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 2011-10-20 06:51:50 +05:30
parent c17fb8bd5e
commit eda4c65740
1 changed files with 27 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
recipes/ming_pao.recipe
View File

@ -18,10 +18,13 @@ __InclPremium__ = False
__ParsePFF__ = True __ParsePFF__ = True
# (HK only) Turn below to True if you wish hi-res images (Default: False) # (HK only) Turn below to True if you wish hi-res images (Default: False)
__HiResImg__ = False __HiResImg__ = False
# Override the date returned by the program if specifying a YYYYMMDD below
__Date__ = ''
''' '''
Change Log: Change Log:
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
2011/10/04: option to get hi-res photos for the articles 2011/10/04: option to get hi-res photos for the articles
2011/09/21: fetching "column" section is made optional. 2011/09/21: fetching "column" section is made optional.
@ -170,13 +173,22 @@ class MPRecipe(BasicNewsRecipe):
return dt_local return dt_local
def get_fetchdate(self): def get_fetchdate(self):
return self.get_dtlocal().strftime("%Y%m%d") if __Date__ <> '':
return __Date__
else:
return self.get_dtlocal().strftime("%Y%m%d")
def get_fetchformatteddate(self): def get_fetchformatteddate(self):
return self.get_dtlocal().strftime("%Y-%m-%d") if __Date__ <> '':
return __Date__[0:4]+'-'+__Date__[4:6]+'-'+__Date__[6:8]
else:
return self.get_dtlocal().strftime("%Y-%m-%d")
def get_fetchday(self): def get_fetchday(self):
return self.get_dtlocal().strftime("%d") if __Date__ <> '':
return __Date__[6:8]
else:
return self.get_dtlocal().strftime("%d")
def get_cover_url(self): def get_cover_url(self):
if __Region__ == 'Hong Kong': if __Region__ == 'Hong Kong':
@ -563,42 +575,41 @@ class MPRecipe(BasicNewsRecipe):
# .txt based file # .txt based file
splitter = re.compile(r'\n') # Match non-digits splitter = re.compile(r'\n') # Match non-digits
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_mov_link = False
next_is_img_txt = False next_is_img_txt = False
title_started = False title_started = 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()
if item.startswith(u'\u3010'): if item.startswith(u'\u3010'):
met_article_start_char = True met_article_start_char = True
new_raw_html = new_raw_html + '</div><div class="content"><p>' + item + '<p>\n' new_raw_html = new_raw_html + '</div><div class="content"><p>' + item + '<p>\n'
else: else:
if next_is_img_txt == False and next_is_mov_link == False: if next_is_img_txt == False:
item = item.strip()
if item.startswith("=@"): if item.startswith("=@"):
next_is_mov_link = True print 'skip movie link'
elif item.startswith("=?"): elif item.startswith("=?"):
next_is_img_txt = True next_is_img_txt = True
new_raw_html += '<img src="' + str(item)[2:].strip() + '.gif" /><p>\n' new_raw_html += '<img src="' + str(item)[2:].strip() + '.gif" /><p>\n'
elif item.startswith('=='):
next_is_img_txt = True
new_raw_html += '<img src="' + str(item)[2:].strip() + '.jpg" /><p>\n'
elif item.startswith('='): elif item.startswith('='):
next_is_img_txt = True next_is_img_txt = True
new_raw_html += '<img src="' + str(item)[1:].strip() + '.jpg" /><p>\n' new_raw_html += '<img src="' + str(item)[1:].strip() + '.jpg" /><p>\n'
else: else:
if item <> '': if next_is_img_txt == False and met_article_start_char == False:
if next_is_img_txt == False and met_article_start_char == False: if item <> '':
if title_started == False: if title_started == False:
#print 'Title started at ', item #print 'Title started at ', item
new_raw_html = new_raw_html + '</div><div class="heading">' + item + '\n' new_raw_html = new_raw_html + '</div><div class="heading">' + item + '\n'
title_started = True title_started = True
else: else:
new_raw_html = new_raw_html + item + '\n' new_raw_html = new_raw_html + item + '\n'
else: else:
new_raw_html = new_raw_html + item + '<p>\n' new_raw_html = new_raw_html + item + '<p>\n'
else: else:
if next_is_mov_link == True: next_is_img_txt = False
next_is_mov_link = False new_raw_html = new_raw_html + item + '\n'
else:
next_is_img_txt = False
new_raw_html = new_raw_html + item + '\n'
return new_raw_html + '</div></body></html>' return new_raw_html + '</div></body></html>'
def preprocess_html(self, soup): def preprocess_html(self, soup):