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

Speedup economist download by not downloading images from the article carousel

Browse Source
This commit is contained in:
Kovid Goyal 2016-06-02 17:32:57 +05:30
parent 7a9d29261d
commit 3c27f28fdb
2 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
recipes/economist.recipe
View File

@ -49,7 +49,7 @@ class Economist(BasicNewsRecipe):
'main-content-container', 'ec-topic-widget']}), 'main-content-container', 'ec-topic-widget']}),
{'class': lambda x: x and 'share-links-header' in x}, {'class': lambda x: x and 'share-links-header' in x},
] ]
keep_only_tags = [dict(name='article')] keep_only_tags = [dict(name='article', id=lambda x: not x)]
no_stylesheets = True no_stylesheets = True
preprocess_regexps = [(re.compile('</html>.*', re.DOTALL), preprocess_regexps = [(re.compile('</html>.*', re.DOTALL),
lambda x:'</html>')] lambda x:'</html>')]
@ -78,6 +78,7 @@ class Economist(BasicNewsRecipe):
return self.economist_parse_index() return self.economist_parse_index()
def economist_parse_index(self): def economist_parse_index(self):
# return [('Articles', [{'title':'test', 'url':'http://www.economist.com/news/americas/21699494-guide-cutting-corners-way-jos'}])]
soup = self.index_to_soup(self.INDEX) soup = self.index_to_soup(self.INDEX)
div = soup.find('div', attrs={'class':'issue-image'}) div = soup.find('div', attrs={'class':'issue-image'})
if div is not None: if div is not None:

4
recipes/economist_free.recipe
View File

@ -49,7 +49,7 @@ class Economist(BasicNewsRecipe):
'main-content-container', 'ec-topic-widget']}), 'main-content-container', 'ec-topic-widget']}),
{'class': lambda x: x and 'share-links-header' in x}, {'class': lambda x: x and 'share-links-header' in x},
] ]
keep_only_tags = [dict(name='article')] keep_only_tags = [dict(name='article', id=lambda x: not x)]
no_stylesheets = True no_stylesheets = True
preprocess_regexps = [(re.compile('</html>.*', re.DOTALL), preprocess_regexps = [(re.compile('</html>.*', re.DOTALL),
lambda x:'</html>')] lambda x:'</html>')]
@ -59,6 +59,7 @@ class Economist(BasicNewsRecipe):
delay = 1 delay = 1
needs_subscription = False needs_subscription = False
def get_browser(self): def get_browser(self):
br = BasicNewsRecipe.get_browser(self) br = BasicNewsRecipe.get_browser(self)
# Add a cookie indicating we have accepted Economist's cookie # Add a cookie indicating we have accepted Economist's cookie
@ -77,6 +78,7 @@ class Economist(BasicNewsRecipe):
return self.economist_parse_index() return self.economist_parse_index()
def economist_parse_index(self): def economist_parse_index(self):
# return [('Articles', [{'title':'test', 'url':'http://www.economist.com/news/americas/21699494-guide-cutting-corners-way-jos'}])]
soup = self.index_to_soup(self.INDEX) soup = self.index_to_soup(self.INDEX)
div = soup.find('div', attrs={'class':'issue-image'}) div = soup.find('div', attrs={'class':'issue-image'})
if div is not None: if div is not None: