| 1 |
## |
| 2 |
# Title: BBC News, Sport, and Blog Calibre Recipe |
| 3 |
# Contact: mattst - [email protected] |
| 4 |
## |
| 5 |
# License: GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html |
| 6 |
# Copyright: mattst - [email protected] |
| 7 |
## |
| 8 |
# Written: November 2011 |
| 9 |
# Last Edited: 2011-11-19 |
| 10 |
## |
| 11 |
|
| 12 |
__license__ = 'GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html' |
| 13 |
__copyright__ = 'mattst - [email protected]' |
| 14 |
|
| 15 |
|
| 16 |
''' |
| 17 |
BBC News, Sport, and Blog Calibre Recipe |
| 18 |
''' |
| 19 |
|
| 20 |
# Import the regular expressions module. |
| 21 |
import re |
| 22 |
|
| 23 |
# Import the BasicNewsRecipe class which this class extends. |
| 24 |
from calibre.web.feeds.recipes import BasicNewsRecipe |
| 25 |
|
| 26 |
|
| 27 |
class BBCBrasilRecipe(BasicNewsRecipe): |
| 28 |
# |
| 29 |
# **** IMPORTANT USERS READ ME **** |
| 30 |
# |
| 31 |
# First select the feeds you want then scroll down below the feeds list |
| 32 |
# and select the values you want for the other user preferences, like |
| 33 |
# oldest_article and such like. |
| 34 |
# |
| 35 |
# |
| 36 |
# Select the BBC rss feeds which you want in your ebook. |
| 37 |
# Selected feed have NO '#' at their start, de-selected feeds begin with a '#'. |
| 38 |
# |
| 39 |
# Eg. ("News Home", "http://feeds.bbci.co.uk/... - include feed. |
| 40 |
# Eg. #("News Home", "http://feeds.bbci.co.uk/... - do not include feed. |
| 41 |
# |
| 42 |
# There are 68 feeds below which constitute the bulk of the available rss |
| 43 |
# feeds on the BBC web site. These include 5 blogs by editors and |
| 44 |
# correspondents, 16 sports feeds, 15 'sub' regional feeds (Eg. North West |
| 45 |
# Wales, Scotland Business), and 7 Welsh language feeds. |
| 46 |
# |
| 47 |
# Some of the feeds are low volume (Eg. blogs), or very low volume (Eg. Click) |
| 48 |
# so if "oldest_article = 1.5" (only articles published in the last 36 hours) |
| 49 |
# you may get some 'empty feeds' which will not then be included in the ebook. |
| 50 |
# |
| 51 |
# The 15 feeds currently selected below are simply my default ones. |
| 52 |
# |
| 53 |
# Note: With all 68 feeds selected, oldest_article set to 2, |
| 54 |
# max_articles_per_feed set to 100, and simultaneous_downloads set to 10, |
| 55 |
# the ebook creation took 29 minutes on my speedy 100 mbps net connection, |
| 56 |
# fairly high-end desktop PC running Linux (Ubuntu Lucid-Lynx). |
| 57 |
# More realistically with 15 feeds selected, oldest_article set to 1.5, |
| 58 |
# max_articles_per_feed set to 100, and simultaneous_downloads set to 20, |
| 59 |
# it took 6 minutes. If that's too slow increase 'simultaneous_downloads'. |
| 60 |
# |
| 61 |
# Select / de-select the feeds you want in your ebook. |
| 62 |
# |
| 63 |
feeds = [ |
| 64 |
('Primeira P\xe1gina', 'http://www.bbc.co.uk/portuguese/index.xml'), |
| 65 |
('\xdaltimas Not\xedcias', 'http://www.bbc.co.uk/portuguese/ultimas_noticias/index.xml'), |
| 66 |
('Internacional', 'http://www.bbc.co.uk/portuguese/topicos/internacional/index.xml'), |
| 67 |
('Brasil', 'http://www.bbc.co.uk/portuguese/topicos/brasil/index.xml'), |
| 68 |
('Am\xe9rica Latina', 'http://www.bbc.co.uk/portuguese/topicos/america_latina/index.xml'), |
| 69 |
('Economia', 'http://www.bbc.co.uk/portuguese/topicos/economia/index.xml'), |
| 70 |
('Sa\xfade', 'http://www.bbc.co.uk/portuguese/topicos/saude/index.xml'), |
| 71 |
('Ci\xeancia e Tecnologia', 'http://www.bbc.co.uk/portuguese/topicos/ciencia_e_tecnologia/index.xml'), |
| 72 |
('Cultura', 'http://www.bbc.co.uk/portuguese/topicos/cultura/index.xml'), |
| 73 |
('V\xeddeos e Fotos', 'http://www.bbc.co.uk/portuguese/videos_e_fotos/index.xml'), |
| 74 |
('Especiais', 'http://www.bbc.co.uk/portuguese/especiais/index.xml'), |
| 75 |
] |
| 76 |
|
| 77 |
# **** SELECT YOUR USER PREFERENCES **** |
| 78 |
|
| 79 |
# Title to use for the ebook. |
| 80 |
# |
| 81 |
title = 'BBC Brasil' |
| 82 |
|
| 83 |
# A brief description for the ebook. |
| 84 |
# |
| 85 |
description = 'Not\xedcias do Brasil e do mundo pela British Broadcasting Corporation' |
| 86 |
