| 1 |
__license__ = 'GPL v3' |
| 2 |
|
| 3 |
''' |
| 4 |
www.esquire.com |
| 5 |
''' |
| 6 |
from collections import defaultdict |
| 7 |
|
| 8 |
from css_selectors import Select |
| 9 |
|
| 10 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 11 |
|
| 12 |
|
| 13 |
def absolutize(url): |
| 14 |
if url.startswith('/'): |
| 15 |
url = 'https://www.esquire.com' + url |
| 16 |
return url |
| 17 |
|
| 18 |
|
| 19 |
def classes(classes): |
| 20 |
q = frozenset(classes.split(' ')) |
| 21 |
return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}) |
| 22 |
|
| 23 |
|
| 24 |
class Esquire(BasicNewsRecipe): |
| 25 |
title = 'Esquire' |
| 26 |
__author__ = 'Kovid Goyal' |
| 27 |
description = 'Esquire: Man at His Best' |
| 28 |
publisher = 'Hearst Communications, Inc.' |
| 29 |
no_stylesheets = True |
| 30 |
encoding = 'utf-8' |
| 31 |
language = 'en' |
| 32 |
|
| 33 |
keep_only_tags = [classes('article-header gallery-header listicle-header listicle-body standard-header standard-body article-body gallery-main-view')] |
| 34 |
|
| 35 |
remove_tags = [classes('article-body--share-container tags--top image-share share-gallery embedded-image--expand embedded-image--close')] |
| 36 |
|
| 37 |
def preprocess_html(self, soup): |
| 38 |
for img in soup.findAll('img', attrs={'data-src': True}): |
| 39 |
img['src'] = img['data-src'] |
| 40 |
return soup |
| 41 |
|
| 42 |
def parse_index(self): |
| 43 |
url = 'https://www.esquire.com' |
| 44 |
root = self.index_to_soup(url, as_tree=True) |
| 45 |
select = Select(root) |
| 46 |
feeds = defaultdict(list) |
| 47 |
|
| 48 |
for a in select('.cover-story-marquee a[href]'): |
| 49 |
title = self.tag_to_string(a).strip() or 'Cover Story' |
| 50 |
url = absolutize(a.get('href')) |
| 51 |
self.log('Cover story:', title, url) |
| 52 |
feeds['Cover Story'] = [{'title': title, 'url': url}] |
| 53 |
break |
| 54 |
|
| 55 |
for a in select('a[data-vars-cta]'): |
| 56 |
title = self.tag_to_string(a).strip() |
| 57 |
if not title: |
| 58 |
continue |
| 59 |
url = absolutize(a.get('href')) |
| 60 |
section = a.get('data-vars-cta') |
| 61 |
feeds[section].append({'title': title, 'url': url}) |
| 62 |
self.log(title, url) |
| 63 |
|
| 64 |
ans = [] |
| 65 |
for sec in sorted(feeds, key=lambda x: (x != 'Cover Story', x)): |
| 66 |
articles = feeds[sec] |
| 67 |
if articles: |
| 68 |
ans.append((sec, articles)) |
| 69 |
return ans |