Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-11-03 19:17:02 -05:00
Code Issues Packages Projects Releases Wiki Activity

pep8

Browse Source
This commit is contained in:
Kovid Goyal 2014-05-08 07:26:51 +05:30
parent fb970e24c6
commit a1f0c360e7
1 changed files with 39 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
src/calibre/ebooks/metadata/sources/ozon.py
View File

@ -50,7 +50,7 @@ class Ozon(Source):
ozon_id = identifiers.get('ozon', None) ozon_id = identifiers.get('ozon', None)
res = None res = None
if ozon_id: if ozon_id:
#no affiliateId is used in search/detail # no affiliateId is used in search/detail
url = '{}/context/detail/id/{}'.format(self.ozon_url, urllib2.quote(ozon_id), _get_affiliateId()) url = '{}/context/detail/id/{}'.format(self.ozon_url, urllib2.quote(ozon_id), _get_affiliateId())
res = ('ozon', ozon_id, url) res = ('ozon', ozon_id, url)
return res return res
@ -64,7 +64,7 @@ class Ozon(Source):
# for ozon.ru search we have to format ISBN with '-' # for ozon.ru search we have to format ISBN with '-'
isbn = _format_isbn(log, identifiers.get('isbn', None)) isbn = _format_isbn(log, identifiers.get('isbn', None))
if isbn and not '-' in isbn: if isbn and '-' not in isbn:
log.error("%s requires formatted ISBN for search. %s cannot be formated - removed. (only Russian ISBN format is supported now)" log.error("%s requires formatted ISBN for search. %s cannot be formated - removed. (only Russian ISBN format is supported now)"
% (self.name, isbn)) % (self.name, isbn))
isbn = None isbn = None
@ -96,7 +96,7 @@ class Ozon(Source):
def identify(self, log, result_queue, abort, title=None, authors=None, def identify(self, log, result_queue, abort, title=None, authors=None,
identifiers={}, timeout=90): # {{{ identifiers={}, timeout=90): # {{{
from lxml import html, etree from lxml import html
from calibre.ebooks.chardet import xml_to_unicode from calibre.ebooks.chardet import xml_to_unicode
if not self.is_configured(): if not self.is_configured():
@ -119,7 +119,7 @@ class Ozon(Source):
entries = doc.xpath(u'//div[@class="SearchResults"]//div[@itemprop="itemListElement"]') entries = doc.xpath(u'//div[@class="SearchResults"]//div[@itemprop="itemListElement"]')
if entries: if entries:
#for entry in entries: # for entry in entries:
# log.debug('entries %s' % etree.tostring(entry)) # log.debug('entries %s' % etree.tostring(entry))
metadata = self.get_metadata(log, entries, title, authors, identifiers) metadata = self.get_metadata(log, entries, title, authors, identifiers)
self.get_all_details(log, metadata, abort, result_queue, identifiers, timeout) self.get_all_details(log, metadata, abort, result_queue, identifiers, timeout)
@ -139,27 +139,27 @@ class Ozon(Source):
def get_metadata_from_detail(self, log, entry, title, authors, identifiers): # {{{ def get_metadata_from_detail(self, log, entry, title, authors, identifiers): # {{{
title = unicode(entry.xpath(u'normalize-space(.//h1[@itemprop="name"][1]/text())')) title = unicode(entry.xpath(u'normalize-space(.//h1[@itemprop="name"][1]/text())'))
#log.debug(u'Tile (from_detail): -----> %s' % title) # log.debug(u'Tile (from_detail): -----> %s' % title)
author = unicode(entry.xpath(u'normalize-space(.//a[contains(@href, "person")][1]/text())')) author = unicode(entry.xpath(u'normalize-space(.//a[contains(@href, "person")][1]/text())'))
#log.debug(u'Author (from_detail): -----> %s' % author) # log.debug(u'Author (from_detail): -----> %s' % author)
