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

Cleanup previous PR

Browse Source 
recipes have to run on old python 2 based calibre as well, so no type
annotations
This commit is contained in:
Kovid Goyal 2022-02-18 17:29:35 +05:30
parent ac8a115eed
commit 803da449ba
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 7 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
recipes/mainichi_en.recipe
View File

@ -12,9 +12,7 @@ www.mainichi.jp/english
""" """
from datetime import datetime from datetime import datetime
from typing import List, Dict
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
@ -40,7 +38,7 @@ class MainichiEnglishNews(BasicNewsRecipe):
remove_tags_after = {"class": "main-text"} remove_tags_after = {"class": "main-text"}
remove_tags = [{"name": "div", "id": "tools"}, {"name": "div", "class": "sub"}] remove_tags = [{"name": "div", "id": "tools"}, {"name": "div", "class": "sub"}]
def get_pickup_section(self, soup: BeautifulSoup()) -> List[Dict[str, str]]: def get_pickup_section(self, soup):
# Topmost story # Topmost story
top = soup.find("section", attrs={"class": "pickup section"}) top = soup.find("section", attrs={"class": "pickup section"})
top_link = top.find("p", attrs={"class": "midashi"}).find("a") top_link = top.find("p", attrs={"class": "midashi"}).find("a")
@ -69,7 +67,7 @@ class MainichiEnglishNews(BasicNewsRecipe):
} }
] ]
def retrieve_news_from_column(self, column) -> List[Dict[str, str]]: def retrieve_news_from_column(self, column):
column_news = [] column_news = []
for item in column.findAll("li"): for item in column.findAll("li"):
@ -88,7 +86,7 @@ class MainichiEnglishNews(BasicNewsRecipe):
return column_news return column_news
def get_top_stories(self, soup: BeautifulSoup()) -> List[Dict[str, str]]: def get_top_stories(self, soup):
top_stories = self.get_pickup_section(soup) top_stories = self.get_pickup_section(soup)
news_section = soup.find("section", attrs={"class": "newslist"}) news_section = soup.find("section", attrs={"class": "newslist"})
@ -98,7 +96,7 @@ class MainichiEnglishNews(BasicNewsRecipe):
return top_stories return top_stories
def get_editor_picks(self, soup: BeautifulSoup()) -> List[Dict[str, str]]: def get_editor_picks(self, soup):
editor_picks = [] editor_picks = []
news_section = soup.find("section", attrs={"class": "newslist"}) news_section = soup.find("section", attrs={"class": "newslist"})
@ -108,8 +106,8 @@ class MainichiEnglishNews(BasicNewsRecipe):
return editor_picks return editor_picks
def get_section(self, section) -> List[Dict[str, str]]: def get_section(self, section):
soup: BeautifulSoup = self.index_to_soup(self.index + section + "index.html") soup = self.index_to_soup(self.index + section + "index.html")
section_news_items = self.get_pickup_section(soup) section_news_items = self.get_pickup_section(soup)
@ -124,7 +122,7 @@ class MainichiEnglishNews(BasicNewsRecipe):
return section_news_items return section_news_items
def parse_index(self): def parse_index(self):
soup: BeautifulSoup = self.index_to_soup(self.index + "index.html") soup = self.index_to_soup(self.index + "index.html")
feeds = [ feeds = [
("Top Stories", self.get_top_stories(soup)), ("Top Stories", self.get_top_stories(soup)),
@ -142,6 +140,3 @@ class MainichiEnglishNews(BasicNewsRecipe):
] ]
return feeds return feeds
calibre_most_common_ua = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.87 Safari/537.36"