this is the reicpe.
(science magazine, was requested here)
got a 403 error.. It could be accessed with read_url.
The below recipe works but images fail with 403.
Code:
#!/usr/bin/env python
from calibre.scraper.simple import read_url
from calibre.web.feeds.news import BasicNewsRecipe, classes
from calibre.ebooks.BeautifulSoup import BeautifulSoup
def absurl(url):
if url.startswith('/'):
url = 'https://www.science.org' + url
return url
class science(BasicNewsRecipe):
title = 'Science Journal'
__author__ = 'unkn0wn'
description = (
'Science continues to publish the very best in research across the sciences, with articles that '
'consistently rank among the most cited in the world.'
)
encoding = 'utf-8'
no_javascript = True
no_stylesheets = True
remove_attributes = ['style', 'height', 'width']
language = 'en'
extra_css = '''
.news-article__figure__caption {font-size:small; text-align:center;}
.contributors, .core-self-citation, .meta-panel__left-content, .news-article__hero__top-meta,
.news-article__hero__bottom-meta, #bibliography, #elettersSection {font-size:small;}
img {display:block; margin:0 auto;}
.core-lede {font-style:italic; color:#202020;}
'''
ignore_duplicate_articles = {'url'}
def preprocess_html(self, soup):
for p in soup.findAll(attrs={'role':'paragraph'}):
p.name = 'p'
return soup
keep_only_tags = [
classes('meta-panel__left-content news-article__hero__info news-article__hero__figure bodySection'),
dict(name='h1', attrs={'property':'name'}),
classes('core-lede contributors core-self-citation'),
dict(attrs={'data-core-wrapper':'content'})
]
remove_tags = [
classes('pb-ad')
]
articles_are_obfuscated = True
def get_obfuscated_article(self, url):
return { 'data': read_url([], url), 'url': url }
def parse_index(self):
url = 'https://www.science.org/toc/science/current'
soup = BeautifulSoup(read_url([], url))
tme = soup.find(**classes('journal-issue__vol'))
if tme:
self.timefmt = ' [%s]' % self.tag_to_string(tme).strip()
det = soup.find(attrs={'id':'journal-issue-details'})
if det:
self.description = self.tag_to_string(det).strip()
feeds = []
div = soup.find('div', attrs={'class':'toc__body'})
for sec in div.findAll('section', **classes('toc__section')):
name = sec.find(**classes('sidebar-article-title--decorated'))
section = self.tag_to_string(name).strip()
self.log(section)
articles = []
for card in sec.findAll(**classes('card-header')):
ti = card.find(**classes('article-title'))
url = absurl(ti.a['href'])
title = self.tag_to_string(ti).strip()
desc = ''
meta = card.find(**classes('card-meta'))
if meta:
desc = self.tag_to_string(meta).strip()
self.log(' ', title, '\n\t', desc, '\n\t', url)
articles.append({'title': title, 'description':desc, 'url': url})
feeds.append((section, articles))
return feeds
I made changes and tried something but got a I got a TypeError
should i've not used index_to_soup with read_url
File "<string>", line 66, in parse_index
File "calibre\web\feeds\news.py", line 731, in index_to_soup
TypeError: science.open() got an unexpected keyword argument 'timeout'