mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Update The BBC
This commit is contained in:
Kovid Goyal
parent
9569e33d09
commit
2e6f0e7a59
@ -142,9 +142,7 @@ to the recipe. Finally, lets replace some of the :term:`CSS` that we disabled ea
|
||||
|
||||
extra_css = '.headline {font-size: x-large;} \n .fact { padding-top: 10pt }'
|
||||
|
||||
With these additions, our recipe has become "production quality", indeed it is very close to the actual recipe used by calibre for the *BBC*, shown below:
|
||||
|
||||
.. literalinclude:: ../../../recipes/bbc.recipe
|
||||
With these additions, our recipe has become "production quality".
|
||||
|
||||
This :term:`recipe` explores only the tip of the iceberg when it comes to the power of calibre. To explore more of the abilities of calibre we'll examine a more complex real life example in the next section.
|
||||
|
||||
|
||||
@ -1,72 +1,115 @@
|
||||
##
|
||||
# Title: BBC News, Sport, and Blog Calibre Recipe
|
||||
# Contact: mattst - jmstanfield@gmail.com
|
||||
##
|
||||
# License: GNU General Public License v3 - https://www.gnu.org/copyleft/gpl.html
|
||||
# Copyright: mattst - jmstanfield@gmail.com
|
||||
##
|
||||
# Written: November 2011
|
||||
# Last Edited: 2011-11-19
|
||||
##
|
||||
#!/usr/bin/env python
|
||||
# vim:fileencoding=utf-8
|
||||
# License: GPLv3 Copyright: 2020, Kovid Goyal <kovid at kovidgoyal.net>
|
||||
|
||||
__license__ = 'GNU General Public License v3 - https://www.gnu.org/copyleft/gpl.html'
|
||||
__copyright__ = 'mattst - jmstanfield@gmail.com'
|
||||
import json
|
||||
|
||||
|
||||
'''
|
||||
BBC News, Sport, and Blog Calibre Recipe
|
||||
'''
|
||||
|
||||
# Import the regular expressions module.
|
||||
import re
|
||||
|
||||
# Import the BasicNewsRecipe class which this class extends.
|
||||
from calibre import prepare_string_for_xml
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
|
||||
|
||||
def classes(classes):
|
||||
q = frozenset(classes.split(' '))
|
||||
return dict(attrs={
|
||||
'class': lambda x: x and frozenset(x.split()).intersection(q)})
|
||||
# Article JSON parser {{{
|
||||
def serialize_image(block):
|
||||
yield '<div>'
|
||||
block = block['model']
|
||||
media = block['media']
|
||||
alt = prepare_string_for_xml(media.get('alt') or '', True)
|
||||
src = prepare_string_for_xml(media['src'])
|
||||
yield '<img src="{}" alt="{}"/>'.format(src, alt)
|
||||
caption = block.get('caption')
|
||||
if caption:
|
||||
yield '<div>{}</div>'.format(prepare_string_for_xml(caption))
|
||||
yield '</div>'
|
||||
|
||||
|
||||
def block_tag(name, generator):
|
||||
yield '<' + name + '>'
|
||||
yield from generator
|
||||
yield '</' + name + '>'
|
||||
|
||||
|
||||
def serialize_paragraph(block):
|
||||
block = block['model']
|
||||
for x in block['blocks']:
|
||||
xt = x['type']
|
||||
if xt == 'fragment':
|
||||
styles = []
|
||||
model = x['model']
|
||||
for attr in model['attributes']:
|
||||
if attr == 'bold':
|
||||
styles.append('font-weight: bold')
|
||||
elif attr in ('italic', 'italics'):
|
||||
styles.append('font-style: italic')
|
||||
if styles:
|
||||
prefix = '<span style="{}">'.format('; '.join(styles))
|
||||
suffix = '</span>'
|
||||
else:
|
||||
prefix = suffix = ''
|
||||
yield prefix + prepare_string_for_xml(model['text']) + suffix
|
||||
elif xt == 'urlLink':
|
||||
model = x['model']
|
||||
yield '<a href="{}">{}</a>'.format(prepare_string_for_xml(model['locator'], True), prepare_string_for_xml(model['text']))
|
||||
|
||||
|
||||
def serialize_list(block):
|
||||
for x in block['model']['blocks']:
|
||||
if x['type'] == 'listItem':
|
||||
yield from block_tag('li', serialize_paragraph(x))
|
||||
|
||||
|
||||
def serialize_text(block):
|
||||
block = block['model']
|
||||
for x in block['blocks']:
|
||||
xt = x['type']
|
||||
if xt == 'paragraph':
|
||||
yield from block_tag('p', serialize_paragraph(x))
|
||||
elif xt == 'unorderedList':
|
||||
yield from block_tag('ul', serialize_list(x))
|
||||
elif xt == 'orderedList':
|
||||
yield from block_tag('ol', serialize_list(x))
|
||||
else:
|
||||
raise KeyError('Unknown block type: ' + x['type'])
|
||||
|
||||
|
||||
def serialize_contributor(contributor):
|
||||
if 'title' in contributor:
|
||||
yield '<h3>' + prepare_string_for_xml(contributor['title']) + '</h3>'
|
||||
if 'subtitle' in contributor:
|
||||
yield '<div>' + prepare_string_for_xml(contributor['subtitle']) + '</div>'
|
||||
|
||||
|
||||
def parse_article_json(root, abort_article):
|
||||
data = root['data']
|
||||
has_media_experience = False
|
||||
for key in data:
|
||||
if key.startswith('article?'):
|
||||
article = data[key]['data']
|
||||
break
|
||||
elif key.startswith('media-experience?'):
|
||||
has_media_experience = True
|
||||
else:
|
||||
if has_media_experience:
|
||||
abort_article('Skipping video article')
|
||||
return
|
||||
raise KeyError('No article found in data keys: {}'.format(data.keys()))
|
||||
lines = []
|
||||
if article.get('headline'):
|
||||
lines.append('<h1>{}</h1>'.format(prepare_string_for_xml(article['headline'])))
|
||||
if article.get('contributor'):
|
||||
lines.extend(serialize_contributor(article['contributor']))
|
||||
for block in article['blocks']:
|
||||
bt = block.get('type')
|
||||
if bt == 'image':
|
||||
lines.extend(serialize_image(block))
|
||||
elif bt == 'text':
|
||||
lines.extend(serialize_text(block))
|
||||
return '<html><body id="main-content">' + '\n'.join(lines) + '</body></html>'
|
||||
# }}}
|
||||
|
||||
|
||||
class BBCNews(BasicNewsRecipe):
