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

More robust cover fetching for the economist

Browse Source
This commit is contained in:
Kovid Goyal 2011-11-12 23:03:20 +05:30
parent 19b54b8008
commit d26a9127a2
2 changed files with 22 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
recipes/economist.recipe
View File

@ -55,12 +55,17 @@ class Economist(BasicNewsRecipe):
''' '''
def get_cover_url(self): def get_cover_url(self):
br = self.browser soup = self.index_to_soup('http://www.economist.com/printedition/covers')
br.open(self.INDEX) div = soup.find('div', attrs={'class':lambda x: x and
issue = br.geturl().split('/')[4] 'print-cover-links' in x})
self.log('Fetching cover for issue: %s'%issue) a = div.find('a', href=True)
cover_url = "http://media.economist.com/sites/default/files/imagecache/print-cover-full/print-covers/%s_CNA400_0.jpg" %(issue.translate(None,'-')) url = a.get('href')
return cover_url if url.startswith('/'):
url = 'http://www.economist.com' + url
soup = self.index_to_soup(url)
div = soup.find('div', attrs={'class':'cover-content'})
img = div.find('img', src=True)
return img.get('src')
def parse_index(self): def parse_index(self):
return self.economist_parse_index() return self.economist_parse_index()

18
recipes/economist_free.recipe
View File

@ -39,13 +39,17 @@ class Economist(BasicNewsRecipe):
delay = 1 delay = 1
def get_cover_url(self): def get_cover_url(self):
br = self.browser soup = self.index_to_soup('http://www.economist.com/printedition/covers')
br.open(self.INDEX) div = soup.find('div', attrs={'class':lambda x: x and
issue = br.geturl().split('/')[4] 'print-cover-links' in x})
self.log('Fetching cover for issue: %s'%issue) a = div.find('a', href=True)
cover_url = "http://media.economist.com/sites/default/files/imagecache/print-cover-full/print-covers/%s_CNA400_0.jpg" %(issue.translate(None,'-')) url = a.get('href')
return cover_url if url.startswith('/'):
url = 'http://www.economist.com' + url
soup = self.index_to_soup(url)
div = soup.find('div', attrs={'class':'cover-content'})
img = div.find('img', src=True)
return img.get('src')
def parse_index(self): def parse_index(self):
try: try: