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

Update Foreign Affairs

Browse Source
This commit is contained in:
Kovid Goyal 2013-03-26 10:08:33 +05:30
parent 7be79b4ff8
commit 1afd955ae0
1 changed files with 5 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
recipes/foreignaffairs.recipe
View File

@ -1,6 +1,5 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
import re import re
from calibre.ptempfile import PersistentTemporaryFile
class ForeignAffairsRecipe(BasicNewsRecipe): class ForeignAffairsRecipe(BasicNewsRecipe):
''' there are three modifications: ''' there are three modifications:
@ -45,7 +44,6 @@ class ForeignAffairsRecipe(BasicNewsRecipe):
'publisher': publisher} 'publisher': publisher}
temp_files = [] temp_files = []
articles_are_obfuscated = True
def get_cover_url(self): def get_cover_url(self):
soup = self.index_to_soup(self.FRONTPAGE) soup = self.index_to_soup(self.FRONTPAGE)
@ -53,20 +51,6 @@ class ForeignAffairsRecipe(BasicNewsRecipe):
img_url = div.find('img')['src'] img_url = div.find('img')['src']
return self.INDEX + img_url return self.INDEX + img_url
def get_obfuscated_article(self, url):
br = self.get_browser()
br.open(url)
response = br.follow_link(url_regex = r'/print/[0-9]+', nr = 0)
html = response.read()
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write(html)
self.temp_files[-1].close()
return self.temp_files[-1].name
def parse_index(self): def parse_index(self):
answer = [] answer = []
@ -89,10 +73,10 @@ class ForeignAffairsRecipe(BasicNewsRecipe):
if div.find('a') is not None: if div.find('a') is not None:
originalauthor=self.tag_to_string(div.findNext('div', attrs = {'class':'views-field-field-article-book-nid'}).div.a) originalauthor=self.tag_to_string(div.findNext('div', attrs = {'class':'views-field-field-article-book-nid'}).div.a)
title=subsectiontitle+': '+self.tag_to_string(div.span.a)+' by '+originalauthor title=subsectiontitle+': '+self.tag_to_string(div.span.a)+' by '+originalauthor
url=self.INDEX+div.span.a['href'] url=self.INDEX+self.index_to_soup(self.INDEX+div.span.a['href']).find('a', attrs={'class':'fa_addthis_print'})['href']
atr=div.findNext('div', attrs = {'class': 'views-field-field-article-display-authors-value'}) atr=div.findNext('div', attrs = {'class': 'views-field-field-article-display-authors-value'})
if atr is not None: if atr is not None:
author=self.tag_to_string(atr.span.a) author=self.tag_to_string(atr.span)
else: else:
author='' author=''
desc=div.findNext('span', attrs = {'class': 'views-field-field-article-summary-value'}) desc=div.findNext('span', attrs = {'class': 'views-field-field-article-summary-value'})
@ -106,10 +90,10 @@ class ForeignAffairsRecipe(BasicNewsRecipe):
for div in sec.findAll('div', attrs = {'class': 'views-field-title'}): for div in sec.findAll('div', attrs = {'class': 'views-field-title'}):
if div.find('a') is not None: if div.find('a') is not None:
title=self.tag_to_string(div.span.a) title=self.tag_to_string(div.span.a)
url=self.INDEX+div.span.a['href'] url=self.INDEX+self.index_to_soup(self.INDEX+div.span.a['href']).find('a', attrs={'class':'fa_addthis_print'})['href']
atr=div.findNext('div', attrs = {'class': 'views-field-field-article-display-authors-value'}) atr=div.findNext('div', attrs = {'class': 'views-field-field-article-display-authors-value'})
if atr is not None: if atr is not None:
author=self.tag_to_string(atr.span.a) author=self.tag_to_string(atr.span)
else: else:
author='' author=''
desc=div.findNext('span', attrs = {'class': 'views-field-field-article-summary-value'}) desc=div.findNext('span', attrs = {'class': 'views-field-field-article-summary-value'})
@ -119,7 +103,7 @@ class ForeignAffairsRecipe(BasicNewsRecipe):
description='' description=''
articles.append({'title':title, 'date':None, 'url':url, 'description':description, 'author':author}) articles.append({'title':title, 'date':None, 'url':url, 'description':description, 'author':author})
if articles: if articles:
answer.append((section, articles)) answer.append((section, articles))
return answer return answer
def preprocess_html(self, soup): def preprocess_html(self, soup):