|
||||
|
||||
#
|
||||
# **** IMPORTANT USERS READ ME ****
|
||||
#
|
||||
# First select the feeds you want then scroll down below the feeds list
|
||||
# and select the values you want for the other user preferences, like
|
||||
# oldest_article and such like.
|
||||
#
|
||||
#
|
||||
# Select the BBC rss feeds which you want in your ebook.
|
||||
# Selected feed have NO '#' at their start, de-selected feeds begin with a '#'.
|
||||
#
|
||||
# Eg. ("News Home", "https://feeds.bbci.co.uk/... - include feed.
|
||||
# Eg. #("News Home", "https://feeds.bbci.co.uk/... - do not include feed.
|
||||
#
|
||||
# There are 68 feeds below which constitute the bulk of the available rss
|
||||
# feeds on the BBC web site. These include 5 blogs by editors and
|
||||
# correspondents, 16 sports feeds, 15 'sub' regional feeds (Eg. North West
|
||||
# Wales, Scotland Business), and 7 Welsh language feeds.
|
||||
#
|
||||
# Some of the feeds are low volume (Eg. blogs), or very low volume (Eg. Click)
|
||||
# so if "oldest_article = 1.5" (only articles published in the last 36 hours)
|
||||
# you may get some 'empty feeds' which will not then be included in the ebook.
|
||||
#
|
||||
# The 15 feeds currently selected below are simply my default ones.
|
||||
#
|
||||
# Note: With all 68 feeds selected, oldest_article set to 2,
|
||||
# max_articles_per_feed set to 100, and simultaneous_downloads set to 10,
|
||||
# the ebook creation took 29 minutes on my speedy 100 mbps net connection,
|
||||
# fairly high-end desktop PC running Linux (Ubuntu Lucid-Lynx).
|
||||
# More realistically with 15 feeds selected, oldest_article set to 1.5,
|
||||
# max_articles_per_feed set to 100, and simultaneous_downloads set to 20,
|
||||
# it took 6 minutes. If that's too slow increase 'simultaneous_downloads'.
|
||||
#
|
||||
# Select / de-select the feeds you want in your ebook.
|
||||
#
|
||||
feeds = [
|
||||
("News Home", "https://feeds.bbci.co.uk/news/rss.xml"),
|
||||
("UK", "https://feeds.bbci.co.uk/news/uk/rss.xml"),
|
||||
@ -175,11 +218,6 @@ class BBCNews(BasicNewsRecipe):
|
||||
#
|
||||
simultaneous_downloads = 20
|
||||
|
||||
# Timeout for fetching files from the server in seconds. The default of
|
||||
# 120 seconds, seems somewhat excessive.
|
||||
#
|
||||
timeout = 30
|
||||
|
||||
# The format string for the date shown on the ebook's first page.
|
||||
# List of all values: https://docs.python.org/library/time.html
|
||||
# Default in news.py has a leading space so that's mirrored here.
|
||||
@ -208,29 +246,14 @@ class BBCNews(BasicNewsRecipe):
|
||||
#
|
||||
|
||||
# Author of this recipe.
|
||||
__author__ = 'mattst'
|
||||
__author__ = 'Kovid Goyal'
|
||||
|
||||
# Specify English as the language of the RSS feeds (ISO-639 code).
|
||||
language = 'en_GB'
|
||||
|
||||
# Set tags.
|
||||
tags = 'news, sport, blog'
|
||||
|
||||
# Set publisher and publication type.
|
||||
publisher = 'BBC'
|
||||
publication_type = 'newspaper'
|
||||
|
||||
# Disable stylesheets from site.
|
||||
no_stylesheets = True
|
||||
|
||||
# Specifies an override encoding for sites that have an incorrect charset
|
||||
# specified. Default of 'None' says to auto-detect. Some other BBC recipes
|
||||
# use 'utf8', which works fine (so use that if necessary) but auto-detecting
|
||||
# with None is working fine, so stick with that for robustness.
|
||||
encoding = None
|
||||
|
||||
# Sets whether a feed has full articles embedded in it. The BBC feeds do
|
||||
# not.
|
||||
encoding = 'utf-8'
|
||||
use_embedded_content = False
|
||||
|
||||
# Removes empty feeds - why keep them!?
|
||||
@ -238,473 +261,13 @@ class BBCNews(BasicNewsRecipe):
