| 1 |
#!/usr/bin/env python |
| 2 |
|
| 3 |
__license__ = 'GPL v3' |
| 4 |
__copyright__ = '2014, Nikolas Mangold-Takao <nmangold at gmail.com>' |
| 5 |
__version__ = '0.10' |
| 6 |
|
| 7 |
from calibre.web.feeds.recipes import BasicNewsRecipe |
| 8 |
|
| 9 |
|
| 10 |
class IncMagazineRecipe(BasicNewsRecipe): |
| 11 |
language = 'en' |
| 12 |
version = 1 |
| 13 |
|
| 14 |
__author__ = 'Nikolas Mangold-Takao <nmangold at gmail.com>' |
| 15 |
|
| 16 |
title = 'Inc Magazine' |
| 17 |
publisher = 'Mansueto Ventures LLC' |
| 18 |
category = 'News, Business' |
| 19 |
description = 'Free account required to browse website. Handbook of the American Entrepeneur' |
| 20 |
|
| 21 |
# signup is free, without account browsing is limited and recipe won't work |
| 22 |
needs_subscription = True |
| 23 |
|
| 24 |
use_embedded_content = False |
| 25 |
remove_empty_feeds = True |
| 26 |
|
| 27 |
no_stylesheets = True |
| 28 |
remove_javascript = True |
| 29 |
|
| 30 |
INDEX = 'http://www.inc.com/magazine' |
| 31 |
|
| 32 |
remove_tags_before = dict(name='div', attrs={'id': 'outercontainer'}) |
| 33 |
remove_tags = [dict(name='div', attrs={'id': 'morearticles'})] |
| 34 |
remove_tags_after = dict(name='div', attrs={'id': 'article-share-footer'}) |
| 35 |
|
| 36 |
extra_css = ''' |
| 37 |
div.byline {font-size: x-small; color: #696969; margin-top: 0.4em;} |
| 38 |
''' |
| 39 |
|
| 40 |
def get_browser(self): |
| 41 |
def has_login_name(form): |
| 42 |
try: |
| 43 |
form.find_control(name='email') |
| 44 |
except Exception: |
| 45 |
return False |
| 46 |
else: |
| 47 |
return True |
| 48 |
|
| 49 |
br = BasicNewsRecipe.get_browser(self) |
| 50 |
if self.username is not None and self.password is not None: |
| 51 |
br.open('http://www.inc.com/login') |
| 52 |
br.select_form(predicate=has_login_name) |
| 53 |
br['email'] = self.username |
| 54 |
br['password'] = self.password |
| 55 |
br.submit() |
| 56 |
return br |
| 57 |
|
| 58 |
def parse_index(self): |
| 59 |
soup = self.index_to_soup(self.INDEX) |
| 60 |
|
| 61 |
feeds = [] |
| 62 |
articles = [] |
| 63 |
|
| 64 |
# We need for sure 'toc-top-l-column' and 'toc-bot-l-column' |
| 65 |
# I am not sure about 'toc-top-r-column and 'toc-bot-r-column', seems |
| 66 |
# to be mostly ads |
| 67 |
for toc in soup.findAll('div', id=lambda x: x and x.endswith('-l-column')): |
| 68 |
# h1-h2-h3 |
| 69 |
for article in toc.findAll('div', {'class': lambda x: x and x.startswith('toc-h')}): |
| 70 |
link = article.find('a') |
| 71 |
if link is None: |
| 72 |
continue |
| 73 |
article_title = self.tag_to_string(link) |
| 74 |
article_link = link.get('href') |
| 75 |
articles.append({'title': article_title, 'url': article_link}) |
| 76 |
feeds.append(('Articles', articles)) # TODO figure out sections |
| 77 |
return feeds |
| 78 |
|
| 79 |
def preprocess_html(self, soup): |
| 80 |
for alink in soup.findAll('a'): |
| 81 |
if alink.string is not None: |
| 82 |
tstr = alink.string |
| 83 |
alink.replaceWith(tstr) |
| 84 |
return soup |