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

...

Browse Source
This commit is contained in:
Kovid Goyal 2011-09-21 09:55:55 -06:00
parent 64051b546d
commit 16c222f8bc
1 changed files with 13 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
recipes/ming_pao.recipe
View File

@ -12,11 +12,14 @@ __UseChineseTitle__ = False
__KeepImages__ = True
# (HK only) Turn below to true if you wish to use life.mingpao.com as the main article source
__UseLife__ = True
# (HK only) if __UseLife__ is true, turn this on if you want to include the column section
__InclCols__ = False
'''
Change Log:
2011/09/18: parse "column" section stuff from source text files directly.
2011/09/21: fetching "column" section is made optional. Default is False
2011/09/18: parse "column" section stuff from source text file directly.
2011/09/07: disable "column" section as it is no longer offered free.
2011/06/26: add fetching Vancouver and Toronto versions of the paper, also provide captions for images using life.mingpao fetch source
provide options to remove all images in the file
@ -241,12 +244,13 @@ class MPRecipe(BasicNewsRecipe):
if articles:
feeds.append((title, articles))
# parse column section articles directly from .txt files
for title, url, keystr in [(u'\u5c08\u6b04 Columns', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn', 'ncl')
]:
articles = self.parse_section2_col(url, keystr)
if articles:
feeds.append((title, articles))
if __InclCols__ == True:
# parse column section articles directly from .txt files
for title, url, keystr in [(u'\u5c08\u6b04 Columns', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn', 'ncl')
]:
articles = self.parse_section2_txt(url, keystr)
if articles:
feeds.append((title, articles))
for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'),
(u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]:
@ -368,8 +372,8 @@ class MPRecipe(BasicNewsRecipe):
current_articles.reverse()
return current_articles
# parse from life.mingpao.com
def parse_section2_col(self, url, keystr):
# parse from text file of life.mingpao.com
def parse_section2_txt(self, url, keystr):
self.get_fetchdate()
soup = self.index_to_soup(url)
a = soup.findAll('a', href=True)
@ -654,4 +658,3 @@ class MPRecipe(BasicNewsRecipe):
with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file):
opf.render(opf_file, ncx_file)