|
||||
ignore_duplicate_articles = {'title', 'url'}
|
||||
resolve_internal_links = True
|
||||
|
||||
# Create a custom title which fits nicely in the Kindle title list.
|
||||
# Requires "import time" above class declaration, and replacing
|
||||
# title with custom_title in conversion_options (right column only).
|
||||
# Example of string below: "BBC News - 14 Nov 2011"
|
||||
#
|
||||
# custom_title = "BBC News - " + time.strftime('%d %b %Y')
|
||||
|
||||
# Conversion options for advanced users. Avoid setting 'linearize_tables'
|
||||
# as that plays havoc with the 'old style' table based pages.
|
||||
conversion_options = {
|
||||
# 'title' : title,
|
||||
# 'comments' : description,
|
||||
# 'tags' : tags,
|
||||
# 'language' : language,
|
||||
# 'publisher' : publisher,
|
||||
# 'authors' : publisher,
|
||||
'smarten_punctuation' : True
|
||||
}
|
||||
|
||||
# Specify extra CSS - overrides ALL other CSS (IE. Added last).
|
||||
extra_css = 'body { font-family: verdana, helvetica, sans-serif; } \
|
||||
.introduction, .first { font-weight: bold; } \
|
||||
.cross-head { font-weight: bold; font-size: 125%; } \
|
||||
.cap, .caption { display: block; font-size: 80%; font-style: italic; } \
|
||||
.cap, .caption, .caption img, .caption span { display: block; text-align: center; margin: 5px auto; } \
|
||||
.byl, .byd, .byline img, .byline-name, .byline-title, .author-name, .author-position, \
|
||||
.correspondent-portrait img, .byline-lead-in, .name, .bbc-role { display: block; \
|
||||
text-align: center; font-size: 80%; font-style: italic; margin: 1px auto; } \
|
||||
.story-date, .published { font-size: 80%; } \
|
||||
table { width: 100%; } \
|
||||
td img { display: block; margin: 5px auto; } \
|
||||
ul { padding-top: 10px; } \
|
||||
ol { padding-top: 10px; } \
|
||||
li { padding-top: 5px; padding-bottom: 5px; } \
|
||||
h1 { text-align: center; font-size: 175%; font-weight: bold; } \
|
||||
h2 { text-align: center; font-size: 150%; font-weight: bold; } \
|
||||
h3 { text-align: center; font-size: 125%; font-weight: bold; } \
|
||||
h4, h5, h6 { text-align: center; font-size: 100%; font-weight: bold; }'
|
||||
|
||||
# Remove various tag attributes to improve the look of the ebook pages.
|
||||
remove_attributes = ['border', 'cellspacing', 'align', 'cellpadding', 'colspan',
|
||||
'valign', 'vspace', 'hspace', 'alt', 'width', 'height']
|
||||
|
||||
# Remove the (admittedly rarely used) line breaks, "<br />", which sometimes
|
||||
# cause a section of the ebook to start in an unsightly fashion or, more
|
||||
# frequently, a "<br />" will muck up the formatting of a correspondant's byline.
|
||||
# "<br />" and "<br clear/>" are far more frequently used on the table formatted
|
||||
# style of pages, and really spoil the look of the ebook pages.
|
||||
preprocess_regexps = [(re.compile(r'<br[ ]*/>', re.IGNORECASE), lambda m: ''),
|
||||
(re.compile(r'<br[ ]*clear.*/>', re.IGNORECASE), lambda m: '')]
|
||||
|
||||
# Create regular expressions for tag keeping and removal to make the matches more
|
||||
# robust against minor changes and errors in the HTML, Eg. double spaces, leading
|
||||
# and trailing spaces, missing hyphens, and such like.
|
||||
# Python regular expression ('re' class) page:
|
||||
# https://docs.python.org/library/re.html
|
||||
|
||||
# ***************************************
|
||||
# Regular expressions for keep_only_tags:
|
||||
# ***************************************
|
||||
|
||||
# The BBC News HTML pages use variants of 'storybody' to denote the section of a HTML
|
||||
# page which contains the main text of the article. Match storybody variants: 'storybody',
|
||||
# 'story-body', 'story body','storybody ', etc.
|
||||
storybody_reg_exp = '^.*story[_ -]*body.*$'
|
||||
|
||||
# The BBC sport and 'newsbeat' (features) HTML pages use 'blq_content' to hold the title
|
||||
# and published date. This is one level above the usual news pages which have the title
|
||||
# and date within 'story-body'. This is annoying since 'blq_content' must also be kept,
|
||||
# resulting in a lot of extra things to be removed by remove_tags.
|
||||
blq_content_reg_exp = '^.*blq[_ -]*content.*$'
|
||||
|
||||
# The BBC has an alternative page design structure, which I suspect is an out-of-date
|
||||
# design but which is still used in some articles, Eg. 'Click' (technology), 'FastTrack'
|
||||
# (travel), and in some sport pages. These alternative pages are table based (which is
|
||||
# why I think they are an out-of-date design) and account for -I'm guesstimaking- less
|
||||
# than 1% of all articles. They use a table class 'storycontent' to hold the article
|
||||
# and like blq_content (above) have required lots of extra removal by
|
||||
# remove_tags.
|
||||
story_content_reg_exp = '^.*story[_ -]*content.*$'
|
||||
|
||||
# Keep the sections of the HTML which match the list below. The HTML page created by
|
||||
# Calibre will fill <body> with those sections which are matched. Note that the
|
||||
# blq_content_reg_exp must be listed before storybody_reg_exp in keep_only_tags due to
|
||||
# it being the parent of storybody_reg_exp, that is to say the div class/id 'story-body'
|
||||
# will be inside div class/id 'blq_content' in the HTML (if 'blq_content' is there at
|
||||
# all). If they are the other way around in keep_only_tags then blq_content_reg_exp
|
||||
# will end up being discarded.
|
||||
keep_only_tags = [dict(name='table', attrs={'class': re.compile(story_content_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
blq_content_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'id': re.compile(
|
||||
blq_content_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
storybody_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'id': re.compile(storybody_reg_exp, re.IGNORECASE)})]
|
||||
|
||||
# ************************************
|
||||
# Regular expressions for remove_tags:
|
||||
# ************************************
|
||||
|
||||
# Regular expression to remove share-help and variant tags. The share-help class
|
||||
# is used by the site for a variety of 'sharing' type links, Eg. Facebook, delicious,
|
||||
# twitter, email. Removed to avoid page clutter.
|
||||
share_help_reg_exp = '^.*share[_ -]*help.*$'
