Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

skip the wayback archive for the index page

Browse Source
This commit is contained in:
Kovid Goyal 2022-11-19 10:37:51 +05:30
parent 8db5fff5ac
commit 176171a116
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
recipes/nytimes.recipe
View File

@ -101,8 +101,8 @@ class NewYorkTimes(BasicNewsRecipe):
self._nyt_parser = ans = load_module('calibre.web.site_parsers.nytimes') self._nyt_parser = ans = load_module('calibre.web.site_parsers.nytimes')
return ans return ans
def get_nyt_page(self, url): def get_nyt_page(self, url, skip_wayback=False):
if use_wayback_machine: if use_wayback_machine and not skip_wayback:
from calibre import browser from calibre import browser
return self.nyt_parser.download_url(url, browser()) return self.nyt_parser.download_url(url, browser())
return self.browser.open_novisit(url).read() return self.browser.open_novisit(url).read()
@ -123,7 +123,7 @@ class NewYorkTimes(BasicNewsRecipe):
def read_todays_paper(self): def read_todays_paper(self):
INDEX = 'https://www.nytimes.com/section/todayspaper' INDEX = 'https://www.nytimes.com/section/todayspaper'
# INDEX = 'file:///t/raw.html' # INDEX = 'file:///t/raw.html'
return self.index_to_soup(self.get_nyt_page(INDEX)) return self.index_to_soup(self.get_nyt_page(INDEX, skip_wayback=True))
def read_nyt_metadata(self): def read_nyt_metadata(self):
soup = self.read_todays_paper() soup = self.read_todays_paper()

6
recipes/nytimes_sub.recipe
View File

@ -101,8 +101,8 @@ class NewYorkTimes(BasicNewsRecipe):
self._nyt_parser = ans = load_module('calibre.web.site_parsers.nytimes') self._nyt_parser = ans = load_module('calibre.web.site_parsers.nytimes')
return ans return ans
def get_nyt_page(self, url): def get_nyt_page(self, url, skip_wayback=False):
if use_wayback_machine: if use_wayback_machine and not skip_wayback:
from calibre import browser from calibre import browser
return self.nyt_parser.download_url(url, browser()) return self.nyt_parser.download_url(url, browser())
return self.browser.open_novisit(url).read() return self.browser.open_novisit(url).read()
@ -123,7 +123,7 @@ class NewYorkTimes(BasicNewsRecipe):
def read_todays_paper(self): def read_todays_paper(self):
INDEX = 'https://www.nytimes.com/section/todayspaper' INDEX = 'https://www.nytimes.com/section/todayspaper'
# INDEX = 'file:///t/raw.html' # INDEX = 'file:///t/raw.html'
return self.index_to_soup(self.get_nyt_page(INDEX)) return self.index_to_soup(self.get_nyt_page(INDEX, skip_wayback=True))
def read_nyt_metadata(self): def read_nyt_metadata(self):
soup = self.read_todays_paper() soup = self.read_todays_paper()