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 Ars Technica

Browse Source 
Merge branch 'patch-1' of https://github.com/Hainish/calibre
This commit is contained in:
Kovid Goyal 2014-05-02 08:38:47 +05:30
commit fbbdd931bb
1 changed files with 33 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
recipes/ars_technica.recipe
View File

@ -28,73 +28,71 @@ class ArsTechnica(BasicNewsRecipe):
img{display: block} img{display: block}
.caption-text{font-size:small; font-style:italic} .caption-text{font-size:small; font-style:italic}
.caption-byline{font-size:small; font-style:italic; font-weight:bold} .caption-byline{font-size:small; font-style:italic; font-weight:bold}
''' '''
conversion_options = { conversion_options = {
'comments' : description 'comments' : description
,'tags' : category ,'tags' : category
,'language' : language ,'language' : language
,'publisher' : publisher ,'publisher' : publisher
} }
keep_only_tags = [ keep_only_tags = [
dict(attrs={'class':'standalone'}) dict(attrs={'class':'standalone'})
,dict(attrs={'id':'article-guts'}) ,dict(attrs={'id':'article-guts'})
] ]
remove_tags = [ remove_tags = [
dict(name=['object','link','embed','iframe','meta']) dict(name=['object','link','embed','iframe','meta'])
,dict(attrs={'class':'corner-info'}) ,dict(attrs={'class':'corner-info'})
] ]
remove_attributes = ['lang'] remove_attributes = ['lang']
feeds = [ feeds = [
(u'Infinite Loop (Apple content)' , u'http://feeds.arstechnica.com/arstechnica/apple/' ) (u'Infinite Loop (Apple content)' , u'http://feeds.arstechnica.com/arstechnica/apple/')
,(u'Opposable Thumbs (Gaming content)' , u'http://feeds.arstechnica.com/arstechnica/gaming/' ) ,(u'Opposable Thumbs (Gaming content)' , u'http://feeds.arstechnica.com/arstechnica/gaming/')
,(u'Gear and Gadgets' , u'http://feeds.arstechnica.com/arstechnica/gadgets/' ) ,(u'Gear and Gadgets' , u'http://feeds.arstechnica.com/arstechnica/gadgets/')
,(u'Uptime (IT content)' , u'http://feeds.arstechnica.com/arstechnica/business/' ) ,(u'Uptime (IT content)' , u'http://feeds.arstechnica.com/arstechnica/business/')
,(u'Open Ended (Open Source content)' , u'http://feeds.arstechnica.com/arstechnica/open-source/') ,(u'Open Ended (Open Source content)' , u'http://feeds.arstechnica.com/arstechnica/open-source/')
,(u'One Microsoft Way' , u'http://feeds.arstechnica.com/arstechnica/microsoft/' ) ,(u'One Microsoft Way' , u'http://feeds.arstechnica.com/arstechnica/microsoft/')
,(u'Scientific method (Science content)' , u'http://feeds.arstechnica.com/arstechnica/science/' ) ,(u'Scientific method (Science content)' , u'http://feeds.arstechnica.com/arstechnica/science/')
,(u'Law & Disorder (Tech policy content)' , u'http://feeds.arstechnica.com/arstechnica/tech-policy/') ,(u'Law & Disorder (Tech policy content)' , u'http://feeds.arstechnica.com/arstechnica/tech-policy/')
,(u'Risk Assessment (Security content)' , u'http://feeds.arstechnica.com/arstechnica/security/')
] ]
def append_page(self, soup, appendtag, position): def append_page(self, soup, appendtag, position):
pager = soup.find(attrs={'class':'numbers'}) pager = soup.find(attrs={'class':'numbers'})
if pager: if pager:
nexttag = pager.find(attrs={'class':'next'}) nexttag = pager.find(attrs={'class':'next'})
if nexttag: if nexttag:
nurl = nexttag.parent['href'] nurl = nexttag.parent['href']
rawc = self.index_to_soup(nurl,True) rawc = self.index_to_soup(nurl,True)
soup2 = BeautifulSoup(rawc, fromEncoding=self.encoding) soup2 = BeautifulSoup(rawc, fromEncoding=self.encoding)
texttag = soup2.find(attrs={'id':'article-guts'}) texttag = soup2.find(attrs={'id':'article-guts'})
newpos = len(texttag.contents) newpos = len(texttag.contents)
self.append_page(soup2,texttag,newpos) self.append_page(soup2,texttag,newpos)
texttag.extract() texttag.extract()
pager.extract() pager.extract()
appendtag.insert(position,texttag) appendtag.insert(position,texttag)
def preprocess_html(self, soup): def preprocess_html(self, soup):
self.append_page(soup, soup.body, 3) self.append_page(soup, soup.body, 3)
for item in soup.findAll('a'): for item in soup.findAll('a'):
limg = item.find('img') limg = item.find('img')
if item.string is not None: if item.string is not None:
str = item.string str = item.string
item.replaceWith(str) item.replaceWith(str)
else: else:
if limg: if limg:
item.name = 'div' item.name = 'div'
item.attrs = [] item.attrs = []
else: else:
str = self.tag_to_string(item) str = self.tag_to_string(item)
item.replaceWith(str) item.replaceWith(str)
for item in soup.findAll('img'): for item in soup.findAll('img'):
if not item.has_key('alt'): if 'alt' not in item:
item['alt'] = 'image' item['alt'] = 'image'
return soup return soup
def preprocess_raw_html(self, raw, url): def preprocess_raw_html(self, raw, url):
return '<html><head>'+raw[raw.find('</head>'):] return '<html><head>'+raw[raw.find('</head>'):]