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

Fix Newsweek recipe

Browse Source
This commit is contained in:
Kovid Goyal 2009-09-04 09:41:37 -06:00
parent 0a840e9e2b
commit f457341a36
2 changed files with 20 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/calibre/web/feeds/recipes/recipe_economist.py
View File

@ -62,7 +62,9 @@ class Economist(BasicNewsRecipe):
a = tag.find('a', href=True) a = tag.find('a', href=True)
if a is not None: if a is not None:
url=a['href'].replace('displaystory', 'PrinterFriendly').strip() url=a['href'].replace('displaystory', 'PrinterFriendly').strip()
if url.startswith('/') or url.startswith('PrinterF'): if url.startswith('Printer'):
url = '/'+url
if url.startswith('/'):
url = 'http://www.economist.com' + url url = 'http://www.economist.com' + url
try: try:
subtitle = tag.previousSibling.contents[0].contents[0] subtitle = tag.previousSibling.contents[0].contents[0]

23
src/calibre/web/feeds/recipes/recipe_newsweek.py
View File

@ -89,6 +89,17 @@ class Newsweek(BasicNewsRecipe):
return cmp(tx, ty) return cmp(tx, ty)
return sorted(ans, cmp=fcmp) return sorted(ans, cmp=fcmp)
def ensure_html(self, soup):
root = soup.find(name=True)
if root.name == 'html': return soup
nsoup = BeautifulSoup('<html><head></head><body/></html>')
nroot = nsoup.find(name='body')
for x in soup.contents:
if getattr(x, 'name', False):
x.extract()
nroot.insert(len(nroot), x)
return nsoup
def postprocess_html(self, soup, first_fetch): def postprocess_html(self, soup, first_fetch):
if not first_fetch: if not first_fetch:
h1 = soup.find(id='headline') h1 = soup.find(id='headline')
@ -99,7 +110,7 @@ class Newsweek(BasicNewsRecipe):
div.extract() div.extract()
divs = list(soup.findAll('div', 'pagination')) divs = list(soup.findAll('div', 'pagination'))
if not divs: if not divs:
return soup return self.ensure_html(soup)
for div in divs[1:]: div.extract() for div in divs[1:]: div.extract()
all_a = divs[0].findAll('a', href=True) all_a = divs[0].findAll('a', href=True)
divs[0]['style']="display:none" divs[0]['style']="display:none"
@ -109,7 +120,7 @@ class Newsweek(BasicNewsRecipe):
for a in soup.findAll('a', href=test): for a in soup.findAll('a', href=test):
if a not in all_a: if a not in all_a:
del a['href'] del a['href']
return soup return self.ensure_html(soup)
def get_current_issue(self): def get_current_issue(self):
soup = self.index_to_soup('http://www.newsweek.com') soup = self.index_to_soup('http://www.newsweek.com')
@ -132,7 +143,7 @@ class Newsweek(BasicNewsRecipe):
def postprocess_book(self, oeb, opts, log) : def postprocess_book(self, oeb, opts, log) :
def extractByline(href) : def extractByline(href) :
soup = BeautifulSoup(str(oeb.manifest.hrefs[href])) soup = BeautifulSoup(str(oeb.manifest.hrefs[href]))
byline = soup.find(True,attrs={'class':'authorInfo'}) byline = soup.find(True,attrs={'class':'authorInfo'})
byline = self.tag_to_string(byline) if byline is not None else '' byline = self.tag_to_string(byline) if byline is not None else ''
issueDate = soup.find(True,attrs={'class':'issueDate'}) issueDate = soup.find(True,attrs={'class':'issueDate'})
@ -142,7 +153,7 @@ class Newsweek(BasicNewsRecipe):
return byline + ' | ' + issueDate return byline + ' | ' + issueDate
else : else :
return byline + issueDate return byline + issueDate
def extractDescription(href) : def extractDescription(href) :
soup = BeautifulSoup(str(oeb.manifest.hrefs[href])) soup = BeautifulSoup(str(oeb.manifest.hrefs[href]))
description = soup.find(True,attrs={'name':'description'}) description = soup.find(True,attrs={'name':'description'})
@ -156,8 +167,8 @@ class Newsweek(BasicNewsRecipe):
description = soup.find(True, attrs={'class':'story'}) description = soup.find(True, attrs={'class':'story'})
firstPara = soup.find('p') firstPara = soup.find('p')
description = self.tag_to_string(firstPara) description = self.tag_to_string(firstPara)
return description return description
for section in oeb.toc : for section in oeb.toc :
for article in section : for article in section :
if article.author is None : if article.author is None :