|
| 87 |
# The max number of articles which may be downloaded from each feed. |
| 88 |
# I've never seen more than about 70 articles in a single feed in the |
| 89 |
# BBC feeds. |
| 90 |
# |
| 91 |
max_articles_per_feed = 100 |
| 92 |
|
| 93 |
# The max age of articles which may be downloaded from each feed. This is |
| 94 |
# specified in days - note fractions of days are allowed, Eg. 2.5 (2 and a |
| 95 |
# half days). My default of 1.5 days is the last 36 hours, the point at |
| 96 |
# which I've decided 'news' becomes 'old news', but be warned this is not |
| 97 |
# so good for the blogs, technology, magazine, etc., and sports feeds. |
| 98 |
# You may wish to extend this to 2-5 but watch out ebook creation time will |
| 99 |
# increase as well. Setting this to 30 will get everything (AFAICT) as long |
| 100 |
# as max_articles_per_feed remains set high (except for 'Click' which is |
| 101 |
# v. low volume and its currently oldest article is 4th Feb 2011). |
| 102 |
# |
| 103 |
oldest_article = 1.5 |
| 104 |
|
| 105 |
# Number of simultaneous downloads. 20 is consistently working fine on the |
| 106 |
# BBC News feeds with no problems. Speeds things up from the default of 5. |
| 107 |
# If you have a lot of feeds and/or have increased oldest_article above 2 |
| 108 |
# then you may wish to try increasing simultaneous_downloads to 25-30, |
| 109 |
# Or, of course, if you are in a hurry. [I've not tried beyond 20.] |
| 110 |
# |
| 111 |
simultaneous_downloads = 20 |
| 112 |
|
| 113 |
# Timeout for fetching files from the server in seconds. The default of |
| 114 |
# 120 seconds, seems somewhat excessive. |
| 115 |
# |
| 116 |
timeout = 30 |
| 117 |
|
| 118 |
# The format string for the date shown on the ebook's first page. |
| 119 |
# List of all values: http://docs.python.org/library/time.html |
| 120 |
# Default in news.py has a leading space so that's mirrored here. |
| 121 |
# As with 'feeds' select/de-select by adding/removing the initial '#', |
| 122 |
# only one timefmt should be selected, here's a few to choose from. |
| 123 |
# |
| 124 |
# [Fri, 14 Nov 2011] (Calibre default) |
| 125 |
timefmt = ' [%a, %d %b %Y]' |
| 126 |
# timefmt = ' [%a, %d %b %Y %H:%M]' # [Fri, 14 Nov 2011 18:30] |
| 127 |
# timefmt = ' [%a, %d %b %Y %I:%M %p]' # [Fri, 14 Nov 2011 06:30 PM] |
| 128 |
# timefmt = ' [%d %b %Y]' # [14 Nov 2011] |
| 129 |
# timefmt = ' [%d %b %Y %H:%M]' # [14 Nov 2011 18.30] |
| 130 |
# timefmt = ' [%Y-%m-%d]' # [2011-11-14] |
| 131 |
# timefmt = ' [%Y-%m-%d-%H-%M]' # [2011-11-14-18-30] |
| 132 |
|
| 133 |
# |
| 134 |
# **** IMPORTANT **** |
| 135 |
# |
| 136 |
# DO NOT EDIT BELOW HERE UNLESS YOU KNOW WHAT YOU ARE DOING. |
| 137 |
# |
| 138 |
# DO NOT EDIT BELOW HERE UNLESS YOU KNOW WHAT YOU ARE DOING. |
| 139 |
# |
| 140 |
# I MEAN IT, YES I DO, ABSOLUTELY, AT YOU OWN RISK. :) |
| 141 |
# |
| 142 |
# **** IMPORTANT **** |
| 143 |
# |
| 144 |
|
| 145 |
# Author of this recipe. |
| 146 |
__author__ = 'Carlos Laviola' |
| 147 |
|
| 148 |
language = 'pt_BR' |
| 149 |
|
| 150 |
# Set tags. |
| 151 |
tags = 'news, sport, blog' |
| 152 |
|
| 153 |
# Set publisher and publication type. |
| 154 |
publisher = 'BBC' |
| 155 |
publication_type = 'newspaper' |
| 156 |
|
| 157 |
# Disable stylesheets from site. |
| 158 |
no_stylesheets = True |
| 159 |
|
| 160 |
# Specifies an override encoding for sites that have an incorrect charset |
| 161 |
# specified. Default of 'None' says to auto-detect. Some other BBC recipes |
| 162 |
# use 'utf8', which works fine (so use that if necessary) but auto-detecting |
| 163 |
# with None is working fine, so stick with that for robustness. |
| 164 |
encoding = None |
| 165 |
|
| 166 |
# Sets whether a feed has full articles embedded in it. The BBC feeds do |
| 167 |
# not. |
| 168 |
use_embedded_content = False |
| 169 |
|
| 170 |
# Removes empty feeds - why keep them!? |
| 171 |
remove_empty_feeds = True |
| 172 |
|
| 173 |
# Create a custom title which fits nicely in the Kindle title list. |
| 174 |
# Requires "import time" above class declaration, and replacing |
| 175 |
# title with custom_title in conversion_options (right column only). |
| 176 |