|
||||
|
||||
# Regular expression to remove embedded-hyper and variant tags. This class is used to
|
||||
# display links to other BBC News articles on the same/similar subject.
|
||||
embedded_hyper_reg_exp = '^.*embed*ed[_ -]*hyper.*$'
|
||||
|
||||
# Regular expression to remove hypertabs and variant tags. This class is used to
|
||||
# display a tab bar at the top of an article which allows the user to switch to
|
||||
# an article (viewed on the same page) providing further info., 'in depth' analysis,
|
||||
# an editorial, a correspondant's blog entry, and such like. The ability to handle
|
||||
# a tab bar of this nature is currently beyond the scope of this recipe and
|
||||
# possibly of Calibre itself (not sure about that - TO DO - check!).
|
||||
hypertabs_reg_exp = '^.*hyper[_ -]*tabs.*$'
|
||||
|
||||
# Regular expression to remove story-feature and variant tags. Eg. 'story-feature',
|
||||
# 'story-feature related narrow', 'story-feature wide', 'story-feature narrow'.
|
||||
# This class is used to add additional info. boxes, or small lists, outside of
|
||||
# the main story. TO DO: Work out a way to incorporate these neatly.
|
||||
story_feature_reg_exp = '^.*story[_ -]*feature.*$'
|
||||
|
||||
# Regular expression to remove video and variant tags, Eg. 'videoInStoryB',
|
||||
# 'videoInStoryC'. This class is used to embed video.
|
||||
video_reg_exp = '^.*video.*$'
|
||||
|
||||
# Regular expression to remove audio and variant tags, Eg. 'audioInStoryD'.
|
||||
# This class is used to embed audio.
|
||||
audio_reg_exp = '^.*audio.*$'
|
||||
|
||||
# Regular expression to remove pictureGallery and variant tags, Eg. 'pictureGallery'.
|
||||
# This class is used to embed a photo slideshow. See also 'slideshow'
|
||||
# below.
|
||||
picture_gallery_reg_exp = '^.*picture.*$'
|
||||
|
||||
# Regular expression to remove slideshow and variant tags, Eg. 'dslideshow-enclosure'.
|
||||
# This class is used to embed a slideshow (not necessarily photo) but both
|
||||
# 'slideshow' and 'pictureGallery' are used for slideshows.
|
||||
slideshow_reg_exp = '^.*slide[_ -]*show.*$'
|
||||
|
||||
# Regular expression to remove social-links and variant tags. This class is used to
|
||||
# display links to a BBC bloggers main page, used in various columnist's blogs
|
||||
# (Eg. Nick Robinson, Robert Preston).
|
||||
social_links_reg_exp = '^.*social[_ -]*links.*$'
|
||||
|
||||
# Regular expression to remove quote and (multi) variant tags, Eg. 'quote',
|
||||
# 'endquote', 'quote-credit', 'quote-credit-title', etc. These are usually
|
||||
# removed by 'story-feature' removal (as they are usually within them), but
|
||||
# not always. The quotation removed is always (AFAICT) in the article text
|
||||
# as well but a 2nd copy is placed in a quote tag to draw attention to it.
|
||||
# The quote class tags may or may not appear in div's.
|
||||
quote_reg_exp = '^.*quote.*$'
|
||||
|
||||
# Regular expression to remove hidden and variant tags, Eg. 'hidden'.
|
||||
# The purpose of these is unclear, they seem to be an internal link to a
|
||||
# section within the article, but the text of the link (Eg. 'Continue reading
|
||||
# the main story') never seems to be displayed anyway. Removed to avoid clutter.
|
||||
# The hidden class tags may or may not appear in div's.
|
||||
hidden_reg_exp = '^.*hidden.*$'
|
||||
|
||||
# Regular expression to remove comment and variant tags, Eg. 'comment-introduction'.
|
||||
# Used on the site to display text about registered users entering
|
||||
# comments.
|
||||
comment_reg_exp = '^.*comment.*$'
|
||||
|
||||
# Regular expression to remove form and variant tags, Eg. 'comment-form'.
|
||||
# Used on the site to allow registered BBC users to fill in forms, typically
|
||||
# for entering comments about an article.
|
||||
form_reg_exp = '^.*form.*$'
|
||||
|
||||
# Extra things to remove due to the addition of 'blq_content' in
|
||||
# keep_only_tags.
|
||||
|
||||
# <div class="story-actions"> Used on sports pages for 'email' and 'print'.
|
||||
story_actions_reg_exp = '^.*story[_ -]*actions.*$'
|
||||
|
||||
# <div class="bookmark-list"> Used on sports pages instead of 'share-help' (for
|
||||
# social networking links).
|
||||
bookmark_list_reg_exp = '^.*bookmark[_ -]*list.*$'
|
||||
|
||||
# <div id="secondary-content" class="content-group">
|
||||
# NOTE: Don't remove class="content-group" that is needed.
|
||||
# Used on sports pages to link to 'similar stories'.
|
||||
secondary_content_reg_exp = '^.*secondary[_ -]*content.*$'
|
||||
|
||||
# <div id="featured-content" class="content-group">
|
||||
# NOTE: Don't remove class="content-group" that is needed.
|
||||
# Used on sports pages to link to pages like 'tables', 'fixtures', etc.
|
||||
featured_content_reg_exp = '^.*featured[_ -]*content.*$'
|
||||
|
||||
# <div id="navigation">
|
||||
# Used on sports pages to link to pages like 'tables', 'fixtures', etc.
|
||||
# Used sometimes instead of "featured-content" above.
|
||||
navigation_reg_exp = '^.*navigation.*$'
|
||||
|
||||
# <a class="skip" href="#blq-container-inner">Skip to top</a>
|
||||
# Used on sports pages to link to the top of the page.
|
||||
skip_reg_exp = '^.*skip.*$'
