXT = 'Unlimited'
FIELD_KEYWORDS = 'k'
def search_amazon(self, query, max_results=10, timeout=60, write_html_to=None):
field_keywords = self.FIELD_KEYWORDS
uquery = self.SEARCH_BASE_QUERY.copy()
uquery[field_keywords] = query
def asbytes(x):
if isinstance(x, type('')):
x = x.encode('utf-8')
return x
uquery = {asbytes(k):asbytes(v) for k, v in uquery.items()}
url = self.SEARCH_BASE_URL + '?' + urlencode(uquery)
counter = max_results
raw = read_url(self.scraper_storage, url, timeout=timeout)
if write_html_to is not None:
with open(write_html_to, 'w') as f:
f.write(raw)
doc = html.fromstring(raw)
for result in doc.xpath('//div[contains(@class, "s-result-list")]//div[@data-index and @data-asin]'):
kformat = ''.join(result.xpath('.//a[contains(text(), "{}")]//text()'.format(self.KINDLE_EDITION)))
# 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.
if 'kindle' not in kformat.lower():
continue
asin = result.get('data-asin')
if not asin:
continue
cover_url = ''.join(result.xpath('.//img/@src'))
title = etree.tostring(result.xpath('.//h2')[0], method='text', encoding='unicode')
adiv = result.xpath('.//div[contains(@class, "a-color-secondary")]')[0]
aparts = etree.tostring(adiv, method='text', encoding='unicode').split()
idx = aparts.index(self.BY)
author = ' '.join(aparts[idx+1:]).split('|')[0].strip()
price = ''
for span in result.xpath('.//span[contains(@class, "a-price")]/span[contains(@class, "a-offscreen")]'):
q = ''.join(span.xpath('./text()'))
if q:
price = q
break
counter -= 1
s = SearchResult()
s.cover_url = cover_url.strip()
s.title = title.strip()
s.author = author.strip()
s.detail_item = asin.strip()
s.price = price.strip()
s.formats = 'Kindle'
yield s
def get_details_amazon(self, search_result, timeout):
url = self.DETAILS_URL + search_result.detail_item
raw = read_url(self.scraper_storage, url, timeout=timeout)
idata = html.fromstring(raw)
return self.parse_details_amazon(idata, search_result)
def parse_details_amazon(self, idata, search_result):
if idata.xpath('boolean(//div[@class="content"]//li/b[contains(text(), "' +
self.DRM_SEARCH_TEXT + '")])'):
if idata.xpath('boolean(//div[@class="content"]//li[contains(., "' +
self.DRM_FREE_TEXT + '") and contains(b, "' +
self.DRM_SEARCH_TEXT + '")])'):
search_result.drm = SearchResult.DRM_UNLOCKED
else:
search_result.drm = SearchResult.DRM_UNKNOWN
else:
search_result.drm = SearchResult.DRM_LOCKED
return True
def open(self, parent=None, detail_item=None, external=False):
store_link = (self.DETAILS_URL + detail_item) if detail_item else self.STORE_LINK
open_url(QUrl(store_link))
def search(self, query, max_results=10, timeout=60):
for result in self.search_amazon(query, max_results=max_results, timeout=timeout):
yield result
def get_details(self, search_result, timeout):
return self.get_details_amazon(search_result, timeout)
def develop_plugin(self):
import sys
for result in self.search_amazon(' '.join(sys.argv[1:]), write_html_to='/t/amazon.html'):
print(result)

151
src/calibre/gui2/store/stores/amazon_au_plugin.py
View File

@ -3,150 +3,27 @@
# License: GPLv3 Copyright: 2015, Kovid Goyal <kovid at kovidgoyal.net>
from __future__ import absolute_import, division, print_function, unicode_literals
store_version = 5 # Needed for dynamic plugin loading
store_version = 20 # Needed for dynamic plugin loading
from contextlib import closing
try:
from urllib.parse import urlencode
except ImportError:
from urllib import urlencode
from lxml import html
from qt.core import QUrl
from calibre import browser
from calibre.gui2 import open_url
from calibre.gui2.store import StorePlugin
from calibre.gui2.store.search_result import SearchResult
SEARCH_BASE_URL = 'https://www.amazon.com.au/s/'
SEARCH_BASE_QUERY = {'url': 'search-alias=digital-text'}
DETAILS_URL = 'https://amazon.com.au/dp/'
STORE_LINK = 'https://www.amazon.com.au'
DRM_SEARCH_TEXT = 'Simultaneous Device Usage'
DRM_FREE_TEXT = 'Unlimited'
try:
from calibre.gui2.store.amazon_base import AmazonStore
except ImportError:
class AmazonStore:
minimum_calibre_version = 9999, 0, 0
def get_user_agent():
return 'Mozilla/5.0 (Windows NT 6.1; Trident/7.0; rv:11.0) like Gecko'
class Base(AmazonStore):
scraper_storage = []
SEARCH_BASE_URL = 'https://www.amazon.com.au/s/'
SEARCH_BASE_QUERY = {'url': 'search-alias=digital-text'}
DETAILS_URL = 'https://amazon.com.au/dp/'
STORE_LINK = 'https://www.amazon.com.au'
def search_amazon(query, max_results=10, timeout=60,
write_html_to=None,
base_url=SEARCH_BASE_URL,
base_query=SEARCH_BASE_QUERY,
field_keywords='field-keywords'
):
uquery = base_query.copy()
uquery[field_keywords] = query
def asbytes(x):
if isinstance(x, type('')):
x = x.encode('utf-8')
return x
uquery = {asbytes(k):asbytes(v) for k, v in uquery.items()}
url = base_url + '?' + urlencode(uquery)
br = browser(user_agent=get_user_agent())
counter = max_results
with closing(br.open(url, timeout=timeout)) as f:
raw = f.read()
if write_html_to is not None:
with open(write_html_to, 'wb') as f:
f.write(raw)
doc = html.fromstring(raw)
try:
results = doc.xpath('//div[@id="atfResults" and @class]')[0]
except IndexError:
return
if 's-result-list-parent-container' in results.get('class', ''):
data_xpath = "descendant-or-self::li[@class and contains(concat(' ', normalize-space(@class), ' '), ' s-result-item ')]"
format_xpath = './/a[@title="Kindle Edition"]/@title'
asin_xpath = '@data-asin'
cover_xpath = "descendant-or-self::img[@class and contains(concat(' ', normalize-space(@class), ' '), ' s-access-image ')]/@src"
title_xpath = "descendant-or-self::h2[@class and contains(concat(' ', normalize-space(@class), ' '), ' s-access-title ')]//text()"
author_xpath = './/span[starts-with(text(), "by ")]/following-sibling::span//text()'
price_xpath = ('descendant::div[@class="a-row a-spacing-none" and'
' not(span[contains(@class, "kindle-unlimited")])]//span[contains(@class, "s-price")]//text()')
else:
return
for data in doc.xpath(data_xpath):
if counter <= 0:
break
# Even though we are searching digital-text only Amazon will still
# put in results for non Kindle books (author pages). Se 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
# 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))
author = ''.join(data.xpath(author_xpath))
try:
author = author.split('by ', 1)[1].split(" (")[0]
except:
class AmazonKindleStore(Base, StorePlugin):
pass
price = ''.join(data.xpath(price_xpath))
counter -= 1
s = SearchResult()
s.cover_url = cover_url.strip()
s.title = title.strip()
s.author = author.strip()
s.price = price.strip()
s.detail_item = asin.strip()
s.formats = 'Kindle'
yield s
class AmazonKindleStore(StorePlugin):
def open(self, parent=None, detail_item=None, external=False):
store_link = (DETAILS_URL + detail_item) if detail_item else STORE_LINK
open_url(QUrl(store_link))
def search(self, query, max_results=10, timeout=60):
for result in search_amazon(query, max_results=max_results, timeout=timeout):
yield result
def get_details(self, search_result, timeout):
url = DETAILS_URL
br = browser(user_agent=get_user_agent())
with closing(br.open(url + search_result.detail_item, timeout=timeout)) as nf:
idata = html.fromstring(nf.read())
if idata.xpath('boolean(//div[@class="content"]//li/b[contains(text(), "' +
DRM_SEARCH_TEXT + '")])'):
if idata.xpath('boolean(//div[@class="content"]//li[contains(., "' +
DRM_FREE_TEXT + '") and contains(b, "' +
DRM_SEARCH_TEXT + '")])'):
search_result.drm = SearchResult.DRM_UNLOCKED
else:
search_result.drm = SearchResult.DRM_UNKNOWN
else:
search_result.drm = SearchResult.DRM_LOCKED
return True
if __name__ == '__main__':
import sys
for result in search_amazon(' '.join(sys.argv[1:]), write_html_to='/t/amazon.html'):
print(result)
Base().develop_plugin()

151
src/calibre/gui2/store/stores/amazon_ca_plugin.py
View File

@ -3,150 +3,27 @@
# License: GPLv3 Copyright: 2015, Kovid Goyal <kovid at kovidgoyal.net>
from __future__ import absolute_import, division, print_function, unicode_literals
store_version = 7 # Needed for dynamic plugin loading
store_version = 20 # Needed for dynamic plugin loading
from contextlib import closing
try:
from urllib.parse import urlencode
except ImportError:
from urllib import urlencode
from lxml import html
from qt.core import QUrl
from calibre import browser
from calibre.gui2 import open_url
from calibre.gui2.store import StorePlugin
from calibre.gui2.store.search_result import SearchResult
SEARCH_BASE_URL = 'https://www.amazon.ca/s/'
SEARCH_BASE_QUERY = {'url': 'search-alias=digital-text'}
DETAILS_URL = 'https://amazon.ca/dp/'
STORE_LINK = 'https://www.amazon.ca'
DRM_SEARCH_TEXT = 'Simultaneous Device Usage'
DRM_FREE_TEXT = 'Unlimited'
try:
from calibre.gui2.store.amazon_base import AmazonStore
except ImportError:
class AmazonStore:
minimum_calibre_version = 9999, 0, 0
def get_user_agent():
return 'Mozilla/5.0 (Windows NT 6.1; Trident/7.0; rv:11.0) like Gecko'
class Base(AmazonStore):
scraper_storage = []
SEARCH_BASE_URL = 'https://www.amazon.ca/s/'
SEARCH_BASE_QUERY = {'url': 'search-alias=digital-text'}
DETAILS_URL = 'https://amazon.ca/dp/'
STORE_LINK = 'https://www.amazon.ca'
def search_amazon(query, max_results=10, timeout=60,
write_html_to=None,
base_url=SEARCH_BASE_URL,
base_query=SEARCH_BASE_QUERY,
field_keywords='field-keywords'
):
uquery = base_query.copy()
uquery[field_keywords] = query
def asbytes(x):
if isinstance(x, type('')):
x = x.encode('utf-8')
return x
uquery = {asbytes(k):asbytes(v) for k, v in uquery.items()}
url = base_url + '?' + urlencode(uquery)
br = browser(user_agent=get_user_agent())
counter = max_results
with closing(br.open(url, timeout=timeout)) as f:
raw = f.read()
if write_html_to is not None:
with open(write_html_to, 'wb') as f:
f.write(raw)
doc = html.fromstring(raw)
try:
results = doc.xpath('//div[@id="atfResults" and @class]')[0]
except IndexError:
return
if 's-result-list-parent-container' in results.get('class', ''):
data_xpath = "descendant-or-self::li[@class and contains(concat(' ', normalize-space(@class), ' '), ' s-result-item ')]"
format_xpath = './/a[@title="Kindle Edition"]/@title'
asin_xpath = '@data-asin'
cover_xpath = "descendant-or-self::img[@class and contains(concat(' ', normalize-space(@class), ' '), ' s-access-image ')]/@src"
title_xpath = "descendant-or-self::h2[@class and contains(concat(' ', normalize-space(@class), ' '), ' s-access-title ')]//text()"
author_xpath = './/span[starts-with(text(), "by ")]/following-sibling::span//text()'
price_xpath = ('descendant::div[@class="a-row a-spacing-none" and'
' not(span[contains(@class, "kindle-unlimited")])]//span[contains(@class, "s-price")]//text()')
else:
return
for data in doc.xpath(data_xpath):
if counter <= 0:
break
# Even though we are searching digital-text only Amazon will still
# put in results for non Kindle books (author pages). Se 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
# 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))
author = ''.join(data.xpath(author_xpath))
try:
author = author.split('by ', 1)[1].split(" (")[0]
except:
class AmazonKindleStore(Base, StorePlugin):
pass
price = ''.join(data.xpath(price_xpath))
counter -= 1
s = SearchResult()
s.cover_url = cover_url.strip()
s.title = title.strip()
s.author = author.strip()
s.price = price.strip()
s.detail_item = asin.strip()
s.formats = 'Kindle'
yield s
class AmazonKindleStore(StorePlugin):
def open(self, parent=None, detail_item=None, external=False):
store_link = (DETAILS_URL + detail_item) if detail_item else STORE_LINK
open_url(QUrl(store_link))
def search(self, query, max_results=10, timeout=60):