# Example of string below: "BBC News - 14 Nov 2011" |
| 177 |
# |
| 178 |
# custom_title = "BBC News - " + time.strftime('%d %b %Y') |
| 179 |
|
| 180 |
''' |
| 181 |
# Conversion options for advanced users, but don't forget to comment out the |
| 182 |
# current conversion_options below. Avoid setting 'linearize_tables' as that |
| 183 |
# plays havoc with the 'old style' table based pages. |
| 184 |
# |
| 185 |
conversion_options = { 'title' : title, |
| 186 |
'comments' : description, |
| 187 |
'tags' : tags, |
| 188 |
'language' : language, |
| 189 |
'publisher' : publisher, |
| 190 |
'authors' : publisher, |
| 191 |
'smarten_punctuation' : True |
| 192 |
} |
| 193 |
''' |
| 194 |
|
| 195 |
conversion_options = {'smarten_punctuation': True} |
| 196 |
|
| 197 |
# Specify extra CSS - overrides ALL other CSS (IE. Added last). |
| 198 |
extra_css = '''body { font-family: verdana, helvetica, sans-serif; } |
| 199 |
.introduction, .first { font-weight: bold; } |
| 200 |
.cross-head { font-weight: bold; font-size: 125%; } |
| 201 |
.cap, .caption { display: block; font-size: 80%; font-style: italic; } |
| 202 |
.cap, .caption, .caption img, .caption span { display: block; text-align: center; margin: 5px auto; } |
| 203 |
.byl, .byd, .byline img, .byline-name, .byline-title, .author-name, .author-position, |
| 204 |
.correspondent-portrait img, .byline-lead-in, .name, .role, .bbc-role { display: block; |
| 205 |
text-align: center; font-size: 80%; font-style: italic; margin: 1px auto; } |
| 206 |
.story-date, .published, .datestamp { font-size: 80%; } |
| 207 |
table { width: 100%; } |
| 208 |
td img { display: block; margin: 5px auto; } |
| 209 |
ul { padding-top: 10px; } |
| 210 |
ol { padding-top: 10px; } |
| 211 |
li { padding-top: 5px; padding-bottom: 5px; } |
| 212 |
h1 { text-align: center; font-size: 175%; font-weight: bold; } |
| 213 |
h2 { text-align: center; font-size: 150%; font-weight: bold; } |
| 214 |
h3 { text-align: center; font-size: 125%; font-weight: bold; } |
| 215 |
h4, h5, h6 { text-align: center; font-size: 100%; font-weight: bold; }''' |
| 216 |
|
| 217 |
# Remove various tag attributes to improve the look of the ebook pages. |
| 218 |
remove_attributes = ['border', 'cellspacing', 'align', 'cellpadding', 'colspan', 'valign', 'vspace', 'hspace', 'alt', 'width', 'height'] |
| 219 |
|
| 220 |
# Remove the (admittedly rarely used) line breaks, "<br />", which sometimes |
| 221 |
# cause a section of the ebook to start in an unsightly fashion or, more |
| 222 |
# frequently, a "<br />" will muck up the formatting of a correspondant's byline. |
| 223 |
# "<br />" and "<br clear/>" are far more frequently used on the table formatted |
| 224 |
# style of pages, and really spoil the look of the ebook pages. |
| 225 |
preprocess_regexps = [(re.compile(r'<br[ ]*/>', re.IGNORECASE), lambda m: ''), (re.compile(r'<br[ ]*clear.*/>', re.IGNORECASE), lambda m: '')] |
| 226 |
|
| 227 |
# Create regular expressions for tag keeping and removal to make the matches more |
| 228 |
# robust against minor changes and errors in the HTML, Eg. double spaces, leading |
| 229 |
# and trailing spaces, missing hyphens, and such like. |
| 230 |
# Python regular expression ('re' class) page: |
| 231 |
# http://docs.python.org/library/re.html |
| 232 |
|
| 233 |
# *************************************** |
| 234 |
# Regular expressions for keep_only_tags: |
| 235 |
# *************************************** |
| 236 |
|
| 237 |
# The BBC News HTML pages use variants of 'storybody' to denote the section of a HTML |
| 238 |
# page which contains the main text of the article. Match storybody variants: 'storybody', |
| 239 |
# 'story-body', 'story body','storybody ', etc. |
| 240 |
storybody_reg_exp = '^.*story[_ -]*body.*$' |
| 241 |
|
| 242 |
# The BBC sport and 'newsbeat' (features) HTML pages use 'blq_content' to hold the title |
| 243 |
# and published date. This is one level above the usual news pages which have the title |
| 244 |
# and date within 'story-body'. This is annoying since 'blq_content' must also be kept, |
| 245 |
# resulting in a lot of extra things to be removed by remove_tags. |
| 246 |
