| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
import json |
| 4 |
import re |
| 5 |
from collections import defaultdict |
| 6 |
from datetime import date |
| 7 |
|
| 8 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 9 |
|
| 10 |
|
| 11 |
def absurl(url): |
| 12 |
if url.startswith('/'): |
| 13 |
url = 'https://www.thehindu.com' + url |
| 14 |
return url |
| 15 |
|
| 16 |
|
| 17 |
class TheHindu(BasicNewsRecipe): |
| 18 |
title = 'The Hindu Print Edition' |
| 19 |
__author__ = 'unkn0wn' |
| 20 |
description = "Articles from The Hindu, Today's Paper." |
| 21 |
language = 'en_IN' |
| 22 |
no_stylesheets = True |
| 23 |
masthead_url = 'https://www.thehindu.com/theme/images/th-online/thehindu-logo.svg' |
| 24 |
remove_attributes = ['style', 'height', 'width'] |
| 25 |
|
| 26 |
extra_css = ''' |
| 27 |
.caption {font-size:small; text-align:center;} |
| 28 |
.author, .dateLine {font-size:small;} |
| 29 |
.subhead, .subhead_lead, .bold {font-weight:bold;} |
| 30 |
img {display:block; margin:0 auto;} |
| 31 |
.italic, .sub-title {font-style:italic; color:#202020;} |
| 32 |
''' |
| 33 |
|
| 34 |
recipe_specific_options = { |
| 35 |
'location': { |
| 36 |
'short': 'The name of the local edition', |
| 37 |
'long': ( |
| 38 |
'If The Hindu is available in your local town/city, ' |
| 39 |
'set this to your location, for example, hyderabad\n' |
| 40 |
'Available Editions: bengaluru, chennai, coimbatore, delhi, ' |
| 41 |
'erode, hyderabad, international, kochi, kolkata,\n' |
| 42 |
'kozhikode, madurai, mangalore, mumbai, thiruvananthapuram, ' |
| 43 |
'tiruchirapalli, vijayawada, visakhapatnam' |
| 44 |
), |
| 45 |
'default': 'chennai', |
| 46 |
}, |
| 47 |
'date': {'short': 'The date of the edition to download (YYYY-MM-DD format)', 'long': 'For example, 2023-01-28'}, |
| 48 |
} |
| 49 |
|
| 50 |
ignore_duplicate_articles = {'url'} |
| 51 |
|
| 52 |
keep_only_tags = [classes('article-section')] |
| 53 |
|
| 54 |
remove_tags = [classes('hide-mobile comments-shares share-page editiondetails')] |
| 55 |
|
| 56 |
def preprocess_html(self, soup): |
| 57 |
for cap in soup.findAll('p', attrs={'class': 'caption'}): |
| 58 |
cap.name = 'figcaption' |
| 59 |
for img in soup.findAll('img', attrs={'data-original': True}): |
| 60 |
img['src'] = img['data-original'] |
| 61 |
for h3 in soup.findAll(**classes('sub-title')): |
| 62 |
h3.name = 'p' |
| 63 |
return soup |
| 64 |
|
| 65 |
def parse_index(self): |
| 66 |
self.title = 'The Hindu' |
| 67 |
local_edition = 'th_chennai' |
| 68 |
d = self.recipe_specific_options.get('location') |
| 69 |
if d and isinstance(d, str): |
| 70 |
local_edition = 'th_' + d |
| 71 |
|
| 72 |
past_edition = self.recipe_specific_options.get('date') |
| 73 |
|
| 74 |
dt = date.today() |
| 75 |
if past_edition and isinstance(past_edition, str): |
| 76 |
year, month, day = (int(x) for x in past_edition.split('-')) |
| 77 |
dt = date(year, month, day) |
| 78 |
|
| 79 |
today = dt.strftime('%Y-%m-%d') |
| 80 |
|
| 81 |
self.log('Downloading The Hindu, ' + local_edition[3:] + ' edition, ' + today) |
| 82 |
url = absurl('/todays-paper/' + today + '/' + local_edition + '/') |
| 83 |
if local_edition == 'th_chennai' and today == date.today().strftime('%Y-%m-%d'): |
| 84 |
url = absurl('/todays-paper/') |
| 85 |
|
| 86 |
mag_url = None |
| 87 |
if dt.weekday() == 0: |
| 88 |
mag_url = url + '?supplement=' + local_edition + '-epbs' |
| 89 |
if dt.weekday() == 4: |
| 90 |
mag_url = url + '?supplement=' + local_edition + '-fr' |
| 91 |
if dt.weekday() == 5: |
| 92 |
mag_url = url + '?supplement=' + local_edition + '-mp' |
| 93 |
if dt.weekday() == 6: |
| 94 |
mag_url = url + '?supplement=' + local_edition + '-sm' |
| 95 |
|
| 96 |
raw = self.index_to_soup(url, raw=True) |
| 97 |
soup = self.index_to_soup(raw) |
| 98 |
ans = self.hindu_parse_index(soup) |
| 99 |
if not ans: |
| 100 |
raise ValueError('The Hindu Newspaper is not published Today.') |
| 101 |
cover = soup.find(attrs={'class': 'hindu-ad'}) |
| 102 |
if cover: |
| 103 |
self.cover_url = cover.img['src'] |
| 104 |
if mag_url: |
| 105 |
self.log('\nFetching Magazine') |
| 106 |
soup = self.index_to_soup(mag_url) |
| 107 |
ans2 = self.hindu_parse_index(soup) |
| 108 |
if ans2: |
| 109 |
return ans + ans2 |
| 110 |
self.log('\nMagazine not Found') |
| 111 |
return ans |
| 112 |
return ans |
| 113 |
|
| 114 |
def hindu_parse_index(self, soup): |
| 115 |
for script in soup.findAll('script'): |
| 116 |
if not self.tag_to_string(script).__contains__('grouped_articles = {"'): |
| 117 |
continue |
| 118 |
if script is not None: |
| 119 |
art = re.search(r'grouped_articles = ({\".*)', self.tag_to_string(script)) |
| 120 |
data = json.JSONDecoder().raw_decode(art.group(1))[0] |
| 121 |
|
| 122 |
feeds_dict = defaultdict(list) |
| 123 |
|
| 124 |
a = json.dumps(data) |
| 125 |
for sec in json.loads(a): |
| 126 |
for item in data[sec]: |
| 127 |
section = sec.replace('TH_', '') |
| 128 |
title = item['articleheadline'] |
| 129 |
url = absurl(item['href']) |
| 130 |
desc = 'Page no.' + item['pageno'] + ' | ' + item['teaser_text'] or '' |
| 131 |
self.log(' ', title, '\n\t', url) |
| 132 |
feeds_dict[section].append({'title': title, 'url': url, 'description': desc}) |
| 133 |
return list(feeds_dict.items()) |
| 134 |
else: |
| 135 |
return [] |