fix pyflakes errors

This commit is contained in:
Kovid Goyal 2014-06-11 21:19:21 +05:30
parent 42b2eeb3bc
commit 8f69acf446
4 changed files with 28 additions and 52 deletions

View File

@ -1,4 +1,3 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class JerusalemPost(BasicNewsRecipe): class JerusalemPost(BasicNewsRecipe):
@ -14,31 +13,10 @@ class JerusalemPost(BasicNewsRecipe):
max_articles_per_feed = 10 max_articles_per_feed = 10
no_stylesheets = True no_stylesheets = True
feeds = [ ('Front Page', 'http://www.jpost.com/Rss/RssFeedsFrontPage.aspx'), feeds = [('Front Page', 'http://www.jpost.com/Rss/RssFeedsFrontPage.aspx'),
('Israel News', 'http://www.jpost.com/Rss/RssFeedsIsraelNews.aspx'), ('Israel News', 'http://www.jpost.com/Rss/RssFeedsIsraelNews.aspx'),
('Middle East News', 'http://www.jpost.com/Rss/RssFeedsMiddleEastNews.aspx'), ('Middle East News', 'http://www.jpost.com/Rss/RssFeedsMiddleEastNews.aspx'),
('International News', 'http://www.jpost.com/Rss/RssFeedsInternationalNews.aspx'), ('International News', 'http://www.jpost.com/Rss/RssFeedsInternationalNews.aspx'),
('Editorials', 'http://www.jpost.com/Rss/RssFeedsEditorialsNews.aspx'), ('Editorials', 'http://www.jpost.com/Rss/RssFeedsEditorialsNews.aspx'),
] ]
#remove_tags = [
#dict(id=lambda x: x and 'ads.' in x),
#dict(attrs={'class':['printinfo', 'tt1']}),
#dict(onclick='DoPrint()'),
#dict(name='input'),
#]
#conversion_options = {'linearize_tables':True}
#def preprocess_html(self, soup):
#for tag in soup.findAll('form'):
#tag.name = 'div'
#return soup
#def print_version(self, url):
#m = re.search(r'(ID|id)=(\d+)', url)
#if m is not None:
#id_ = m.group(2)
#return 'http://www.jpost.com/LandedPages/PrintArticle.aspx?id=%s'%id_
#return url

View File

@ -9,9 +9,7 @@ __description__ = 'PCMag (www.pcmag.com) delivers authoritative, labs-based comp
''' '''
http://www.pcmag.com/ http://www.pcmag.com/
''' '''
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class pcMag(BasicNewsRecipe): class pcMag(BasicNewsRecipe):
__author__ = 'Lorenzo Vigentini' __author__ = 'Lorenzo Vigentini'

View File

@ -8,7 +8,7 @@ __copyright__ = 'tomashnyk@gmail.com'
import re import re
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup,Tag from calibre.ebooks.BeautifulSoup import BeautifulSoup
#This imports the version bundled with Calibre #This imports the version bundled with Calibre
import lxml import lxml
from lxml.builder import E from lxml.builder import E

View File

@ -8,9 +8,9 @@ __copyright__ = 'tomashnyk@gmail.com'
import re,os,datetime import re,os,datetime
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup,Tag from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.constants import config_dir, CONFIG_DIR_MODE from calibre.constants import config_dir
#This imports the version bundled with Calibre # This imports the version bundled with Calibre
import lxml import lxml
from lxml.builder import E from lxml.builder import E
@ -30,10 +30,10 @@ class respektWebRecipe(BasicNewsRecipe):
p.indent_first_line {text-indent:30px;}' p.indent_first_line {text-indent:30px;}'
remove_tags_before = dict(name='div',attrs={'class':['l']}) remove_tags_before = dict(name='div',attrs={'class':['l']})
remove_tags_after = dict(id='text') remove_tags_after = dict(id='text')
remove_tags = [dict(name='ul', attrs={'class':['tabs-d'],'id':['comm']}), \ remove_tags = [dict(name='ul', attrs={'class':['tabs-d'],'id':['comm']}),
dict(name='div',attrs={'class':['slot','reklama','date']}), \ dict(name='div',attrs={'class':['slot','reklama','date']}),
dict(name='span', attrs={'class':['detail-vykrik']}), \ dict(name='span', attrs={'class':['detail-vykrik']}),
dict(name='p', attrs={'class':['detail-vykrik']}), \ dict(name='p', attrs={'class':['detail-vykrik']}),
dict(name='div', attrs={'id':['col123d-video','col123d-infographic','col123d-gallery','col12d-discussion']}), # soup>lxml>soup in prprocess requires this dict(name='div', attrs={'id':['col123d-video','col123d-infographic','col123d-gallery','col12d-discussion']}), # soup>lxml>soup in prprocess requires this
dict(name='strong', attrs={'class':['detail-vykrik']}), dict(name='strong', attrs={'class':['detail-vykrik']}),
dict(name='script')] dict(name='script')]
@ -49,7 +49,7 @@ class respektWebRecipe(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
# Read already downloaded articles # Read already downloaded articles
recipe_dir = os.path.join(config_dir,'recipes') recipe_dir = os.path.join(config_dir,'recipes')
old_articles = os.path.join(recipe_dir,self.title.encode('utf-8').replace('/',':')) old_articles = os.path.join(recipe_dir,self.title)
past_items = [] past_items = []
if os.path.exists(old_articles): if os.path.exists(old_articles):
with file(old_articles) as f: with file(old_articles) as f:
@ -112,7 +112,7 @@ class respektWebRecipe(BasicNewsRecipe):
if section[1] == 'Respekt DJ': if section[1] == 'Respekt DJ':
if list_of_articles: if list_of_articles:
if datetime.datetime.today().weekday() in range(0,5) and 6 < datetime.datetime.utcnow().hour < 17: if datetime.datetime.today().weekday() in range(0,5) and 6 < datetime.datetime.utcnow().hour < 17:
#list_of_articles = list_of_articles[:-1] # list_of_articles = list_of_articles[:-1]
current_items = current_items[:-1] current_items = current_items[:-1]
if list_of_articles: if list_of_articles:
ans.append((section[1],list_of_articles)) ans.append((section[1],list_of_articles))
@ -156,7 +156,7 @@ class respektWebRecipe(BasicNewsRecipe):
for i in root.xpath("//h2[@class='d-dj-t']"): for i in root.xpath("//h2[@class='d-dj-t']"):
i.attrib['class'] = '' i.attrib['class'] = ''
E.style = "font-size:60%;font-weight:normal;" E.style = "font-size:60%;font-weight:normal;"
time = E('span',i.getprevious().text_content(),style = E.style) time = E('span',i.getprevious().text_content(),style=E.style)
# Time should be ahead of the title # Time should be ahead of the title
time.tail = ' ' + i.text time.tail = ' ' + i.text
i.text = '' i.text = ''