|
||||
|
||||
# Extra things to remove due to the addition of 'storycontent' in keep_only_tags,
|
||||
# which are the alterative table design based pages. The purpose of some of these
|
||||
# is not entirely clear from the pages (which are a total mess!).
|
||||
|
||||
# Remove mapping based tags, Eg. <map id="world_map">
|
||||
# The dynamic maps don't seem to work during ebook creation. TO DO:
|
||||
# Investigate.
|
||||
map_reg_exp = '^.*map.*$'
|
||||
|
||||
# Remove social bookmarking variation, called 'socialBookMarks'.
|
||||
social_bookmarks_reg_exp = '^.*social[_ -]*bookmarks.*$'
|
||||
|
||||
# Remove page navigation tools, like 'search', 'email', 'print', called
|
||||
# 'blq-mast'.
|
||||
blq_mast_reg_exp = '^.*blq[_ -]*mast.*$'
|
||||
|
||||
# Remove 'sharesb', I think this is a generic 'sharing' class. It seems to appear
|
||||
# alongside 'socialBookMarks' whenever that appears. I am removing it as well
|
||||
# under the assumption that it can appear alone as well.
|
||||
sharesb_reg_exp = '^.*sharesb.*$'
|
||||
|
||||
# Remove class 'o'. The worst named user created css class of all time. The creator
|
||||
# should immediately be fired. I've seen it used to hold nothing at all but with
|
||||
# 20 or so empty lines in it. Also to hold a single link to another article.
|
||||
# Whatever it was designed to do it is not wanted by this recipe. Exact
|
||||
# match only.
|
||||
o_reg_exp = '^o$'
|
||||
|
||||
# Remove 'promotopbg' and 'promobottombg', link lists. Have decided to
|
||||
# use two reg expressions to make removing this (and variants) robust.
|
||||
promo_top_reg_exp = '^.*promotopbg.*$'
|
||||
promo_bottom_reg_exp = '^.*promobottombg.*$'
|
||||
|
||||
# Remove 'nlp', provides heading for link lists. Requires an exact match due to
|
||||
# risk of matching those letters in something needed, unless I see a variation
|
||||
# of 'nlp' used at a later date.
|
||||
nlp_reg_exp = '^nlp$'
|
||||
|
||||
# Remove 'mva', provides embedded floating content of various types. Variant 'mvb'
|
||||
# has also now been seen. Requires an exact match of 'mva' or 'mvb' due to risk of
|
||||
# matching those letters in something needed.
|
||||
mva_or_mvb_reg_exp = '^mv[ab]$'
|
||||
|
||||
# Remove 'mvtb', seems to be page navigation tools, like 'blq-mast'.
|
||||
mvtb_reg_exp = '^mvtb$'
|
||||
|
||||
# Remove 'blq-toplink', class to provide a link to the top of the page.
|
||||
blq_toplink_reg_exp = '^.*blq[_ -]*top[_ -]*link.*$'
|
||||
|
||||
# Remove 'products and services' links, Eg. desktop tools, alerts, and so on.
|
||||
# Eg. Class="servicev4 ukfs_services" - what a mess of a name. Have decided to
|
||||
# use two reg expressions to make removing this (and variants) robust.
|
||||
prods_services_01_reg_exp = '^.*servicev4.*$'
|
||||
prods_services_02_reg_exp = '^.*ukfs[_ -]*services.*$'
|
||||
|
||||
# Remove -what I think is- some kind of navigation tools helper class, though I am
|
||||
# not sure, it's called: 'blq-rst blq-new-nav'. What I do know is it pops up
|
||||
# frequently and it is not wanted. Have decided to use two reg expressions to make
|
||||
# removing this (and variants) robust.
|
||||
blq_misc_01_reg_exp = '^.*blq[_ -]*rst.*$'
|
||||
blq_misc_02_reg_exp = '^.*blq[_ -]*new[_ -]*nav.*$'
|
||||
|
||||
# Remove 'puffbox' - this may only appear inside 'storyextra', so it may not
|
||||
# need removing - I have no clue what it does other than it contains links.
|
||||
# Whatever it is - it is not part of the article and is not wanted.
|
||||
puffbox_reg_exp = '^.*puffbox.*$'
|
||||
|
||||
# Remove 'sibtbg' and 'sibtbgf' - some kind of table formatting classes.
|
||||
sibtbg_reg_exp = '^.*sibtbg.*$'
|
||||
|
||||
# Remove 'storyextra' - links to relevant articles and external sites.
|
||||
storyextra_reg_exp = '^.*story[_ -]*extra.*$'
|
||||
|
||||
remove_tags = [
|
||||
classes('sharetools share-tools--no-event-tag'),
|
||||
dict(name='div', attrs={'class': re.compile(story_feature_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
share_help_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
embedded_hyper_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
hypertabs_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
video_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
audio_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
picture_gallery_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
slideshow_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
quote_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
hidden_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
comment_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
story_actions_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
bookmark_list_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'id': re.compile(
|
||||
secondary_content_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'id': re.compile(
|
||||
featured_content_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'id': re.compile(
|
||||
navigation_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='form', attrs={'id': re.compile(
|
||||
form_reg_exp, re.IGNORECASE)}),
|
||||
dict(attrs={'class': re.compile(
|
||||
quote_reg_exp, re.IGNORECASE)}),
|
||||
dict(attrs={'class': re.compile(
|
||||
hidden_reg_exp, re.IGNORECASE)}),
|
||||
dict(attrs={'class': re.compile(
|
||||
social_links_reg_exp, re.IGNORECASE)}),
|
||||
dict(attrs={'class': re.compile(
|
||||
comment_reg_exp, re.IGNORECASE)}),
|
||||
dict(attrs={'class': re.compile(
|
||||
skip_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='map', attrs={'id': re.compile(
|
||||
map_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='map', attrs={'name': re.compile(
|
||||
map_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'id': re.compile(
|
||||
social_bookmarks_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'id': re.compile(
|
||||
blq_mast_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
sharesb_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={
|
||||
'class': re.compile(o_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
promo_top_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
promo_bottom_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={
|
||||
'class': re.compile(nlp_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
mva_or_mvb_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
mvtb_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
blq_toplink_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
prods_services_01_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
prods_services_02_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
blq_misc_01_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
blq_misc_02_reg_exp, re.IGNORECASE)}),
|
||||
dict(name='div', attrs={'class': re.compile(
|
||||
puffbox_reg_exp, re.IGNORECASE)}),
|
||||
dict(attrs={'class': re.compile(
|
||||
sibtbg_reg_exp, re.IGNORECASE)}),
|
||||
dict(attrs={'class': re.compile(
|
||||
storyextra_reg_exp, re.IGNORECASE)})
|
||||
]