norm_authors = map(_normalizeAuthorNameWithInitials, map(unicode.strip, unicode(author).split(u','))) norm_authors = map(_normalizeAuthorNameWithInitials, map(unicode.strip, unicode(author).split(u',')))
mi = Metadata(title, norm_authors) mi = Metadata(title, norm_authors)
ozon_id = entry.xpath(u'substring-before(substring-after(normalize-space(.//a[starts-with(@href, "/context/detail/id/")][1]/@href), "id/"), "/")') ozon_id = entry.xpath(u'substring-before(substring-after(normalize-space(.//a[starts-with(@href, "/context/detail/id/")][1]/@href), "id/"), "/")')
if ozon_id: if ozon_id:
#log.debug(u'ozon_id (from_detail): -----> %s' % ozon_id) # log.debug(u'ozon_id (from_detail): -----> %s' % ozon_id)
mi.identifiers = {'ozon':ozon_id} mi.identifiers = {'ozon':ozon_id}
mi.ozon_cover_url = None mi.ozon_cover_url = None
cover = entry.xpath(u'normalize-space(.//img[1]/@src)') cover = entry.xpath(u'normalize-space(.//img[1]/@src)')
if cover: if cover:
mi.ozon_cover_url = _translateToBigCoverUrl(cover) mi.ozon_cover_url = _translateToBigCoverUrl(cover)
#log.debug(u'mi.ozon_cover_url (from_detail): -----> %s' % mi.ozon_cover_url) # log.debug(u'mi.ozon_cover_url (from_detail): -----> %s' % mi.ozon_cover_url)
mi.rating = self.get_rating(entry) mi.rating = self.get_rating(entry)
#log.debug(u'mi.rating (from_detail): -----> %s' % mi.rating) # log.debug(u'mi.rating (from_detail): -----> %s' % mi.rating)
if not mi.rating: if not mi.rating:
log.debug('No rating (from_detail) found. ozon_id:%s'%ozon_id) log.debug('No rating (from_detail) found. ozon_id:%s'%ozon_id)
@ -248,7 +248,7 @@ class Ozon(Source):
return metadata return metadata
# }}} # }}}
def get_all_details(self, log, metadata, abort, result_queue, identifiers, timeout, cachedPagesDict = {}): # {{{ def get_all_details(self, log, metadata, abort, result_queue, identifiers, timeout, cachedPagesDict={}): # {{{
req_isbn = identifiers.get('isbn', None) req_isbn = identifiers.get('isbn', None)
for mi in metadata: for mi in metadata:
@ -258,7 +258,7 @@ class Ozon(Source):
ozon_id = mi.identifiers['ozon'] ozon_id = mi.identifiers['ozon']
try: try:
self.get_book_details(log, mi, timeout, cachedPagesDict[ozon_id] if cachedPagesDict and cachedPagesDict.has_key(ozon_id) else None) self.get_book_details(log, mi, timeout, cachedPagesDict[ozon_id] if cachedPagesDict and ozon_id in cachedPagesDict else None)
except: except:
log.exception(u'Failed to get details for metadata: %s' % mi.title) log.exception(u'Failed to get details for metadata: %s' % mi.title)
@ -281,10 +281,10 @@ class Ozon(Source):
def to_metadata(self, log, entry): # {{{ def to_metadata(self, log, entry): # {{{
title = unicode(entry.xpath(u'normalize-space(.//span[@itemprop="name"][1]/text())')) title = unicode(entry.xpath(u'normalize-space(.//span[@itemprop="name"][1]/text())'))
#log.debug(u'Tile: -----> %s' % title) # log.debug(u'Tile: -----> %s' % title)
author = unicode(entry.xpath(u'normalize-space(.//a[contains(@href, "person")][1]/text())')) author = unicode(entry.xpath(u'normalize-space(.//a[contains(@href, "person")][1]/text())'))
#log.debug(u'Author: -----> %s' % author) # log.debug(u'Author: -----> %s' % author)
norm_authors = map(_normalizeAuthorNameWithInitials, map(unicode.strip, unicode(author).split(u','))) norm_authors = map(_normalizeAuthorNameWithInitials, map(unicode.strip, unicode(author).split(u',')))
mi = Metadata(title, norm_authors) mi = Metadata(title, norm_authors)
@ -292,22 +292,22 @@ class Ozon(Source):
ozon_id = entry.xpath(u'substring-before(substring-after(normalize-space(.//a[starts-with(@href, "/context/detail/id/")][1]/@href), "id/"), "/")') ozon_id = entry.xpath(u'substring-before(substring-after(normalize-space(.//a[starts-with(@href, "/context/detail/id/")][1]/@href), "id/"), "/")')