blq_content_reg_exp = '^.*blq[_ -]*content.*$' |
| 247 |
|
| 248 |
# The BBC has an alternative page design structure, which I suspect is an out-of-date |
| 249 |
# design but which is still used in some articles, Eg. 'Click' (technology), 'FastTrack' |
| 250 |
# (travel), and in some sport pages. These alternative pages are table based (which is |
| 251 |
# why I think they are an out-of-date design) and account for -I'm guesstimaking- less |
| 252 |
# than 1% of all articles. They use a table class 'storycontent' to hold the article |
| 253 |
# and like blq_content (above) have required lots of extra removal by |
| 254 |
# remove_tags. |
| 255 |
story_content_reg_exp = '^.*story[_ -]*content.*$' |
| 256 |
|
| 257 |
# Keep the sections of the HTML which match the list below. The HTML page created by |
| 258 |
# Calibre will fill <body> with those sections which are matched. Note that the |
| 259 |
# blq_content_reg_exp must be listed before storybody_reg_exp in keep_only_tags due to |
| 260 |
# it being the parent of storybody_reg_exp, that is to say the div class/id 'story-body' |
| 261 |
# will be inside div class/id 'blq_content' in the HTML (if 'blq_content' is there at |
| 262 |
# all). If they are the other way around in keep_only_tags then blq_content_reg_exp |
| 263 |
# will end up being discarded. |
| 264 |
keep_only_tags = [ |
| 265 |
dict(name='table', attrs={'class': re.compile(story_content_reg_exp, re.IGNORECASE)}), |
| 266 |
dict(name='div', attrs={'class': re.compile(blq_content_reg_exp, re.IGNORECASE)}), |
| 267 |
dict(name='div', attrs={'id': re.compile(blq_content_reg_exp, re.IGNORECASE)}), |
| 268 |
dict(name='div', attrs={'class': re.compile(storybody_reg_exp, re.IGNORECASE)}), |
| 269 |
dict(name='div', attrs={'id': re.compile(storybody_reg_exp, re.IGNORECASE)}), |
| 270 |
] |
| 271 |
|
| 272 |
# ************************************ |
| 273 |
# Regular expressions for remove_tags: |
| 274 |
# ************************************ |
| 275 |
|
| 276 |
# Regular expression to remove share-help and variant tags. The share-help class |
| 277 |
# is used by the site for a variety of 'sharing' type links, Eg. Facebook, delicious, |
| 278 |
# twitter, email. Removed to avoid page clutter. |
| 279 |
share_help_reg_exp = '^.*share[_ -]*help.*$' |
| 280 |
|
| 281 |
# Regular expression to remove embedded-hyper and variant tags. This class is used to |
| 282 |
# display links to other BBC News articles on the same/similar subject. |
| 283 |
embedded_hyper_reg_exp = '^.*embed*ed[_ -]*hyper.*$' |
| 284 |
|
| 285 |
# Regular expression to remove hypertabs and variant tags. This class is used to |
| 286 |
# display a tab bar at the top of an article which allows the user to switch to |
| 287 |
# an article (viewed on the same page) providing further info., 'in depth' analysis, |
| 288 |
# an editorial, a correspondant's blog entry, and such like. The ability to handle |
| 289 |
# a tab bar of this nature is currently beyond the scope of this recipe and |
| 290 |
# possibly of Calibre itself (not sure about that - TO DO - check!). |
| 291 |
hypertabs_reg_exp = '^.*hyper[_ -]*tabs.*$' |
| 292 |
|
| 293 |
# Regular expression to remove story-feature and variant tags. Eg. 'story-feature', |
| 294 |
# 'story-feature related narrow', 'story-feature wide', 'story-feature narrow'. |
| 295 |
# This class is used to add additional info. boxes, or small lists, outside of |
| 296 |
# the main story. TO DO: Work out a way to incorporate these neatly. |
| 297 |
story_feature_reg_exp = '^.*story[_ -]*feature.*$' |
| 298 |
|
| 299 |
# Regular expression to remove video and variant tags, Eg. 'videoInStoryB', |
| 300 |
# 'videoInStoryC'. This class is used to embed video. |
| 301 |
video_reg_exp = '^.*video.*$' |
| 302 |
|
| 303 |
# Regular expression to remove audio and variant tags, Eg. 'audioInStoryD'. |
| 304 |
# This class is used to embed audio. |
| 305 |
audio_reg_exp = '^.*audio.*$' |
| 306 |
|
| 307 |
# Regular expression to remove pictureGallery and variant tags, Eg. 'pictureGallery'. |
| 308 |
# This class is used to embed a photo slideshow. See also 'slideshow' |
| 309 |