|
||||
|
||||
# Uses url to create and return the 'printer friendly' version of the url.
|
||||
# In other words the 'print this page' address of the page.
|
||||
#
|
||||
# There are 3 types of urls used in the BBC site's rss feeds. There is just
|
||||
# 1 type for the standard news while there are 2 used for sports feed urls.
|
||||
# Note: Sports urls are linked from regular news feeds (Eg. 'News Home') when
|
||||
# there is a major story of interest to 'everyone'. So even if no BBC sports
|
||||
# feeds are added to 'feeds' the logic of this method is still needed to avoid
|
||||
# blank / missing / empty articles which have an index title and then no
|
||||
# body.
|
||||
def print_version(self, url):
|
||||
if url.startswith("https://www.bbc.co.uk/news/world-51235105"):
|
||||
self.abort_article("This article contains a gigantic coronavirus table")
|
||||
|
||||
# Handle sports page urls type 01:
|
||||
if (url.find("go/rss/-/sport1/") != -1):
|
||||
temp_url = url.replace("go/rss/-/", "")
|
||||
|
||||
# Handle sports page urls type 02:
|
||||
elif (url.find("go/rss/int/news/-/sport1/") != -1):
|
||||
temp_url = url.replace("go/rss/int/news/-/", "")
|
||||
|
||||
# Handle regular news page urls:
|
||||
else:
|
||||
temp_url = url.replace("go/rss/int/news/-/", "")
|
||||
|
||||
# Always add "?print=true" to the end of the url.
|
||||
print_url = temp_url + "?print=true"
|
||||
|
||||
return print_url
|
||||
|
||||
def canonicalize_internal_url(self, url, is_link=True):
|
||||
if url.endswith('?print=true'):
|
||||
url = url.rpartition('?')[0]
|
||||
return BasicNewsRecipe.canonicalize_internal_url(self, url, is_link=is_link)
|
||||
|
||||
# Remove articles in feeds based on a string in the article title or url.
|
||||
#
|
||||
# Code logic written by: Starson17 - posted in: "Recipes - Re-usable code"
|
||||
# thread, in post with title: "Remove articles from feed", see url:
|
||||
# https://www.mobileread.com/forums/showpost.php?p=1165462&postcount=6
|
||||
# Many thanks and all credit to Starson17.
|
||||
#
|
||||
# Starson17's code has obviously been altered to suite my requirements.
|
||||
def parse_feeds(self):
|
||||
|
||||
# Call parent's method.
|
||||
feeds = BasicNewsRecipe.parse_feeds(self)
|
||||
|
||||
# Loop through all feeds.
|
||||
for feed in feeds:
|
||||
|
||||
# Loop through all articles in feed.
|
||||
for article in feed.articles[:]:
|
||||
|
||||
# Match key words and remove article if there's a match.
|
||||
|
||||
# Most BBC rss feed video only 'articles' use upper case 'VIDEO'
|
||||
# as a title prefix. Just match upper case 'VIDEO', so that
|
||||
# articles like 'Video game banned' won't be matched and
|
||||
# removed.
|
||||
if 'VIDEO' in article.title:
|
||||
feed.articles.remove(article)
|
||||
|
||||
# Most BBC rss feed audio only 'articles' use upper case 'AUDIO'
|
||||
# as a title prefix. Just match upper case 'AUDIO', so that
|
||||
# articles like 'Hi-Def audio...' won't be matched and removed.
|
||||
elif 'AUDIO' in article.title:
|
||||
feed.articles.remove(article)
|
||||
|
||||
# Most BBC rss feed photo slideshow 'articles' use 'In Pictures',
|
||||
# 'In pictures', and 'in pictures', somewhere in their title.
|
||||
# Match any case of that phrase.
|
||||
elif 'IN PICTURES' in article.title.upper():
|
||||
feed.articles.remove(article)
|
||||
|
||||
# As above, but user contributed pictures. Match any case.
|
||||
elif 'YOUR PICTURES' in article.title.upper():
|
||||
feed.articles.remove(article)
|
||||
|
||||
# 'Sportsday Live' are articles which contain a constantly and
|
||||
# dynamically updated 'running commentary' during a live sporting
|
||||
# event. Match any case.
|
||||
elif 'SPORTSDAY LIVE' in article.title.upper():
|
||||
feed.articles.remove(article)
|
||||
|
||||
# Sometimes 'Sportsday Live' (above) becomes 'Live - Sport Name'.
|
||||
# These are being matched below using 'Live - ' because removing all
|
||||
# articles with 'live' in their titles would remove some articles
|
||||
# that are in fact not live sports pages. Match any case.
|
||||
elif 'LIVE - ' in article.title.upper():
|
||||
feed.articles.remove(article)
|
||||
|
||||
# 'Quiz of the week' is a Flash player weekly news quiz. Match only
|
||||
# the 'Quiz of the' part in anticipation of monthly and yearly
|
||||
# variants. Match any case.
|
||||
elif 'QUIZ OF THE' in article.title.upper():
|
||||
feed.articles.remove(article)