if ozon_id: if ozon_id:
mi.identifiers = {'ozon':ozon_id} mi.identifiers = {'ozon':ozon_id}
#log.debug(u'ozon_id: -----> %s' % ozon_id) # log.debug(u'ozon_id: -----> %s' % ozon_id)
mi.ozon_cover_url = None mi.ozon_cover_url = None
cover = entry.xpath(u'normalize-space(.//img[1]/@src)') cover = entry.xpath(u'normalize-space(.//img[1]/@src)')
#log.debug(u'cover: -----> %s' % cover) # log.debug(u'cover: -----> %s' % cover)
if cover: if cover:
mi.ozon_cover_url = _translateToBigCoverUrl(cover) mi.ozon_cover_url = _translateToBigCoverUrl(cover)
#log.debug(u'mi.ozon_cover_url: -----> %s' % mi.ozon_cover_url) # log.debug(u'mi.ozon_cover_url: -----> %s' % mi.ozon_cover_url)
pub_year = None pub_year = None
if pub_year: if pub_year:
mi.pubdate = toPubdate(log, pub_year) mi.pubdate = toPubdate(log, pub_year)
#log.debug('pubdate %s' % mi.pubdate) # log.debug('pubdate %s' % mi.pubdate)
mi.rating = self.get_rating(entry) mi.rating = self.get_rating(entry)
#if not mi.rating: # if not mi.rating:
# log.debug('No rating found. ozon_id:%s'%ozon_id) # log.debug('No rating found. ozon_id:%s'%ozon_id)
return mi return mi
@ -392,13 +392,13 @@ class Ozon(Source):
if not cachedPage: if not cachedPage:
url = self.get_book_url(metadata.get_identifiers())[2] url = self.get_book_url(metadata.get_identifiers())[2]
#log.debug(u'book_details_url', url) # log.debug(u'book_details_url', url)
raw = self.browser.open_novisit(url, timeout=timeout).read() raw = self.browser.open_novisit(url, timeout=timeout).read()
fulldoc = html.fromstring(xml_to_unicode(raw, verbose=True)[0]) fulldoc = html.fromstring(xml_to_unicode(raw, verbose=True)[0])
else: else:
fulldoc = cachedPage fulldoc = cachedPage
#log.debug(u'book_details -> using cached page') # log.debug(u'book_details -> using cached page')
doc = fulldoc.xpath(u'//div[@id="PageContent"][1]')[0] doc = fulldoc.xpath(u'//div[@id="PageContent"][1]')[0]
@ -409,7 +409,7 @@ class Ozon(Source):
series = doc.xpath(xpt_tmpl_a % u'Сери') series = doc.xpath(xpt_tmpl_a % u'Сери')
if series: if series:
metadata.series = series metadata.series = series
#log.debug(u'Seria: ', metadata.series) # log.debug(u'Seria: ', metadata.series)
xpt_isbn = u'normalize-space(' + xpt_tmpl_base + u')' xpt_isbn = u'normalize-space(' + xpt_tmpl_base + u')'
isbn_str = doc.xpath(xpt_isbn % u'ISBN') isbn_str = doc.xpath(xpt_isbn % u'ISBN')
@ -433,9 +433,9 @@ class Ozon(Source):
lng_splt = langs.split(u',') lng_splt = langs.split(u',')
if lng_splt: if lng_splt:
displ_lang = lng_splt[0].strip() displ_lang = lng_splt[0].strip()
#log.debug(u'displ_lang1: ', displ_lang) # log.debug(u'displ_lang1: ', displ_lang)
metadata.language = _translageLanguageToCode(displ_lang) metadata.language = _translageLanguageToCode(displ_lang)
#log.debug(u'Language: ', metadata.language) # log.debug(u'Language: ', metadata.language)
# can be set before from xml search responce # can be set before from xml search responce
if not metadata.pubdate: if not metadata.pubdate:
@ -537,7 +537,7 @@ def _format_isbn(log, isbn): # {{{
def _translageLanguageToCode(displayLang): # {{{ def _translageLanguageToCode(displayLang): # {{{
displayLang = unicode(displayLang).strip() if displayLang else None displayLang = unicode(displayLang).strip() if displayLang else None
langTbl = { None: 'ru', langTbl = {None: 'ru',
u'Русский': 'ru', u'Русский': 'ru',
u'Немецкий': 'de', u'Немецкий': 'de',
u'Английский': 'en', u'Английский': 'en',