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

Merge changes from lp:~tomek3d/calibre/store.

Browse Source
This commit is contained in:
John Schember 2012-06-12 21:06:30 -04:00
commit 15a451fe63
1 changed files with 11 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
src/calibre/gui2/store/stores/virtualo_plugin.py
View File

@ -40,39 +40,35 @@ 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 = [ form.split('_')[-1].replace('.png', '') for form in data.xpath('.//div[@style="width:55%;float:left;text-align:left;height:18px;"]//img/@src')]
formats = ', '.join(data.xpath('.//span[@class="format"]/a/text()')) nodrm = no_drm_pattern.search(''.join(data.xpath('.//div[@style="width:45%;float:right;text-align:right;height:18px;"]/div/div/text()')))
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
s = SearchResult() s = SearchResult()
s.cover_url = cover_url.split('.jpg')[0] + '.jpg' s.cover_url = cover_url.split('.jpg')[0] + '.jpg'
s.title = title.strip() + ' ' + formats s.title = title.strip()
s.author = author.strip() s.author = author.strip()
s.price = price + ' zł' s.price = price + ' zł'
s.detail_item = 'http://virtualo.pl' + id.strip().split('http://')[0] s.detail_item = 'http://virtualo.pl' + id.strip().split('http://')[0]
s.formats = formats.upper().strip() s.formats = ', '.join(formats).upper()
s.drm = SearchResult.DRM_LOCKED if drm else SearchResult.DRM_UNLOCKED s.drm = SearchResult.DRM_UNLOCKED if nodrm else SearchResult.DRM_UNKNOWN
yield s yield s