for result in search_amazon(query, max_results=max_results, timeout=timeout):
yield result
def get_details(self, search_result, timeout):
url = DETAILS_URL
br = browser(user_agent=get_user_agent())
with closing(br.open(url + search_result.detail_item, timeout=timeout)) as nf:
idata = html.fromstring(nf.read())
if idata.xpath('boolean(//div[@class="content"]//li/b[contains(text(), "' +
DRM_SEARCH_TEXT + '")])'):
if idata.xpath('boolean(//div[@class="content"]//li[contains(., "' +
DRM_FREE_TEXT + '") and contains(b, "' +
DRM_SEARCH_TEXT + '")])'):
search_result.drm = SearchResult.DRM_UNLOCKED
else:
search_result.drm = SearchResult.DRM_UNKNOWN
else:
search_result.drm = SearchResult.DRM_LOCKED
return True
if __name__ == '__main__':
import sys
for result in search_amazon(' '.join(sys.argv[1:]), write_html_to='/t/amazon.html'):
print(result)
Base().develop_plugin()

153
src/calibre/gui2/store/stores/amazon_in_plugin.py
View File

@ -3,152 +3,27 @@
# License: GPLv3 Copyright: 2015, Kovid Goyal <kovid at kovidgoyal.net>
from __future__ import absolute_import, division, print_function, unicode_literals
store_version = 5 # Needed for dynamic plugin loading
store_version = 20 # Needed for dynamic plugin loading
from contextlib import closing
try:
from urllib.parse import urlencode
except ImportError:
from urllib import urlencode
from lxml import html
from qt.core import QUrl
from calibre import browser
from calibre.gui2 import open_url
from calibre.gui2.store import StorePlugin
from calibre.gui2.store.search_result import SearchResult
SEARCH_BASE_URL = 'https://www.amazon.in/s/'
SEARCH_BASE_QUERY = {'url': 'search-alias=digital-text'}
DETAILS_URL = 'https://amazon.in/dp/'
STORE_LINK = 'https://www.amazon.in'
DRM_SEARCH_TEXT = 'Simultaneous Device Usage'
DRM_FREE_TEXT = 'Unlimited'
try:
from calibre.gui2.store.amazon_base import AmazonStore
except ImportError:
class AmazonStore:
minimum_calibre_version = 9999, 0, 0
def get_user_agent():
return 'Mozilla/5.0 (Windows NT 6.1; Trident/7.0; rv:11.0) like Gecko'
class Base(AmazonStore):
scraper_storage = []
SEARCH_BASE_URL = 'https://www.amazon.in/s/'
SEARCH_BASE_QUERY = {'url': 'search-alias=digital-text'}
DETAILS_URL = 'https://amazon.in/dp/'
STORE_LINK = 'https://www.amazon.in'
def search_amazon(query, max_results=10, timeout=60,
write_html_to=None,
base_url=SEARCH_BASE_URL,
base_query=SEARCH_BASE_QUERY,
field_keywords='field-keywords'
):
uquery = base_query.copy()
uquery[field_keywords] = query
def asbytes(x):
if isinstance(x, type('')):
x = x.encode('utf-8')
return x
uquery = {asbytes(k):asbytes(v) for k, v in uquery.items()}
url = base_url + '?' + urlencode(uquery)
br = browser(user_agent=get_user_agent())
counter = max_results
with closing(br.open(url, timeout=timeout)) as f:
raw = f.read()
if write_html_to is not None:
with open(write_html_to, 'wb') as f:
f.write(raw)
doc = html.fromstring(raw)
try:
results = doc.xpath('//div[@id="atfResults" and @class]')[0]
except IndexError:
return
if 's-result-list-parent-container' in results.get('class', ''):
data_xpath = "descendant-or-self::li[@class and contains(concat(' ', normalize-space(@class), ' '), ' s-result-item ')]"
format_xpath = './/a[@title="Kindle Edition"]/@title'
asin_xpath = '@data-asin'
cover_xpath = "descendant-or-self::img[@class and contains(concat(' ', normalize-space(@class), ' '), ' s-access-image ')]/@src"
title_xpath = "descendant-or-self::h2[@class and contains(concat(' ', normalize-space(@class), ' '), ' s-access-title ')]//text()"
author_xpath = './/span[starts-with(text(), "by ")]/following-sibling::span//text()'
price_xpath = ('descendant::div[@class="a-row a-spacing-none" and'
' not(span[contains(@class, "kindle-unlimited")])]//span[contains(@class, "s-price")]//text()')
else:
return
for data in doc.xpath(data_xpath):
if counter <= 0:
break
# Even though we are searching digital-text only Amazon will still
# put in results for non Kindle books (author pages). Se 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
# 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))
author = ''.join(data.xpath(author_xpath))
try:
author = author.split('by ', 1)[1].split(" (")[0]
except:
class AmazonKindleStore(Base, StorePlugin):
pass
price = ''.join(data.xpath(price_xpath))
counter -= 1
s = SearchResult()
s.cover_url = cover_url.strip()
s.title = title.strip()
s.author = author.strip()
s.price = price.strip()
if s.price:
s.price = '₹ ' + s.price
s.detail_item = asin.strip()
s.formats = 'Kindle'
yield s
class AmazonKindleStore(StorePlugin):
def open(self, parent=None, detail_item=None, external=False):
store_link = (DETAILS_URL + detail_item) if detail_item else STORE_LINK
open_url(QUrl(store_link))
def search(self, query, max_results=10, timeout=60):
for result in search_amazon(query, max_results=max_results, timeout=timeout):
yield result
def get_details(self, search_result, timeout):
url = DETAILS_URL
br = browser(user_agent=get_user_agent())
with closing(br.open(url + search_result.detail_item, timeout=timeout)) as nf:
idata = html.fromstring(nf.read())
if idata.xpath('boolean(//div[@class="content"]//li/b[contains(text(), "' +
DRM_SEARCH_TEXT + '")])'):
if idata.xpath('boolean(//div[@class="content"]//li[contains(., "' +
DRM_FREE_TEXT + '") and contains(b, "' +
DRM_SEARCH_TEXT + '")])'):
search_result.drm = SearchResult.DRM_UNLOCKED
else:
search_result.drm = SearchResult.DRM_UNKNOWN
else:
search_result.drm = SearchResult.DRM_LOCKED
return True
if __name__ == '__main__':
import sys
for result in search_amazon(' '.join(sys.argv[1:]), write_html_to='/t/amazon.html'):
print(result)
Base().develop_plugin()

128
src/calibre/gui2/store/stores/amazon_plugin.py
View File

@ -3,129 +3,23 @@
# License: GPLv3 Copyright: 2015, Kovid Goyal <kovid at kovidgoyal.net>
from __future__ import absolute_import, division, print_function, unicode_literals
store_version = 19 # Needed for dynamic plugin loading
store_version = 20 # Needed for dynamic plugin loading
from contextlib import closing
try:
from urllib.parse import urlencode
except ImportError:
from urllib import urlencode
from lxml import html, etree
from qt.core import QUrl
from calibre import browser
from calibre.gui2 import open_url
from calibre.gui2.store import StorePlugin
from calibre.gui2.store.search_result import SearchResult
SEARCH_BASE_URL = 'https://www.amazon.com/s/'
SEARCH_BASE_QUERY = {'i': 'digital-text'}
BY = 'by'
KINDLE_EDITION = 'Kindle Edition'
DETAILS_URL = 'https://amazon.com/dp/'
STORE_LINK = 'https://www.amazon.com/Kindle-eBooks'
DRM_SEARCH_TEXT = 'Simultaneous Device Usage'
DRM_FREE_TEXT = 'Unlimited'
try:
from calibre.gui2.store.amazon_base import AmazonStore
except ImportError:
class AmazonStore:
minimum_calibre_version = 9999, 0, 0
def get_user_agent():
return 'Mozilla/5.0 (Windows NT 6.1; Trident/7.0; rv:11.0) like Gecko'
class Base(AmazonStore):
scraper_storage = []
def search_amazon(query, max_results=10, timeout=60,
write_html_to=None,
base_url=SEARCH_BASE_URL,
base_query=SEARCH_BASE_QUERY,
field_keywords='k'
):
uquery = base_query.copy()
uquery[field_keywords] = query
def asbytes(x):
if isinstance(x, type('')):
x = x.encode('utf-8')
return x
uquery = {asbytes(k):asbytes(v) for k, v in uquery.items()}
url = base_url + '?' + urlencode(uquery)
br = browser(user_agent=get_user_agent())
counter = max_results
with closing(br.open(url, timeout=timeout)) as f:
raw = f.read()
if write_html_to is not None:
with open(write_html_to, 'wb') as f:
f.write(raw)
doc = html.fromstring(raw)
for result in doc.xpath('//div[contains(@class, "s-result-list")]//div[@data-index and @data-asin]'):
kformat = ''.join(result.xpath('.//a[contains(text(), "{}")]//text()'.format(KINDLE_EDITION)))