# below. |
| 310 |
picture_gallery_reg_exp = '^.*picture.*$' |
| 311 |
|
| 312 |
# Regular expression to remove slideshow and variant tags, Eg. 'dslideshow-enclosure'. |
| 313 |
# This class is used to embed a slideshow (not necessarily photo) but both |
| 314 |
# 'slideshow' and 'pictureGallery' are used for slideshows. |
| 315 |
slideshow_reg_exp = '^.*slide[_ -]*show.*$' |
| 316 |
|
| 317 |
# Regular expression to remove social-links and variant tags. This class is used to |
| 318 |
# display links to a BBC bloggers main page, used in various columnist's blogs |
| 319 |
# (Eg. Nick Robinson, Robert Preston). |
| 320 |
social_links_reg_exp = '^.*social[_ -]*links.*$' |
| 321 |
|
| 322 |
# Regular expression to remove quote and (multi) variant tags, Eg. 'quote', |
| 323 |
# 'endquote', 'quote-credit', 'quote-credit-title', etc. These are usually |
| 324 |
# removed by 'story-feature' removal (as they are usually within them), but |
| 325 |
# not always. The quotation removed is always (AFAICT) in the article text |
| 326 |
# as well but a 2nd copy is placed in a quote tag to draw attention to it. |
| 327 |
# The quote class tags may or may not appear in div's. |
| 328 |
quote_reg_exp = '^.*quote.*$' |
| 329 |
|
| 330 |
# Regular expression to remove hidden and variant tags, Eg. 'hidden'. |
| 331 |
# The purpose of these is unclear, they seem to be an internal link to a |
| 332 |
# section within the article, but the text of the link (Eg. 'Continue reading |
| 333 |
# the main story') never seems to be displayed anyway. Removed to avoid clutter. |
| 334 |
# The hidden class tags may or may not appear in div's. |
| 335 |
hidden_reg_exp = '^.*hidden.*$' |
| 336 |
|
| 337 |
# Regular expression to remove comment and variant tags, Eg. 'comment-introduction'. |
| 338 |
# Used on the site to display text about registered users entering |
| 339 |
# comments. |
| 340 |
comment_reg_exp = '^.*comment.*$' |
| 341 |
|
| 342 |
# Regular expression to remove form and variant tags, Eg. 'comment-form'. |
| 343 |
# Used on the site to allow registered BBC users to fill in forms, typically |
| 344 |
# for entering comments about an article. |
| 345 |
form_reg_exp = '^.*form.*$' |
| 346 |
|
| 347 |
# Extra things to remove due to the addition of 'blq_content' in |
| 348 |
# keep_only_tags. |
| 349 |
|
| 350 |
# <div class="story-actions"> Used on sports pages for 'email' and 'print'. |
| 351 |
story_actions_reg_exp = '^.*story[_ -]*actions.*$' |
| 352 |
|
| 353 |
# <div class="bookmark-list"> Used on sports pages instead of 'share-help' (for |
| 354 |
# social networking links). |
| 355 |
bookmark_list_reg_exp = '^.*bookmark[_ -]*list.*$' |
| 356 |
|
| 357 |
# <div id="secondary-content" class="content-group"> |
| 358 |
# NOTE: Don't remove class="content-group" that is needed. |
| 359 |
# Used on sports pages to link to 'similar stories'. |
| 360 |
secondary_content_reg_exp = '^.*secondary[_ -]*content.*$' |
| 361 |
|
| 362 |
# <div id="featured-content" class="content-group"> |
| 363 |
# NOTE: Don't remove class="content-group" that is needed. |
| 364 |
# Used on sports pages to link to pages like 'tables', 'fixtures', etc. |
| 365 |
featured_content_reg_exp = '^.*featured[_ -]*content.*$' |
| 366 |
|
| 367 |
# <div id="navigation"> |
| 368 |
# Used on sports pages to link to pages like 'tables', 'fixtures', etc. |
| 369 |
# Used sometimes instead of "featured-content" above. |
| 370 |
navigation_reg_exp = '^.*navigation.*$' |
| 371 |
|
| 372 |
# <a class="skip" href="#blq-container-inner">Skip to top</a> |
| 373 |
# Used on sports pages to link to the top of the page. |
| 374 |
skip_reg_exp = '^.*skip.*$' |
| 375 |
|
| 376 |
# Extra things to remove due to the addition of 'storycontent' in keep_only_tags, |
| 377 |
# which are the alternative table design based pages. The purpose of some of these |
| 378 |
# is not entirely clear from the pages (which are a total mess!). |
| 379 |
|
| 380 |
# Remove mapping based tags, Eg. <map id="world_map"> |
| 381 |
# The dynamic maps don't seem to work during ebook creation. TO DO: |
| 382 |
# Investigate. |
| 383 |
