| 1 |
import re |
| 2 |
from collections import OrderedDict |
| 3 |
|
| 4 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 5 |
|
| 6 |
|
| 7 |
class HistoryToday(BasicNewsRecipe): |
| 8 |
title = 'History Today' |
| 9 |
__author__ = 'Rick Shang' |
| 10 |
|
| 11 |
description = 'UK-based magazine, publishing articles and book reviews covering all types and periods of history.' |
| 12 |
language = 'en' |
| 13 |
category = 'news' |
| 14 |
encoding = 'UTF-8' |
| 15 |
|
| 16 |
remove_tags = [ |
| 17 |
dict(name='div', attrs={'class': ['print-logo', 'print-site_name', 'print-breadcrumb']}), |
| 18 |
dict(name='div', attrs={'id': ['ht-tools', 'ht-tools2', 'ht-tags']}), |
| 19 |
] |
| 20 |
no_javascript = True |
| 21 |
no_stylesheets = True |
| 22 |
|
| 23 |
needs_subscription = True |
| 24 |
|
| 25 |
def get_browser(self): |
| 26 |
br = BasicNewsRecipe.get_browser(self) |
| 27 |
if self.username is not None and self.password is not None: |
| 28 |
br.open('https://www.historytoday.com/user/login') |
| 29 |
br.select_form(nr=1) |
| 30 |
br['name'] = self.username |
| 31 |
br['pass'] = self.password |
| 32 |
res = br.submit() |
| 33 |
raw = res.read() |
| 34 |
if b'Session limit exceeded' in raw: |
| 35 |
br.select_form(nr=1) |
| 36 |
control = br.find_control('sid').items[1] |
| 37 |
sid = [] |
| 38 |
br['sid'] = sid.join(control) |
| 39 |
br.submit() |
| 40 |
return br |
| 41 |
|
| 42 |
def parse_index(self): |
| 43 |
|
| 44 |
# Find date |
| 45 |
soup0 = self.index_to_soup('https://www.historytoday.com/') |
| 46 |
dates = self.tag_to_string(soup0.find('div', attrs={'id': 'block-block-226'}).span) |
| 47 |
self.timefmt = ' [%s]' % dates |
| 48 |
|
| 49 |
# Go to issue |
| 50 |
soup = self.index_to_soup('https://www.historytoday.com/contents') |
| 51 |
cover = soup.find('div', attrs={'id': 'content-area'}).find('img', attrs={'src': re.compile(r'.*cover.*')})['src'] |
| 52 |
self.cover_url = cover |
| 53 |
self.log(self.cover_url) |
| 54 |
|
| 55 |
# Go to the main body |
| 56 |
|
| 57 |
div = soup.find('div', attrs={'class': 'region region-content-bottom'}) |
| 58 |
|
| 59 |
feeds = OrderedDict() |
| 60 |
section_title = '' |
| 61 |
for section in div.findAll('div', attrs={'id': re.compile(r'block\-views\-contents.*')}): |
| 62 |
section_title = self.tag_to_string(section.find('h2', attrs={'class': 'title'})) |
| 63 |
sectionbody = section.find('div', attrs={'class': 'view-content'}) |
| 64 |
for article in sectionbody.findAll('div', attrs={'class': re.compile(r'views\-row.*')}): |
| 65 |
articles = [] |
| 66 |
subarticle = [] |
| 67 |
subarticle = article.findAll('div') |
| 68 |
if len(subarticle) < 2: |
| 69 |
continue |
| 70 |
title = self.tag_to_string(subarticle[0]) |
| 71 |
originalurl = 'https://www.historytoday.com' + subarticle[0].span.a['href'].strip() |
| 72 |
originalpage = self.index_to_soup(originalurl) |
| 73 |
printurl = originalpage.find('div', attrs={'id': 'ht-tools'}).a['href'].strip() |
| 74 |
url = 'https://www.historytoday.com' + printurl |
| 75 |
desc = self.tag_to_string(subarticle[1]) |
| 76 |
articles.append({'title': title, 'url': url, 'description': desc, 'date': ''}) |
| 77 |
|
| 78 |
if articles: |
| 79 |
if section_title not in feeds: |
| 80 |
feeds[section_title] = [] |
| 81 |
feeds[section_title] += articles |
| 82 |
|
| 83 |
ans = list(feeds.items()) |
| 84 |
return ans |
| 85 |
|
| 86 |
def cleanup(self): |
| 87 |
self.browser.open('https://www.historytoday.com/logout') |