Store: Fix Wizards Press store when it returns an exact match by loading the detail page.

This commit is contained in:
John Schember 2011-05-16 18:48:14 -04:00
parent a3aa8047c9
commit c69f442060

View File

@ -44,40 +44,70 @@ class WizardsTowerBooksStore(BasicStoreConfig, StorePlugin):
counter = max_results
with closing(br.open(url, timeout=timeout)) as f:
doc = html.fromstring(f.read())
for data in doc.xpath('//table[@class="gridp"]//td'):
if counter <= 0:
break
id = ''.join(data.xpath('.//span[@class="prti"]/a/@href'))
id = id.strip()
if not id:
continue
cover_url = ''.join(data.xpath('.//div[@class="prim"]/a/img/@src'))
cover_url = url_slash_cleaner(self.url + cover_url.strip())
price = ''.join(data.xpath('.//font[@class="selling_price"]//text()'))
price = price.strip()
if not price:
continue
title = ''.join(data.xpath('.//span[@class="prti"]/a/b/text()'))
author = ''.join(data.xpath('.//p[@class="last"]/text()'))
a, b, author = author.partition(' by ')
counter -= 1
if 'search.html' in f.geturl():
for data in doc.xpath('//table[@class="gridp"]//td'):
if counter <= 0:
break
id = ''.join(data.xpath('.//span[@class="prti"]/a/@href'))
id = id.strip()
if not id:
continue
cover_url = ''.join(data.xpath('.//div[@class="prim"]/a/img/@src'))
cover_url = url_slash_cleaner(self.url + cover_url.strip())
price = ''.join(data.xpath('.//font[@class="selling_price"]//text()'))
price = price.strip()
if not price:
continue
title = ''.join(data.xpath('.//span[@class="prti"]/a/b/text()'))
author = ''.join(data.xpath('.//p[@class="last"]/text()'))
a, b, author = author.partition(' by ')
counter -= 1
s = SearchResult()
s.cover_url = cover_url
s.title = title.strip()
s.author = author.strip()
s.price = price.strip()
s.detail_item = id.strip()
s.drm = SearchResult.DRM_UNLOCKED
yield s
# Exact match brought us to the books detail page.
else:
s = SearchResult()
s.cover_url = cover_url
s.title = title.strip()
s.author = author.strip()
s.price = price.strip()
s.detail_item = id.strip()
cover_url = ''.join(doc.xpath('//div[@id="image"]/a/img[@title="Zoom"]/@src')).strip()
s.cover_url = url_slash_cleaner(self.url + cover_url.strip())
s.title = ''.join(doc.xpath('//form[@name="details"]/h1/text()')).strip()
authors = doc.xpath('//p[contains(., "Author:")]//text()')
author_index = None
for i, a in enumerate(authors):
if 'author' in a.lower():
author_index = i + 1
break
if author_index is not None and len(authors) > author_index:
a = authors[author_index]
a = a.replace(u'\xa0', '')
s.author = a.strip()
s.price = ''.join(doc.xpath('//span[@id="price_selling"]//text()')).strip()
s.detail_item = f.geturl().replace(self.url, '').strip()
s.formats = ', '.join(doc.xpath('//select[@id="N1_"]//option//text()'))
s.drm = SearchResult.DRM_UNLOCKED
yield s
def get_details(self, search_result, timeout):
if search_result.formats:
return False
br = browser()
with closing(br.open(url_slash_cleaner(self.url + search_result.detail_item), timeout=timeout)) as nf:
idata = html.fromstring(nf.read())