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

Update wsj.recipe

Browse Source
This commit is contained in:
unkn0w7n 2024-05-15 11:16:07 +05:30
parent d7cedee366
commit b96480d5ab
1 changed files with 49 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
recipes/wsj.recipe
View File

@ -8,6 +8,11 @@ from calibre.web.feeds.news import BasicNewsRecipe, classes
from html5_parser import parse from html5_parser import parse
# Past 6 editions are available for download.
# For available past editions see log and set date to, for example, '20240513'.
past_edition = None
class WSJ(BasicNewsRecipe): class WSJ(BasicNewsRecipe):
title = 'The Wall Street Journal' title = 'The Wall Street Journal'
__author__ = 'unkn0wn' __author__ = 'unkn0wn'
@ -21,6 +26,7 @@ class WSJ(BasicNewsRecipe):
no_javascript = True no_javascript = True
no_stylesheets = True no_stylesheets = True
remove_attributes = ['style', 'height', 'width'] remove_attributes = ['style', 'height', 'width']
resolve_internal_links = True
extra_css = ''' extra_css = '''
#subhed, em { font-style:italic; color:#202020; } #subhed, em { font-style:italic; color:#202020; }
@ -81,11 +87,12 @@ class WSJ(BasicNewsRecipe):
div.extract() div.extract()
return soup return soup
if not past_edition:
def _download_cover(self): def _download_cover(self):
import os import os
from calibre import browser from calibre import browser
from contextlib import closing from contextlib import closing
from calibre.utils.img import add_borders_to_image, image_to_data, save_cover_data_to from calibre.utils.img import save_cover_data_to
br = browser() br = browser()
raw = br.open('https://www.frontpages.com/the-wall-street-journal/') raw = br.open('https://www.frontpages.com/the-wall-street-journal/')
soup = BeautifulSoup(raw.read()) soup = BeautifulSoup(raw.read())
@ -110,13 +117,27 @@ class WSJ(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
index = 'https://bartender.mobile.dowjones.io' index = 'https://bartender.mobile.dowjones.io'
catalog = json.loads(self.index_to_soup(index + '/catalogs/v1/wsj/us/catalog.json', raw=True)) catalog = json.loads(self.index_to_soup(index + '/catalogs/v1/wsj/us/catalog.json', raw=True))
edit = []
for itm in catalog['items']: for itm in catalog['items']:
if itm['type'] == 'ITP': if itm['type'] == 'ITP':
edit.append(itm['key'][3:])
self.log('**Past Editions available :', ', '.join(edit))
for itm in catalog['items']:
if past_edition:
if itm['key'] == 'ITP' + past_edition:
key = itm['key'] key = itm['key']
manifest = itm['manifest'] manifest = itm['manifest']
dt = datetime.fromisoformat(itm['date'][:-1]) + timedelta(seconds=time.timezone) dt = datetime.fromisoformat(itm['date'][:-1]) + timedelta(seconds=time.timezone)
dt = dt.strftime('%b %d, %Y') dt = dt.strftime('%b %d, %Y')
self.log(dt) self.log('Downloading Past Edition ', dt)
self.timefmt = ' [' + dt + ']'
break
elif itm['type'] == 'ITP':
key = itm['key']
manifest = itm['manifest']
dt = datetime.fromisoformat(itm['date'][:-1]) + timedelta(seconds=time.timezone)
dt = dt.strftime('%b %d, %Y')
self.log('Downloading ', dt)
self.timefmt = ' [' + dt + ']' self.timefmt = ' [' + dt + ']'
break break
@ -151,9 +172,20 @@ class WSJ(BasicNewsRecipe):
for x in root.xpath('//image'): for x in root.xpath('//image'):
x.tag = 'img' x.tag = 'img'
return BeautifulSoup(raw).prettify() return BeautifulSoup(raw).prettify()
return raw else:
soup = BeautifulSoup(raw)
url = soup.find('meta', attrs={'property':'og:url'})
if url:
h1 = soup.find('h1')
if h1:
h1['title'] = url['content']
return soup.prettify()
def populate_article_metadata(self, article, soup, first): def populate_article_metadata(self, article, soup, first):
lnk = soup.find('p', attrs={'id':'share-link'}) lnk = soup.find('p', attrs={'id':'share-link'})
if lnk: if lnk:
article.url = lnk['title'] article.url = lnk['title']
art = soup.find('h1', attrs={'title':True})
if art:
self.log('found art ', art['title'])
article.url = art['title']