# Even though we are searching digital-text only Amazon will still
# put in results for non Kindle books (author pages). Se we need
# to explicitly check if the item is a Kindle book and ignore it
# if it isn't.
if 'kindle' not in kformat.lower():
continue
asin = result.get('data-asin')
if not asin:
continue
cover_url = ''.join(result.xpath('.//img/@src'))
title = etree.tostring(result.xpath('.//h2')[0], method='text', encoding='unicode')
adiv = result.xpath('.//div[contains(@class, "a-color-secondary")]')[0]
aparts = etree.tostring(adiv, method='text', encoding='unicode').split()
idx = aparts.index(BY)
author = ' '.join(aparts[idx+1:]).split('|')[0].strip()
price = ''
for span in result.xpath('.//span[contains(@class, "a-price")]/span[contains(@class, "a-offscreen")]'):
q = ''.join(span.xpath('./text()'))
if q:
price = q
break
counter -= 1
s = SearchResult()
s.cover_url = cover_url.strip()
s.title = title.strip()
s.author = author.strip()
s.detail_item = asin.strip()
s.price = price.strip()
s.formats = 'Kindle'
yield s
class AmazonKindleStore(StorePlugin):
def open(self, parent=None, detail_item=None, external=False):
store_link = (DETAILS_URL + detail_item) if detail_item else STORE_LINK
open_url(QUrl(store_link))
def search(self, query, max_results=10, timeout=60):
for result in search_amazon(query, max_results=max_results, timeout=timeout):
yield result
def get_details(self, search_result, timeout):
url = DETAILS_URL
br = browser(user_agent=get_user_agent())
with closing(br.open(url + search_result.detail_item, timeout=timeout)) as nf:
idata = html.fromstring(nf.read())
if idata.xpath('boolean(//div[@class="content"]//li/b[contains(text(), "' +
DRM_SEARCH_TEXT + '")])'):
if idata.xpath('boolean(//div[@class="content"]//li[contains(., "' +
DRM_FREE_TEXT + '") and contains(b, "' +
DRM_SEARCH_TEXT + '")])'):
search_result.drm = SearchResult.DRM_UNLOCKED
else:
search_result.drm = SearchResult.DRM_UNKNOWN
else:
search_result.drm = SearchResult.DRM_LOCKED
return True
class AmazonKindleStore(Base, StorePlugin):
pass
if __name__ == '__main__':
import sys
for result in search_amazon(' '.join(sys.argv[1:]), write_html_to='/t/amazon.html'):
print(result)
Base().develop_plugin()

151
src/calibre/gui2/store/stores/amazon_uk_plugin.py
View File

@ -3,150 +3,27 @@
# License: GPLv3 Copyright: 2015, Kovid Goyal <kovid at kovidgoyal.net>
from __future__ import absolute_import, division, print_function, unicode_literals
store_version = 15 # Needed for dynamic plugin loading
store_version = 20 # Needed for dynamic plugin loading
from contextlib import closing
try:
from urllib.parse import urlencode
except ImportError:
from urllib import urlencode
from lxml import html
from qt.core import QUrl
from calibre import browser
from calibre.gui2 import open_url
from calibre.gui2.store import StorePlugin
from calibre.gui2.store.search_result import SearchResult
SEARCH_BASE_URL = 'https://www.amazon.co.uk/s/'
SEARCH_BASE_QUERY = {'url': 'search-alias=digital-text'}
DETAILS_URL = 'https://amazon.co.uk/dp/'
STORE_LINK = 'https://www.amazon.co.uk'
DRM_SEARCH_TEXT = 'Simultaneous Device Usage'
DRM_FREE_TEXT = 'Unlimited'
try:
from calibre.gui2.store.amazon_base import AmazonStore
except ImportError:
class AmazonStore:
minimum_calibre_version = 9999, 0, 0
def get_user_agent():
return 'Mozilla/5.0 (Windows NT 6.1; Trident/7.0; rv:11.0) like Gecko'
class Base(AmazonStore):
scraper_storage = []
SEARCH_BASE_URL = 'https://www.amazon.co.uk/s/'
