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

Updated Mig Pao

Browse Source
This commit is contained in:
Kovid Goyal 2011-12-01 18:38:28 +05:30
parent 87b37ac4e2
commit 6a1f2e8dd1
1 changed files with 15 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
recipes/ming_pao.recipe
View File

@ -24,6 +24,7 @@ __Date__ = ''
''' '''
Change Log: Change Log:
2011/12/01: take care of situation that in txt source parsing, the article content does start with special character u'\u3010'
2011/10/21: fix a bug that hi-res img is unavailable in pages parsed from source txt 2011/10/21: fix a bug that hi-res img is unavailable in pages parsed from source txt
2011/10/19: fix a bug in txt source parsing 2011/10/19: fix a bug in txt source parsing
2011/10/17: disable fetching of premium content, also improved txt source parsing 2011/10/17: disable fetching of premium content, also improved txt source parsing
@ -533,12 +534,22 @@ class MPRecipe(BasicNewsRecipe):
new_raw_html = '<html><head><title>Untitled</title></head><body><div class="images">' new_raw_html = '<html><head><title>Untitled</title></head><body><div class="images">'
next_is_img_txt = False next_is_img_txt = False
title_started = False title_started = False
title_break_reached = False
met_article_start_char = False met_article_start_char = False
for item in splitter.split(raw_html): for item in splitter.split(raw_html):
item = item.strip() item = item.strip()
if item.startswith(u'\u3010'): # if title already reached but break between title and content not yet found, record title_break_reached
met_article_start_char = True if title_started == True and title_break_reached == False and item == '':
new_raw_html = new_raw_html + '</div><div class="content"><p>' + item + '<p>\n' title_break_reached = True
# if title reached and title_break_reached and met_article_start_char == False and item is not empty
# start content
elif title_started == True and title_break_reached == True and met_article_start_char == False:
if item <> '':
met_article_start_char = True
new_raw_html = new_raw_html + '</div><div class="content"><p>' + item + '<p>\n'
#if item.startswith(u'\u3010'):
# met_article_start_char = True
# new_raw_html = new_raw_html + '</div><div class="content"><p>' + item + '<p>\n'
else: else:
if next_is_img_txt == False: if next_is_img_txt == False:
if item.startswith("=@"): if item.startswith("=@"):
@ -787,3 +798,4 @@ class MPRecipe(BasicNewsRecipe):
with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file): with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file):
opf.render(opf_file, ncx_file) opf.render(opf_file, ncx_file)