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

Use a dict instead of a list of tuples

Browse Source
This commit is contained in:
Henrik Holm 2024-10-06 00:40:05 +02:00
parent 4ebc9ba110
commit 896a9d6561
1 changed files with 15 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
recipes/fokus.recipe
View File

@ -74,37 +74,37 @@ class Fokus(BasicNewsRecipe):
br.submit()
return br
def get_web_sections(self, main_url: str) -> list[tuple[str, str]]:
"""Return a list of tuples of (1) the URL and (2) the name of each section found on the Fokus website.
def get_web_sections(self, main_url: str) -> dict[str, str]:
"""Return a dict of (1) section URL and (2) section name key-value pairs found at `main_url`.
For example, if the Fokus website currently includes an 'Aktuellt' section, create a
`('https://www.fokus.se/aktuellt', 'Aktuellt')` tuple.
For example, if the Fokus website currently includes an 'Aktuellt' section, the dict should include an entry on
the form: `{'https://www.fokus.se/aktuellt': 'Aktuellt'}`.
Args:
main_url (str): The entrypoint URL of the Fokus website.
Yields:
list[tuple[str, str]]: Pairs of (1) the URL and (2) the human-readable name of each Fokus section.
dict[str, str]: (1) URLs and (2) human-readable names of Fokus sections.
"""
soup = self.index_to_soup(main_url)
# Identify all unique <li> tags of class 'menu-item-type-taxonomy'. The class subsetting excludes sections that
# are not suited for reading, e.g., the "Podcast" and "Läs E-Tidningen" sections.
unique_urls = set()
section_urls_and_names = []
section_urls_and_names = {}
for li_tag in soup.find_all('li', class_='menu-item-type-taxonomy'):
# The <li> tag contains (should contain) an <a> anchor that in turn contains the URL and link name.
a_tag = li_tag.find('a')
url = a_tag.get('href').rstrip('/')
link_name = a_tag.text.strip()
section_name = a_tag.text.strip()
# Skip this <li> tag as we have already extracted its URL and link name from another <li> tag.
if url in unique_urls:
continue
unique_urls.add(url)
if url in section_urls_and_names:
# If this section URL has already been extracted from another <li> tag, it can be the case that the
# section name differs within this duplicate pair. In this case, use whichever section name is longer.
if len(section_name) >= len(section_urls_and_names[url]):
section_urls_and_names[url] = section_name
self.log(f"Identified section '{link_name}' at URL '{url}'")
section_urls_and_names.append((url, link_name))
self.log(f"Identified section '{section_name}' at URL '{url}'")
section_urls_and_names[url] = section_name
self.log(f'Identified a total of {len(section_urls_and_names)} unique sections.')
return section_urls_and_names
@ -152,7 +152,7 @@ class Fokus(BasicNewsRecipe):
def parse_index(self):
feeds = []
for section_url, section_title in self.get_web_sections(self.main_url):
for section_url, section_title in self.get_web_sections(self.main_url).items():
try:
soup = self.index_to_soup(section_url)
except Exception: