mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
111 lines
4.0 KiB
Python
111 lines
4.0 KiB
Python
#!/usr/bin/env python
|
|
__license__ = "GPL v3"
|
|
|
|
import json
|
|
from datetime import datetime
|
|
from os.path import splitext
|
|
from urllib.parse import urljoin
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
|
|
|
|
|
class ScientificAmerican(BasicNewsRecipe):
|
|
title = "Scientific American"
|
|
description = "Popular Science. Monthly magazine. Should be downloaded around the middle of each month."
|
|
category = "science"
|
|
__author__ = "Kovid Goyal"
|
|
no_stylesheets = True
|
|
language = "en"
|
|
publisher = "Nature Publishing Group"
|
|
remove_empty_feeds = True
|
|
remove_javascript = True
|
|
timefmt = " [%B %Y]"
|
|
remove_attributes = ["height", "width"]
|
|
masthead_url = (
|
|
"https://static.scientificamerican.com/sciam/assets/Image/newsletter/salogo.png"
|
|
)
|
|
extra_css = """
|
|
.image-captioned{font-size:small;}
|
|
.feature-article__byline-authors{font-size:small;}
|
|
.article-header__inner__category{font-size:small; color:gray;}
|
|
.t_caption{font-size:small; text-align:center;}
|
|
.author-bio{font-size:small;}
|
|
.opinion-article__byline-authors{font-size:small;}
|
|
.article-author{font-size:small;}
|
|
[role="presentation"]{font-size:small;}
|
|
"""
|
|
|
|
needs_subscription = "optional"
|
|
|
|
keep_only_tags = [
|
|
classes(
|
|
"article-header article-content article-media article-author article-text feature-article--header"
|
|
" feature-article--header-title opinion-article__header-title author-bio"
|
|
),
|
|
]
|
|
remove_tags = [
|
|
classes(
|
|
"aside-banner moreToExplore article-footer flex-column--25 article-author__suggested medium-up-hide"
|
|
),
|
|
dict(id=["seeAlsoLinks"]),
|
|
]
|
|
|
|
def get_browser(self, *args):
|
|
br = BasicNewsRecipe.get_browser(self)
|
|
if self.username and self.password:
|
|
br.open("https://www.scientificamerican.com/my-account/login/")
|
|
br.select_form(predicate=lambda f: f.attrs.get("id") == "login")
|
|
br["emailAddress"] = self.username
|
|
br["password"] = self.password
|
|
br.submit()
|
|
return br
|
|
|
|
def parse_index(self):
|
|
# Get the cover, date and issue URL
|
|
fp_soup = self.index_to_soup("https://www.scientificamerican.com")
|
|
curr_issue_link = fp_soup.select(".tout_current-issue__cover a")
|
|
if not curr_issue_link:
|
|
self.abort_recipe_processing("Unable to find issue link")
|
|
issue_url = curr_issue_link[0]["href"]
|
|
soup = self.index_to_soup(issue_url)
|
|
script = soup.find("script", id="__NEXT_DATA__")
|
|
if not script:
|
|
self.abort_recipe_processing("Unable to find script")
|
|
|
|
issue_info = (
|
|
json.loads(script.contents[0])
|
|
.get("props", {})
|
|
.get("pageProps", {})
|
|
.get("issue", {})
|
|
)
|
|
if not issue_info:
|
|
self.abort_recipe_processing("Unable to find issue info")
|
|
|
|
image_id, _ = splitext(issue_info["image"])
|
|
self.cover_url = f"https://static.scientificamerican.com/sciam/cache/file/{image_id}_source.jpg?w=800"
|
|
|
|
edition_date = datetime.strptime(issue_info["issue_date"], "%Y-%m-%d")
|
|
self.timefmt = f" [{edition_date:%B %Y}]"
|
|
|
|
feeds = {}
|
|
for section in ("featured", "departments"):
|
|
for article in issue_info.get("article_previews", {}).get(section, []):
|
|
if section == "featured":
|
|
feed_name = "Features"
|
|
else:
|
|
feed_name = article["category"]
|
|
if feed_name not in feeds:
|
|
feeds[feed_name] = []
|
|
feeds[feed_name].append(
|
|
{
|
|
"title": article["title"],
|
|
"url": urljoin(
|
|
"https://www.scientificamerican.com/article/",
|
|
article["slug"],
|
|
),
|
|
"description": article["summary"],
|
|
}
|
|
)
|
|
|
|
return feeds.items()
|