Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

draft version of improved virtualo plugin

Browse Source
This commit is contained in:
Tomasz Długosz 2012-06-10 12:12:26 +02:00
parent ebc1f0e347
commit 467f0be76f
1 changed files with 8 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
src/calibre/gui2/store/stores/virtualo_plugin.py
View File

@ -40,29 +40,25 @@ class VirtualoStore(BasicStoreConfig, StorePlugin):
url = 'http://virtualo.pl/?q=' + urllib.quote(query) + '&f=format_id:4,6,3' url = 'http://virtualo.pl/?q=' + urllib.quote(query) + '&f=format_id:4,6,3'
br = browser() br = browser()
drm_pattern = re.compile("ADE") no_drm_pattern = re.compile("Znak wodny")
counter = max_results counter = max_results
with closing(br.open(url, timeout=timeout)) as f: with closing(br.open(url, timeout=timeout)) as f:
doc = html.fromstring(f.read()) doc = html.fromstring(f.read())
for data in doc.xpath('//div[@id="product_list"]/div/div[@class="column"]'): for data in doc.xpath('//div[@id="content"]//div[@class="list_box list_box_border"]'):
if counter <= 0: if counter <= 0:
break break
id = ''.join(data.xpath('.//table/tr[1]/td[1]/a/@href')) id = ''.join(data.xpath('.//div[@class="list_middle_left"]//a/@href'))
if not id: if not id:
continue continue
price = ''.join(data.xpath('.//span[@class="price"]/text() | .//span[@class="price abbr"]/text()')) price = ''.join(data.xpath('.//span[@class="price"]/text() | .//span[@class="price abbr"]/text()'))
cover_url = ''.join(data.xpath('.//table/tr[1]/td[1]/a/img/@src')) cover_url = ''.join(data.xpath('.//div[@class="list_middle_left"]//a/img/@src'))
title = ''.join(data.xpath('.//div[@class="title"]/a/text()')) title = ''.join(data.xpath('.//div[@class="list_title list_text_left"]/a/text()'))
title = re.sub(r'\ WM', '', title) author = ', '.join(data.xpath('.//div[@class="list_authors list_text_left"]/a/text()'))
author = ', '.join(data.xpath('.//div[@class="authors"]/a/text()')) formats = ', '#.join(data.xpath('.//div[2]/div[3]//div[@class="list_vertical_wrap_middle"]/img/@src()'))
formats = ', '.join(data.xpath('.//span[@class="format"]/a/text()')) drm = not no_drm_pattern.search(formats)
formats = re.sub(r'(, )?ONLINE(, )?', '', formats)
drm = drm_pattern.search(formats)
formats = re.sub(r'(, )?ADE(, )?', '', formats)
formats = re.sub(r'\ WM', '', formats)
counter -= 1 counter -= 1