map_reg_exp = '^.*map.*$' |
| 384 |
|
| 385 |
# Remove social bookmarking variation, called 'socialBookMarks'. |
| 386 |
social_bookmarks_reg_exp = '^.*social[_ -]*bookmarks.*$' |
| 387 |
|
| 388 |
# Remove page navigation tools, like 'search', 'email', 'print', called |
| 389 |
# 'blq-mast'. |
| 390 |
blq_mast_reg_exp = '^.*blq[_ -]*mast.*$' |
| 391 |
|
| 392 |
# Remove 'sharesb', I think this is a generic 'sharing' class. It seems to appear |
| 393 |
# alongside 'socialBookMarks' whenever that appears. I am removing it as well |
| 394 |
# under the assumption that it can appear alone as well. |
| 395 |
sharesb_reg_exp = '^.*sharesb.*$' |
| 396 |
|
| 397 |
# Remove class 'o'. The worst named user created css class of all time. The creator |
| 398 |
# should immediately be fired. I've seen it used to hold nothing at all but with |
| 399 |
# 20 or so empty lines in it. Also to hold a single link to another article. |
| 400 |
# Whatever it was designed to do it is not wanted by this recipe. Exact |
| 401 |
# match only. |
| 402 |
o_reg_exp = '^o$' |
| 403 |
|
| 404 |
# Remove 'promotopbg' and 'promobottombg', link lists. Have decided to |
| 405 |
# use two reg expressions to make removing this (and variants) robust. |
| 406 |
promo_top_reg_exp = '^.*promotopbg.*$' |
| 407 |
promo_bottom_reg_exp = '^.*promobottombg.*$' |
| 408 |
|
| 409 |
# Remove 'nlp', provides heading for link lists. Requires an exact match due to |
| 410 |
# risk of matching those letters in something needed, unless I see a variation |
| 411 |
# of 'nlp' used at a later date. |
| 412 |
nlp_reg_exp = '^nlp$' |
| 413 |
|
| 414 |
# Remove 'mva', provides embedded floating content of various types. Variant 'mvb' |
| 415 |
# has also now been seen. Requires an exact match of 'mva' or 'mvb' due to risk of |
| 416 |
# matching those letters in something needed. |
| 417 |
mva_or_mvb_reg_exp = '^mv[ab]$' |
| 418 |
|
| 419 |
# Remove 'mvtb', seems to be page navigation tools, like 'blq-mast'. |
| 420 |
mvtb_reg_exp = '^mvtb$' |
| 421 |
|
| 422 |
# Remove 'blq-toplink', class to provide a link to the top of the page. |
| 423 |
blq_toplink_reg_exp = '^.*blq[_ -]*top[_ -]*link.*$' |
| 424 |
|
| 425 |
# Remove 'products and services' links, Eg. desktop tools, alerts, and so on. |
| 426 |
# Eg. Class="servicev4 ukfs_services" - what a mess of a name. Have decided to |
| 427 |
# use two reg expressions to make removing this (and variants) robust. |
| 428 |
prods_services_01_reg_exp = '^.*servicev4.*$' |
| 429 |
prods_services_02_reg_exp = '^.*ukfs[_ -]*services.*$' |
| 430 |
|
| 431 |
# Remove -what I think is- some kind of navigation tools helper class, though I am |
| 432 |
# not sure, it's called: 'blq-rst blq-new-nav'. What I do know is it pops up |
| 433 |
# frequently and it is not wanted. Have decided to use two reg expressions to make |
| 434 |
# removing this (and variants) robust. |
| 435 |
blq_misc_01_reg_exp = '^.*blq[_ -]*rst.*$' |
| 436 |
blq_misc_02_reg_exp = '^.*blq[_ -]*new[_ -]*nav.*$' |
| 437 |
|
| 438 |
# Remove 'puffbox' - this may only appear inside 'storyextra', so it may not |
| 439 |
# need removing - I have no clue what it does other than it contains links. |
| 440 |
# Whatever it is - it is not part of the article and is not wanted. |
| 441 |
puffbox_reg_exp = '^.*puffbox.*$' |
| 442 |
|
| 443 |
# Remove 'sibtbg' and 'sibtbgf' - some kind of table formatting classes. |
| 444 |
sibtbg_reg_exp = '^.*sibtbg.*$' |
| 445 |
|
| 446 |
# Remove 'storyextra' - links to relevant articles and external sites. |
| 447 |
storyextra_reg_exp = '^.*story[_ -]*extra.*$' |
| 448 |
|
| 449 |
remove_tags = [ |
| 450 |
dict(name='div', attrs={'class': re.compile(story_feature_reg_exp, re.IGNORECASE)}), |
| 451 |
dict(name='div', attrs={'class': re.compile(share_help_reg_exp, re.IGNORECASE)}), |
| 452 |
dict(name='div', attrs={'class': re.compile(embedded_hyper_reg_exp, re.IGNORECASE)}), |
| 453 |
dict(name='div', attrs={'class': re.compile(hypertabs_reg_exp, re.IGNORECASE)}), |
| 454 |
dict(name='div', attrs={'class': re.compile(video_reg_exp, re.IGNORECASE)}), |
| 455 |
dict(name='div', attrs={'class': re.compile(audio_reg_exp, re.IGNORECASE)}), |
| 456 |
dict(name='div', attrs={'class': re.compile(picture_gallery_reg_exp, re.IGNORECASE)}), |
| 457 |
dict(name='div', attrs={'class': re.compile(slideshow_reg_exp, re.IGNORECASE)}), |
| 458 |
dict(name='div', attrs={'class': re.compile(quote_reg_exp, re.IGNORECASE)}), |
| 459 |
dict(name='div', attrs={'class': re.compile(hidden_reg_exp, re.IGNORECASE)}), |
| 460 |
dict(name='div', attrs={'class': re.compile(comment_reg_exp, re.IGNORECASE)}), |
| 461 |
dict(name='div', attrs={'class': re.compile(story_actions_reg_exp, re.IGNORECASE)}), |
| 462 |
dict(name='div', attrs={'class': re.compile(bookmark_list_reg_exp, re.IGNORECASE)}), |
| 463 |
dict(name='div', attrs={'id': re.compile(secondary_content_reg_exp, re.IGNORECASE)}), |
| 464 |
dict(name='div', attrs={'id': re.compile(featured_content_reg_exp, re.IGNORECASE)}), |
| 465 |
dict(name='div', attrs={'id': re.compile(navigation_reg_exp, re.IGNORECASE)}), |
| 466 |
dict(name='form', attrs={'id': re.compile(form_reg_exp, re.IGNORECASE)}), |
| 467 |
dict(attrs={'class': re.compile(quote_reg_exp, re.IGNORECASE)}), |
| 468 |
dict(attrs={'class': re.compile(hidden_reg_exp, re.IGNORECASE)}), |
| 469 |
dict(attrs={'class': re.compile(social_links_reg_exp, re.IGNORECASE)}), |
| 470 |
dict(attrs={'class': re.compile(comment_reg_exp, re.IGNORECASE)}), |
| 471 |
dict(attrs={'class': re.compile(skip_reg_exp, re.IGNORECASE)}), |
| 472 |
dict(name='map', attrs={'id': re.compile(map_reg_exp, re.IGNORECASE)}), |
| 473 |
dict(name='map', attrs={'name': re.compile(map_reg_exp, re.IGNORECASE)}), |
| 474 |
dict(name='div', attrs={'id': re.compile(social_bookmarks_reg_exp, re.IGNORECASE)}), |
| 475 |
dict(name='div', attrs={'id': re.compile(blq_mast_reg_exp, re.IGNORECASE)}), |
| 476 |
dict(name='div', attrs={'class': re.compile(sharesb_reg_exp, re.IGNORECASE)}), |
| 477 |
dict(name='div', attrs={'class': re.compile(o_reg_exp, re.IGNORECASE)}), |
| 478 |
dict(name='div', attrs={'class': re.compile(promo_top_reg_exp, re.IGNORECASE)}), |
| 479 |
dict(name='div', attrs={'class': re.compile(promo_bottom_reg_exp, re.IGNORECASE)}), |
| 480 |
dict(name='div', attrs={'class': re.compile(nlp_reg_exp, re.IGNORECASE)}), |
| 481 |
dict(name='div', attrs={'class': re.compile(mva_or_mvb_reg_exp, re.IGNORECASE)}), |
| 482 |
dict(name='div', attrs={'class': re.compile(mvtb_reg_exp, re.IGNORECASE)}), |
| 483 |
dict(name='div', attrs={'class': re.compile(blq_toplink_reg_exp, re.IGNORECASE)}), |
| 484 |
dict(name='div', attrs={'class': re.compile(prods_services_01_reg_exp, re.IGNORECASE)}), |
| 485 |
dict(name='div', attrs={'class': re.compile(prods_services_02_reg_exp, re.IGNORECASE)}), |
| 486 |
dict(name='div', attrs={'class': re.compile(blq_misc_01_reg_exp, re.IGNORECASE)}), |
| 487 |
dict(name='div', attrs={'class': re.compile(blq_misc_02_reg_exp, re.IGNORECASE)}), |
| 488 |
dict(name='div', attrs={'class': re.compile(puffbox_reg_exp, re.IGNORECASE)}), |
| 489 |
dict(attrs={'class': re.compile(sibtbg_reg_exp, re.IGNORECASE)}), |
| 490 |
dict(attrs={'class': re.compile(storyextra_reg_exp, re.IGNORECASE)}), |
| 491 |
dict(name='div', attrs={'class': 'tools-container'}), |
| 492 |
dict(name='div', attrs={'class': 'tools-container-end'}), |
| 493 |
dict(name='div', attrs={'class': 'g-block story-body contextual-links'}), |
| 494 |
dict(name='div', attrs={'class': ' g-w11 sidebar'}), |
| 495 |
] |
| 496 |
|
| 497 |
# Uses url to create and return the 'printer friendly' version of the url. |
| 498 |
# In other words the 'print this page' address of the page. |
| 499 |
# |
| 500 |
# There are 3 types of urls used in the BBC site's rss feeds. There is just |
| 501 |
# 1 type for the standard news while there are 2 used for sports feed urls. |
| 502 |
# Note: Sports urls are linked from regular news feeds (Eg. 'News Home') when |
| 503 |
# there is a major story of interest to 'everyone'. So even if no BBC sports |
| 504 |
# feeds are added to 'feeds' the logic of this method is still needed to avoid |
| 505 |
# blank / missing / empty articles which have an index title and then no |
| 506 |
# body. |
| 507 |
def print_version(self, url): |