|
||||
|
||||
# Remove articles with 'scorecards' in the url. These are BBC sports
|
||||
# pages which just display a cricket scorecard. The pages have a mass
|
||||
# of table and css entries to display the scorecards nicely. Probably
|
||||
# could make them work with this recipe, but might take a whole day
|
||||
# of work to sort out all the css - basically a formatting
|
||||
# nightmare.
|
||||
elif 'scorecards' in article.url:
|
||||
feed.articles.remove(article)
|
||||
|
||||
return feeds
|
||||
|
||||
# End of class and file.
|
||||
def preprocess_raw_html(self, raw_html, url):
|
||||
q = '>window.__INITIAL_DATA__={'
|
||||
idx = raw_html.find(q)
|
||||
if idx < 0:
|
||||
raise ValueError('Failed to find JSON')
|
||||
data = raw_html[idx + len(q) - 1:]
|
||||
idx = data.find('};</script>')
|
||||
data = data[:idx+1]
|
||||
root = json.loads(data)
|
||||
return parse_article_json(root, self.abort_article)
|
||||
|
||||
@ -1,14 +1,115 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010 - 2011, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
news.bbc.co.uk
|
||||
'''
|
||||
#!/usr/bin/env python
|
||||
# vim:fileencoding=utf-8
|
||||
# License: GPLv3 Copyright: 2020, Kovid Goyal <kovid at kovidgoyal.net>
|
||||
|
||||
import json
|
||||
|
||||
from calibre import prepare_string_for_xml
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
|
||||
|
||||
# Article JSON parser {{{
|
||||
def serialize_image(block):
|
||||
yield '<div>'
|
||||
block = block['model']
|
||||
media = block['media']
|
||||
alt = prepare_string_for_xml(media.get('alt') or '', True)
|
||||
src = prepare_string_for_xml(media['src'])
|
||||
yield '<img src="{}" alt="{}"/>'.format(src, alt)
|
||||
caption = block.get('caption')
|
||||
if caption:
|
||||
yield '<div>{}</div>'.format(prepare_string_for_xml(caption))
|
||||
yield '</div>'
|
||||
|
||||
|
||||
def block_tag(name, generator):
|
||||
yield '<' + name + '>'
|
||||
yield from generator
|
||||
yield '</' + name + '>'
|
||||
|
||||
|
||||
def serialize_paragraph(block):
|
||||
block = block['model']
|
||||
for x in block['blocks']:
|
||||
xt = x['type']
|
||||
if xt == 'fragment':
|
||||
styles = []
|
||||
model = x['model']
|
||||
for attr in model['attributes']:
|
||||
if attr == 'bold':
|
||||
styles.append('font-weight: bold')
|
||||
elif attr in ('italic', 'italics'):
|
||||
styles.append('font-style: italic')
|
||||
if styles:
|
||||
prefix = '<span style="{}">'.format('; '.join(styles))
|
||||
suffix = '</span>'
|
||||
else:
|
||||
prefix = suffix = ''
|
||||
yield prefix + prepare_string_for_xml(model['text']) + suffix
|
||||
elif xt == 'urlLink':
|
||||
model = x['model']
|
||||
yield '<a href="{}">{}</a>'.format(prepare_string_for_xml(model['locator'], True), prepare_string_for_xml(model['text']))
|
||||
|
||||
|
||||
def serialize_list(block):
|
||||
for x in block['model']['blocks']:
|
||||
if x['type'] == 'listItem':
|
||||
yield from block_tag('li', serialize_paragraph(x))
|
||||
|
||||
|
||||
def serialize_text(block):
|
||||
block = block['model']
|
||||
for x in block['blocks']:
|
||||
xt = x['type']
|
||||
if xt == 'paragraph':
|
||||
yield from block_tag('p', serialize_paragraph(x))
|
||||
elif xt == 'unorderedList':
|
||||
yield from block_tag('ul', serialize_list(x))
|
||||
elif xt == 'orderedList':
|
||||
yield from block_tag('ol', serialize_list(x))
|
||||
else:
|
||||
raise KeyError('Unknown block type: ' + x['type'])
|
||||
|
||||
|
||||
def serialize_contributor(contributor):
|
||||
if 'title' in contributor:
|
||||
yield '<h3>' + prepare_string_for_xml(contributor['title']) + '</h3>'
|
||||
if 'subtitle' in contributor:
|
||||
yield '<div>' + prepare_string_for_xml(contributor['subtitle']) + '</div>'
|
||||
|
||||
|
||||
def parse_article_json(root, abort_article):
|
||||
data = root['data']
|
||||
has_media_experience = False
|
||||
for key in data:
|
||||
if key.startswith('article?'):
|
||||
article = data[key]['data']
|
||||
break
|
||||
elif key.startswith('media-experience?'):
|
||||
has_media_experience = True
|
||||
else:
|
||||
if has_media_experience:
|
||||
abort_article('Skipping video article')
|
||||
return
|
||||
raise KeyError('No article found in data keys: {}'.format(data.keys()))
|
||||
lines = []
|
||||
if article.get('headline'):
|
||||
lines.append('<h1>{}</h1>'.format(prepare_string_for_xml(article['headline'])))
|
||||
if article.get('contributor'):
|
||||
lines.extend(serialize_contributor(article['contributor']))
|
||||
for block in article['blocks']:
|
||||
bt = block.get('type')
|
||||
if bt == 'image':
|
||||
lines.extend(serialize_image(block))
|
||||
elif bt == 'text':
|
||||
lines.extend(serialize_text(block))
|
||||
return '<html><body id="main-content">' + '\n'.join(lines) + '</body></html>'
|
||||
# }}}
|
||||
|
||||
|
||||
class BBC(BasicNewsRecipe):
|
||||
title = 'BBC News (fast)'
|
||||
__author__ = 'Darko Miletic, Starson17'
|
||||
__author__ = 'Kovid Goyal'
|
||||
