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

Improve the Economist recipes

Browse Source
This commit is contained in:
Kovid Goyal 2010-01-08 14:21:11 -07:00
parent 1325367249
commit 86d97ba6e6
2 changed files with 67 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
resources/recipes/economist.recipe
View File

@ -7,6 +7,7 @@ economist.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.ebooks.BeautifulSoup import Tag, NavigableString
import mechanize, string, urllib, time
@ -103,3 +104,22 @@ class Economist(BasicNewsRecipe):
if not ans:
raise Exception('Could not find any articles. Has your subscription expired?')
return ans
def eco_find_image_tables(self, soup):
for x in soup.findAll('table', align='right'):
if len(x.findAll('font')) in (1,2) and len(x.findAll('img')) == 1:
yield x
def postprocess_html(self, soup, first):
for table in list(self.eco_find_image_tables(soup)):
caption = table.find('font')
img = table.find('img')
div = Tag(soup, 'div')
div['style'] = 'text-align:center;font-size:70%'
ns = NavigableString(self.tag_to_string(caption))
div.insert(0, ns)
div.insert(1, Tag(soup, 'br'))
img.extract()
div.insert(2, img)
table.replaceWith(div)
return soup

51
resources/recipes/economist_free.recipe
View File

@ -1,6 +1,7 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.utils.threadpool import ThreadPool, makeRequests
import time
from calibre.ebooks.BeautifulSoup import Tag, NavigableString
import time, string
from datetime import datetime
from lxml import html
@ -48,7 +49,30 @@ class Economist(BasicNewsRecipe):
for r in requests: pool.putRequest(r)
pool.wait()
return [(t, a) for t, a in self.feed_dict.items()]
return self.eco_sort_sections([(t, a) for t, a in
self.feed_dict.items()])
def eco_sort_sections(self, feeds):
order = {
'The World This Week': 1,
'Leaders': 2,
'Letters': 3,
'Briefing': 4,
'Business': 5,
'Finance And Economics': 6,
'Science & Technology': 7,
'Books & Arts': 8,
'International': 9,
'United States': 10,
'Asia': 11,
'Europe': 12,
'The Americas': 13,
'Middle East & Africa': 14,
'Britain': 15,
'Obituary': 16,
}
return sorted(feeds, cmp=lambda x,y:cmp(order.get(x[0], 100),
order.get(y[0], 100)))
def process_eco_feed_article(self, args):
from calibre import browser
@ -61,8 +85,8 @@ class Economist(BasicNewsRecipe):
matches = root.xpath('//*[@class = "article-section"]')
feedtitle = 'Miscellaneous'
if matches:
feedtitle = html.tostring(matches[0], method='text',
encoding=unicode)
feedtitle = string.capwords(html.tostring(matches[0], method='text',
encoding=unicode))
return (i, feedtitle, url, title, description, author, published)
def eco_article_found(self, req, result):
@ -81,3 +105,22 @@ class Economist(BasicNewsRecipe):
def eco_article_failed(self, req, tb):
self.log.error('Failed to download %s with error:'%req.args[0][2])
self.log.debug(tb)
def eco_find_image_tables(self, soup):
for x in soup.findAll('table', align='right'):
if len(x.findAll('font')) in (1,2) and len(x.findAll('img')) == 1:
yield x
def postprocess_html(self, soup, first):
for table in list(self.eco_find_image_tables(soup)):
caption = table.find('font')
img = table.find('img')
div = Tag(soup, 'div')
div['style'] = 'text-align:center;font-size:70%'
ns = NavigableString(self.tag_to_string(caption))
div.insert(0, ns)
div.insert(1, Tag(soup, 'br'))
img.extract()
div.insert(2, img)
table.replaceWith(div)
return soup