| 508 |
|
| 509 |
# Handle sports page urls type 01: |
| 510 |
if url.find('go/rss/-/sport1/') != -1: |
| 511 |
temp_url = url.replace('go/rss/-/', '') |
| 512 |
|
| 513 |
# Handle sports page urls type 02: |
| 514 |
elif url.find('go/rss/int/news/-/sport1/') != -1: |
| 515 |
temp_url = url.replace('go/rss/int/news/-/', '') |
| 516 |
|
| 517 |
# Handle regular news page urls: |
| 518 |
else: |
| 519 |
temp_url = url.replace('go/rss/int/news/-/', '') |
| 520 |
|
| 521 |
# Always add "?print=true" to the end of the url. |
| 522 |
print_url = temp_url + '?print=true' |
| 523 |
|
| 524 |
return print_url |
| 525 |
|
| 526 |
# Remove articles in feeds based on a string in the article title or url. |
| 527 |
# |
| 528 |
# Code logic written by: Starson17 - posted in: "Recipes - Re-usable code" |
| 529 |
# thread, in post with title: "Remove articles from feed", see url: |
| 530 |
# http://www.mobileread.com/forums/showpost.php?p=1165462&postcount=6 |
| 531 |
# Many thanks and all credit to Starson17. |
| 532 |
# |
| 533 |
# Starson17's code has obviously been altered to suite my requirements. |
| 534 |
def parse_feeds(self): |
| 535 |
|
| 536 |
# Call parent's method. |
| 537 |
feeds = BasicNewsRecipe.parse_feeds(self) |
| 538 |
|
| 539 |
# Loop through all feeds. |
| 540 |
for feed in feeds: |
| 541 |
# Loop through all articles in feed. |
| 542 |
for article in feed.articles[:]: |
| 543 |
# Match key words and remove article if there's a match. |
| 544 |
|
| 545 |
# Most BBC rss feed video only 'articles' use upper case 'VIDEO' |
| 546 |
# as a title prefix. Just match upper case 'VIDEO', so that |
| 547 |
# articles like 'Video game banned' won't be matched and |
| 548 |
# removed. |
| 549 |
if 'VIDEO' in article.title: |
| 550 |
feed.articles.remove(article) |
| 551 |
|
| 552 |
# Most BBC rss feed audio only 'articles' use upper case 'AUDIO' |
| 553 |
# as a title prefix. Just match upper case 'AUDIO', so that |
| 554 |
# articles like 'Hi-Def audio...' won't be matched and removed. |
| 555 |
elif 'AUDIO' in article.title: |
| 556 |
feed.articles.remove(article) |
| 557 |
|
| 558 |
# Most BBC rss feed photo slideshow 'articles' use 'In Pictures', |
| 559 |
# 'In pictures', and 'in pictures', somewhere in their title. |
| 560 |
# Match any case of that phrase. |
| 561 |
elif 'IN PICTURES' in article.title.upper(): |
| 562 |
feed.articles.remove(article) |
| 563 |
|
| 564 |
# As above, but user contributed pictures. Match any case. |
| 565 |
elif 'YOUR PICTURES' in article.title.upper(): |
| 566 |
feed.articles.remove(article) |
| 567 |
|
| 568 |
# 'Sportsday Live' are articles which contain a constantly and |
| 569 |
# dynamically updated 'running commentary' during a live sporting |
| 570 |
# event. Match any case. |
| 571 |
elif 'SPORTSDAY LIVE' in article.title.upper(): |
| 572 |
feed.articles.remove(article) |
| 573 |
|
| 574 |
# Sometimes 'Sportsday Live' (above) becomes 'Live - Sport Name'. |
| 575 |
# These are being matched below using 'Live - ' because removing all |
| 576 |
# articles with 'live' in their titles would remove some articles |
| 577 |
# that are in fact not live sports pages. Match any case. |
| 578 |
elif 'LIVE - ' in article.title.upper(): |
| 579 |
feed.articles.remove(article) |
| 580 |
|
| 581 |
# 'Quiz of the week' is a Flash player weekly news quiz. Match only |
| 582 |
# the 'Quiz of the' part in anticipation of monthly and yearly |
| 583 |
# variants. Match any case. |
| 584 |
elif 'QUIZ OF THE' in article.title.upper(): |
| 585 |
feed.articles.remove(article) |
| 586 |
|
| 587 |
# Remove articles with 'scorecards' in the url. These are BBC sports |
| 588 |
# pages which just display a cricket scorecard. The pages have a mass |
| 589 |
# of table and css entries to display the scorecards nicely. Probably |
| 590 |
# could make them work with this recipe, but might take a whole day |
| 591 |
# of work to sort out all the css - basically a formatting |
| 592 |
# nightmare. |
| 593 |
elif 'scorecards' in article.url: |
| 594 |
feed.articles.remove(article) |
| 595 |
|
| 596 |
return feeds |
| 597 |
|
| 598 |
|
| 599 |
# End of class and file. |