| 1 |
#!/usr/bin/env python |
| 2 |
|
| 3 |
""" |
| 4 |
http://www.pcworld.com/ |
| 5 |
""" |
| 6 |
|
| 7 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 8 |
|
| 9 |
|
| 10 |
class pcWorld(BasicNewsRecipe): |
| 11 |
__author__ = 'unkn0wn' |
| 12 |
description = 'PCWorld helps you navigate the PC ecosystem to find the products you want and the advice you need to get the job done.' |
| 13 |
title = 'PCWorld' |
| 14 |
publisher = 'IDG Communication' |
| 15 |
language = 'en' |
| 16 |
encoding = 'utf-8' |
| 17 |
ignore_duplicate_articles = {'url'} |
| 18 |
remove_javascript = True |
| 19 |
resolve_internal_links = True |
| 20 |
remove_empty_feeds = True |
| 21 |
remove_attributes = ['height', 'width'] |
| 22 |
|
| 23 |
extra_css = ''' |
| 24 |
.entry-meta, .imageCredit {font-size:small;} |
| 25 |
.entry-eyebrow, .article_author_box_bio {font-size:small; color:#404040;} |
| 26 |
.subheadline {font-style:italic; color:#202020;} |
| 27 |
''' |
| 28 |
|
| 29 |
keep_only_tags = [classes('entry-header post-thumbnail'), dict(name='div', attrs={'id': 'link_wrapped_content'}), classes('article_author_box_bio')] |
| 30 |
|
| 31 |
def parse_index(self): |
| 32 |
|
| 33 |
section_list = [ |
| 34 |
('PC & Components', 'pc-components'), |
| 35 |
('Laptops', 'laptops'), |
| 36 |
('Mobile', 'mobile'), |
| 37 |
('How-To', 'howto'), |
| 38 |
('Gaming', 'gaming'), |
| 39 |
('Windows', 'windows'), |
| 40 |
('Best-Picks', 'best-picks'), |
| 41 |
('Reviews', 'reviews'), |
| 42 |
('Security', 'security'), |
| 43 |
('Smart Tech', 'smart-tech'), |
| 44 |
('Software', 'software'), |
| 45 |
('WiFi & Networks', 'wifi-networks'), |
| 46 |
('Deals', 'deals'), |
| 47 |
('Business', 'business'), |
| 48 |
('Entertainment', 'entertainment'), |
| 49 |
] |
| 50 |
|
| 51 |
feeds = [] |
| 52 |
|
| 53 |
# For each section title, fetch the article urls |
| 54 |
for section in section_list: |
| 55 |
section_title = section[0] |
| 56 |
section_url = 'https://www.pcworld.com/' + section[1] |
| 57 |
self.log(section_title, section_url) |
| 58 |
soup = self.index_to_soup(section_url) |
| 59 |
articles = self.articles_from_soup(soup) |
| 60 |
if articles: |
| 61 |
feeds.append((section_title, articles)) |
| 62 |
return feeds |
| 63 |
|
| 64 |
def articles_from_soup(self, soup): |
| 65 |
ans = [] |
| 66 |
feed = soup.find('div', attrs={'class': lambda x: x and 'articleFeed-inner' in x.split()}) |
| 67 |
for item in feed.findAll('div', attrs={'class': 'item-text-inner'}): |
| 68 |
a = item.find('h3').find('a', href=True) |
| 69 |
title = self.tag_to_string(a) |
| 70 |
url = a['href'] |
| 71 |
desc = '' |
| 72 |
if span := item.find(attrs={'class': 'item-excerpt'}): |
| 73 |
desc = self.tag_to_string(span) |
| 74 |
if byline := item.find(attrs={'class': 'item-byline'}): |
| 75 |
desc = self.tag_to_string(byline) + ' | ' + desc |
| 76 |
if eye := item.find(attrs={'class': lambda x: x and 'item-eyebrow' in x.split()}): |
| 77 |
desc = self.tag_to_string(eye) + ' | ' + desc |
| 78 |
if itdate := item.find(attrs={'class': 'item-date'}): |
| 79 |
date = self.tag_to_string(itdate) |
| 80 |
check = 'hours', 'day', 'days' # skipping articles older than a week |
| 81 |
if not any(x in date for x in check): |
| 82 |
continue |
| 83 |
if not url or not title: |
| 84 |
continue |
| 85 |
self.log('\t', title, '\n\t', desc, '\n\t\t', url) |
| 86 |
ans.append({'title': title, 'url': url, 'description': desc}) |
| 87 |
return ans |
| 88 |
|
| 89 |
def get_cover_url(self): |
| 90 |
soup = self.index_to_soup('https://www.magzter.com/US/IDG-Consumer-and-SMB,-Inc./PCWorld/Computer-&-Mobile/') |
| 91 |
return soup.find('img', id=lambda s: s and 'mgd__lhd__cover' in s.split())['src'] |