Update TIME

Fixes #1292474 [Private bug](https://bugs.launchpad.net/calibre/+bug/1292474)
This commit is contained in:
Kovid Goyal 2014-03-17 15:49:57 +05:30
parent 43e325b79e
commit 934ab58b88

View File

@ -13,17 +13,17 @@ from calibre.web.feeds.jsnews import JavascriptRecipe
from lxml import html
def wait_for_load(browser):
# This element is present in the black login bar at the top
browser.wait_for_element('#site-header p.constrain', timeout=180)
# This element is present next to the main TIME logo in the left hand side nav bar
browser.wait_for_element('.signedin-wrap a[href]', timeout=180)
# Keep the login method as standalone, so it can be easily tested
def do_login(browser, username, password):
from calibre.web.jsbrowser.browser import Timeout
browser.visit('http://www.time.com/time/magazine')
form = browser.select_form('#magazine-signup')
browser.visit('http://time.com/magazine')
form = browser.select_form('#sign-in-form')
form['username'] = username
form['password'] = password
browser.submit('#paid-wall-submit')
browser.submit('#Sign_In')
try:
wait_for_load(browser)
except Timeout:
@ -40,100 +40,57 @@ class Time(JavascriptRecipe):
no_stylesheets = True
remove_javascript = True
keep_only_tags = ['article.post']
remove_tags = ['meta', '.entry-sharing', '.entry-footer', '.wp-paginate',
'.post-rail', '.entry-comments', '.entry-tools',
'#paid-wall-cm-ad']
recursions = 1
links_from_selectors = ['.wp-paginate a.page[href]']
extra_css = '.entry-date { padding-left: 2ex }'
keep_only_tags = ['.article-viewport .full-article']
remove_tags = ['.read-more-list', '.read-more-inline', '.article-footer', '.subscribe', '.tooltip', '#first-visit']
def do_login(self, browser, username, password):
do_login(browser, username, password)
def get_publication_data(self, browser):
selector = 'section.sec-mag-showcase ul.ul-mag-showcase img[src]'
def get_time_cover(self, browser):
selector = '#rail-articles img.magazine-thumb'
cover = browser.css_select(selector)
# URL for large cover
cover_url = unicode(cover.evaluateJavaScript('this.src').toString()).replace('_400.', '_600.')
raw = browser.html
ans = {'cover': browser.get_resource(cover_url)}
cover_url = unicode(cover.evaluateJavaScript('this.src').toString()).partition('?')[0] + '?w=814'
return browser.get_resource(cover_url)
def get_publication_data(self, browser):
# We are already at the magazine page thanks to the do_login() method
ans = {}
raw = browser.html
root = html.fromstring(raw)
dates = ''.join(root.xpath('//time[@class="updated"]/text()'))
dates = ''.join(root.xpath('//*[@class="rail-article-magazine-issue"]/date/text()'))
if dates:
self.timefmt = ' [%s]'%dates
feeds = []
parent = root.xpath('//div[@class="content-main-aside"]')[0]
for sec in parent.xpath(
'descendant::section[contains(@class, "sec-mag-section")]'):
h3 = sec.xpath('./h3')
if h3:
section = html.tostring(h3[0], encoding=unicode,
method='text').strip().capitalize()
self.log('Found section', section)
articles = list(self.find_articles(sec))
if articles:
feeds.append((section, articles))
parent = root.xpath('//section[@id="rail-articles"]')[0]
articles = []
for h3 in parent.xpath(
'descendant::h3[contains(@class, "rail-article-title")]'):
title = html.tostring(h3[0], encoding=unicode, method='text').strip()
a = h3.xpath('descendant::a[@href]')[0]
url = a.get('href')
h2 = h3.xpath('following-sibling::h2[@class="rail-article-excerpt"]')
desc = ''
if h2:
desc = html.tostring(h2[0], encoding=unicode, method='text').strip()
self.log('\nFound article:', title)
self.log('\t' + desc)
articles.append({'title':title, 'url':url, 'date':'', 'description':desc})
ans['index'] = feeds
ans['index'] = [('Articles', articles)]
ans['cover'] = self.get_time_cover(browser)
return ans
def find_articles(self, sec):
for article in sec.xpath('./article'):
h2 = article.xpath('./*[@class="entry-title"]')
if not h2:
continue
a = h2[0].xpath('./a[@href]')
if not a:
continue
title = html.tostring(a[0], encoding=unicode,
method='text').strip()
if not title:
continue
url = a[0].get('href')
if url.startswith('/'):
url = 'http://www.time.com'+url
desc = ''
p = article.xpath('./*[@class="entry-content"]')
if p:
desc = html.tostring(p[0], encoding=unicode,
method='text')
self.log('\t', title, ':\n\t\t', url)
yield {
'title' : title,
'url' : url,
'date' : '',
'description' : desc
}
def load_complete(self, browser, url, recursion_level):
# This is needed as without it, subscriber content is blank. time.com
# appears to be using some crazy iframe+js callback for loading content
wait_for_load(browser)
def load_complete(self, browser, url, rl):
browser.wait_for_element('footer.article-footer')
return True
def postprocess_html(self, article, root, url, recursion_level):
# Remove the header and page n of m messages from pages after the first
# page
if recursion_level > 0:
for h in root.xpath('//header[@class="entry-header"]|//span[@class="page"]'):
h.getparent().remove(h)
# Unfloat the article images and also remove them from pages after the
# first page as they are repeated on every page.
for fig in root.xpath('//figure'):
parent = fig.getparent()
if recursion_level > 0:
parent.remove(fig)
else:
idx = parent.index(fig)
for img in reversed(fig.xpath('descendant::img')):
parent.insert(idx, img)
parent.remove(fig)
# get rid of the first visit div which for some reason remove_tags is
# not removing
for div in root.xpath('//*[@id="first-visit"]'):
div.getparent().remove(div)
return root
if __name__ == '__main__':