SEARCH_BASE_QUERY = {'url': 'search-alias=digital-text'}
DETAILS_URL = 'https://amazon.co.uk/dp/'
STORE_LINK = 'https://www.amazon.co.uk'
def search_amazon(query, max_results=10, timeout=60,
write_html_to=None,
base_url=SEARCH_BASE_URL,
base_query=SEARCH_BASE_QUERY,
field_keywords='field-keywords'
):
uquery = base_query.copy()
uquery[field_keywords] = query
def asbytes(x):
if isinstance(x, type('')):
x = x.encode('utf-8')
return x
uquery = {asbytes(k):asbytes(v) for k, v in uquery.items()}
url = base_url + '?' + urlencode(uquery)
br = browser(user_agent=get_user_agent())
counter = max_results
with closing(br.open(url, timeout=timeout)) as f:
raw = f.read()
if write_html_to is not None:
with open(write_html_to, 'wb') as f:
f.write(raw)
doc = html.fromstring(raw)
try:
results = doc.xpath('//div[@id="atfResults" and @class]')[0]
except IndexError:
return
if 's-result-list-parent-container' in results.get('class', ''):
data_xpath = "descendant-or-self::li[@class and contains(concat(' ', normalize-space(@class), ' '), ' s-result-item ')]"
format_xpath = './/a[contains(text(), "Kindle Edition")]//text()'
asin_xpath = '@data-asin'
cover_xpath = "descendant-or-self::img[@class and contains(concat(' ', normalize-space(@class), ' '), ' s-access-image ')]/@src"
title_xpath = "descendant-or-self::h2[@class and contains(concat(' ', normalize-space(@class), ' '), ' s-access-title ')]//text()"
author_xpath = './/span[starts-with(text(), "by ")]/following-sibling::span//text()'
price_xpath = ('descendant::div[@class="a-row a-spacing-none" and'
' not(span[contains(@class, "kindle-unlimited")])]//span[contains(@class, "s-price")]//text()')
else:
return
for data in doc.xpath(data_xpath):
if counter <= 0:
break
# Even though we are searching digital-text only Amazon will still
# put in results for non Kindle books (author pages). Se 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
# 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))
author = ''.join(data.xpath(author_xpath))
try:
author = author.split('by ', 1)[1].split(" (")[0]
except:
class AmazonKindleStore(Base, StorePlugin):
pass
price = ''.join(data.xpath(price_xpath))
counter -= 1
s = SearchResult()
s.cover_url = cover_url.strip()
s.title = title.strip()
s.author = author.strip()
s.price = price.strip()
s.detail_item = asin.strip()
s.formats = 'Kindle'
yield s
class AmazonKindleStore(StorePlugin):
def open(self, parent=None, detail_item=None, external=False):
store_link = (DETAILS_URL + detail_item) if detail_item else STORE_LINK
open_url(QUrl(store_link))
def search(self, query, max_results=10, timeout=60):
for result in search_amazon(query, max_results=max_results, timeout=timeout):
yield result
def get_details(self, search_result, timeout):
url = DETAILS_URL
br = browser(user_agent=get_user_agent())
with closing(br.open(url + search_result.detail_item, timeout=timeout)) as nf:
idata = html.fromstring(nf.read())
if idata.xpath('boolean(//div[@class="content"]//li/b[contains(text(), "' +
DRM_SEARCH_TEXT + '")])'):
if idata.xpath('boolean(//div[@class="content"]//li[contains(., "' +
DRM_FREE_TEXT + '") and contains(b, "' +
DRM_SEARCH_TEXT + '")])'):
search_result.drm = SearchResult.DRM_UNLOCKED
else:
search_result.drm = SearchResult.DRM_UNKNOWN
else:
search_result.drm = SearchResult.DRM_LOCKED
return True
if __name__ == '__main__':
import sys
for result in search_amazon(' '.join(sys.argv[1:]), write_html_to='/t/amazon.html'):
print(result)
Base().develop_plugin()