description = 'Visit BBC News for up-to-the-minute news, breaking news, video, audio and feature stories. BBC News provides trusted World and UK news as well as local and regional perspectives. Also entertainment, business, science, technology and health news.' # noqa
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
@ -18,62 +119,38 @@ class BBC(BasicNewsRecipe):
|
||||
publisher = 'BBC'
|
||||
category = 'news, UK, world'
|
||||
language = 'en_GB'
|
||||
publication_type = 'newsportal'
|
||||
masthead_url = 'http://news.bbcimg.co.uk/img/1_0_1/cream/hi/news/news-blocks.gif'
|
||||
extra_css = """
|
||||
body{ font-family: Verdana,Helvetica,Arial,sans-serif }
|
||||
.introduction{font-weight: bold}
|
||||
.story-feature{display: block; padding: 0; border: 1px solid; width: 40%; font-size: small}
|
||||
.story-feature h2{text-align: center; text-transform: uppercase}
|
||||
"""
|
||||
masthead_url = 'https://news.bbcimg.co.uk/img/1_0_1/cream/hi/news/news-blocks.gif'
|
||||
conversion_options = {
|
||||
'comments': description, 'tags': category, 'language': language, 'publisher': publisher, 'linearize_tables': True
|
||||
'comments': description, 'tags': category, 'language': language, 'publisher': publisher,
|
||||
}
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='div', attrs={'class': ['layout-block-a layout-block']}), dict(attrs={'class': [
|
||||
'story-body', 'storybody']}), dict(attrs={'id': ['meta-information', 'story-body']})
|
||||
]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class': ['story-feature related narrow',
|
||||
'share-help', 'embedded-hyper',
|
||||
'story-feature wide ',
|
||||
'story-feature narrow',
|
||||
'hidden', 'story-actions', 'embedded-hyper']}), dict(name=['img', 'meta', 'link', 'object', 'embed', 'iframe', 'base']), dict(attrs={'class': ['hidden', 'videoInStoryC']}), dict(attrs={'id': ['bbccom_sponsor_section', 'toggle-controls', 'toggle-images', 'toggle-title']}) ] # noqa
|
||||
|
||||
remove_attributes = ['width', 'height', 'xmlns:og', 'lang', 'clear']
|
||||
|
||||
feeds = [
|
||||
('Top Stories', 'http://feeds.bbci.co.uk/news/rss.xml'),
|
||||
('Top Stories', 'https://feeds.bbci.co.uk/news/rss.xml'),
|
||||
('Science/Environment',
|
||||
'http://feeds.bbci.co.uk/news/science_and_environment/rss.xml'),
|
||||
('Technology', 'http://feeds.bbci.co.uk/news/technology/rss.xml'),
|
||||
'https://feeds.bbci.co.uk/news/science_and_environment/rss.xml'),
|
||||
('Technology', 'https://feeds.bbci.co.uk/news/technology/rss.xml'),
|
||||
('Entertainment/Arts',
|
||||
'http://feeds.bbci.co.uk/news/entertainment_and_arts/rss.xml'),
|
||||
('Magazine', 'http://feeds.bbci.co.uk/news/magazine/rss.xml'),
|
||||
('Business', 'http://feeds.bbci.co.uk/news/business/rss.xml'),
|
||||
('Politics', 'http://feeds.bbci.co.uk/news/politics/rss.xml'),
|
||||
('Health', 'http://feeds.bbci.co.uk/news/health/rss.xml'),
|
||||
('US&Canada', 'http://feeds.bbci.co.uk/news/world/us_and_canada/rss.xml'),
|
||||
('Latin America', 'http://feeds.bbci.co.uk/news/world/latin_america/rss.xml'),
|
||||
('Europe', 'http://feeds.bbci.co.uk/news/world/europe/rss.xml'),
|
||||
('South Asia', 'http://feeds.bbci.co.uk/news/world/south_asia/rss.xml'),
|
||||
('England', 'http://feeds.bbci.co.uk/news/england/rss.xml'),
|
||||
('Asia-Pacific', 'http://feeds.bbci.co.uk/news/world/asia_pacific/rss.xml'),
|
||||
('Africa', 'http://feeds.bbci.co.uk/news/world/africa/rss.xml')
|
||||
'https://feeds.bbci.co.uk/news/entertainment_and_arts/rss.xml'),
|
||||
('Magazine', 'https://feeds.bbci.co.uk/news/magazine/rss.xml'),
|
||||
('Business', 'https://feeds.bbci.co.uk/news/business/rss.xml'),
|
||||
('Politics', 'https://feeds.bbci.co.uk/news/politics/rss.xml'),
|
||||
('Health', 'https://feeds.bbci.co.uk/news/health/rss.xml'),
|
||||
('US&Canada', 'https://feeds.bbci.co.uk/news/world/us_and_canada/rss.xml'),
|
||||
('Latin America', 'https://feeds.bbci.co.uk/news/world/latin_america/rss.xml'),
|
||||
('Europe', 'https://feeds.bbci.co.uk/news/world/europe/rss.xml'),
|
||||
('South Asia', 'https://feeds.bbci.co.uk/news/world/south_asia/rss.xml'),
|
||||
('England', 'https://feeds.bbci.co.uk/news/england/rss.xml'),
|
||||
('Asia-Pacific', 'https://feeds.bbci.co.uk/news/world/asia_pacific/rss.xml'),
|
||||
('Africa', 'https://feeds.bbci.co.uk/news/world/africa/rss.xml')
|
||||
]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
for item in soup.findAll('left'):
|
||||
item.name = 'span'
|
||||
for item in soup.findAll('a'):
|
||||
if item.string is not None:
|
||||
str = item.string
|
||||
item.replaceWith(str)
|
||||
else:
|
||||
str = self.tag_to_string(item)
|
||||
item.replaceWith(str)
|
||||
return soup
|
||||
def preprocess_raw_html(self, raw_html, url):
|
||||
q = '>window.__INITIAL_DATA__={'
|
||||
idx = raw_html.find(q)
|
||||
if idx < 0:
|
||||
raise ValueError('Failed to find JSON')
|
||||
data = raw_html[idx + len(q) - 1:]
|
||||
idx = data.find('};</script>')
|
||||
data = data[:idx+1]
|
||||
root = json.loads(data)
|
||||
return parse_article_json(root, self.abort_article)
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user