Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 10:44:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Foreign Affairs

Browse Source
This commit is contained in:
Kovid Goyal 2016-04-17 09:50:32 +05:30
parent 36f1bd005f
commit 72f6c7f2be
1 changed files with 18 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
recipes/foreignaffairs.recipe
View File

@ -1,5 +1,8 @@
#!/usr/bin/env python2
from calibre.web.feeds.news import BasicNewsRecipe
import re
import html5lib
from lxml import html
def select_form(form):
@ -35,44 +38,20 @@ class ForeignAffairsRecipe(BasicNewsRecipe):
needs_subscription = True
INDEX = 'http://www.foreignaffairs.com'
FRONTPAGE = 'http://www.foreignaffairs.com/magazine'
FRONTPAGE = INDEX + '/magazine'
remove_tags = [dict(name='svg')]
remove_tags_before = dict(name='div', attrs={'class': 'print-content'})
remove_tags_after = dict(name='div', attrs={'class': 'print-footer'})
extra_css = '''
body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
div.print-footer {font-size: x-small; color: #696969;}
'''
keep_only_tags = [
dict(attrs={'class':lambda x: x and set(x.split()).intersection(set('article-header l-article-column'.split()))}),
]
conversion_options = {'comments': description, 'tags': category, 'language': 'en',
'publisher': publisher}
temp_files = []
def get_cover_url(self):
soup = self.index_to_soup(self.FRONTPAGE)
div = soup.find('div', attrs={'class':'magazine-hero__image image_auto_width'})
img_url = div.find('img')['src']
return img_url # The url includes the https:// as necessary
def get_print_url(self, url):
article_soup = self.index_to_soup(url.strip())
if article_soup is not None:
shortlink = article_soup.find('a', attrs={'class':re.compile(r'\bicon-print\b')})
if shortlink:
return shortlink['href']
else:
return url
else:
return url
def parse_index(self):
answer = []
soup = self.index_to_soup(self.FRONTPAGE)
div = soup.find('div', attrs={'class':'magazine-hero__image image_auto_width'})
self.cover_url = div.find('img')['src']
# get dates
date = re.split('\s\|\s',self.tag_to_string(soup.head.title.string))[0]
self.title = "Foreign Affairs ({})".format(date)
@ -85,8 +64,7 @@ class ForeignAffairsRecipe(BasicNewsRecipe):
for article_block in sec.findAll('article'):
if article_block.find('a') is not None:
title=self.tag_to_string(article_block.div.a.h2)
article_url = article_block.div.a['href']
url = self.get_print_url(article_url)
url = article_block.div.a['href']
atr=article_block.findNext('p', attrs={'class': 'author'})
if atr is not None:
author=self.tag_to_string(atr)
@ -102,6 +80,14 @@ class ForeignAffairsRecipe(BasicNewsRecipe):
answer.append((section, articles))
return answer
def preprocess_raw_html(self, raw_html, url):
root = html5lib.parse(raw_html, treebuilder='lxml', namespaceHTMLElements=False).getroot()
for svg in tuple(root.iter('{*}svg')):
svg.getparent().remove(svg)
for meta in tuple(root.iter('{*}meta')):
meta.getparent().remove(meta)
return html.tostring(root)
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'src': True}):
if not img['src'].startswith('http'):
@ -110,8 +96,6 @@ class ForeignAffairsRecipe(BasicNewsRecipe):
return soup
def get_browser(self):
import html5lib
from lxml import html
br = BasicNewsRecipe.get_browser(self)
if self.username is not None and self.password is not None:
# mechanize fails to parse the html correctly, so use html5lib to
@ -125,6 +109,3 @@ class ForeignAffairsRecipe(BasicNewsRecipe):
br.form['pass'] = self.password
br.submit()
return br
def cleanup(self):
self.browser.open('https://www.foreignaffairs.com/user/logout')