Various Japanese recipes by Hiroshi Miura

This commit is contained in:
Kovid Goyal 2010-11-23 09:04:13 -07:00
commit 41ba44a793
28 changed files with 817 additions and 0 deletions

Binary file not shown.

After

Width:  |  Height:  |  Size: 892 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 698 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 919 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 543 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 948 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 948 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 948 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 948 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 948 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 948 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 693 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 693 B

View File

@ -13,6 +13,7 @@ class Dnevnik(BasicNewsRecipe):
labguage = 'sl' labguage = 'sl'
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
language = 'sl'
conversion_options = {'linearize_tables' : True} conversion_options = {'linearize_tables' : True}

View File

@ -0,0 +1,32 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
class CNetJapan(BasicNewsRecipe):
title = u'CNET Japan'
oldest_article = 3
max_articles_per_feed = 30
__author__ = 'Hiroshi Miura'
feeds = [(u'cnet rss', u'http://feeds.japan.cnet.com/cnet/rss')]
language = 'ja'
encoding = 'Shift_JIS'
remove_javascript = True
preprocess_regexps = [
(re.compile(ur'<!--\u25B2contents_left END\u25B2-->.*</body>', re.DOTALL|re.IGNORECASE|re.UNICODE),
lambda match: '</body>'),
(re.compile(r'<!--AD_ELU_HEADER-->.*</body>', re.DOTALL|re.IGNORECASE),
lambda match: '</body>'),
(re.compile(ur'<!-- \u25B2\u95A2\u9023\u30BF\u30B0\u25B2 -->.*<!-- \u25B2ZDNet\u25B2 -->', re.UNICODE),
lambda match: '<!-- removed -->'),
]
remove_tags_before = dict(name="h2")
remove_tags = [
{'class':"social_bkm_share"},
{'class':"social_bkm_print"},
{'class':"block20 clearfix"},
dict(name="div",attrs={'id':'bookreview'}),
]
remove_tags_after = {'class':"block20"}

View File

@ -0,0 +1,22 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
'''
japan.engadget.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class EndgadgetJapan(BasicNewsRecipe):
title = u'Endgadget\u65e5\u672c\u7248'
language = 'ja'
__author__ = 'Hiroshi Miura'
cover_url = 'http://skins18.wincustomize.com/1/49/149320/29/7578/preview-29-7578.jpg'
masthead_url = 'http://www.blogsmithmedia.com/japanese.engadget.com/media/eng-jp-logo-t.png'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
language = 'ja'
encoding = 'utf-8'
feeds = [(u'engadget', u'http://japanese.engadget.com/rss.xml')]

View File

@ -0,0 +1,26 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
'''
www.jiji.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class JijiDotCom(BasicNewsRecipe):
title = u'\u6642\u4e8b\u901a\u4fe1'
__author__ = 'Hiroshi Miura'
description = 'World News from Jiji Press'
publisher = 'Jiji Press Ltd.'
category = 'news'
encoding = 'utf-8'
oldest_article = 6
max_articles_per_feed = 100
language = 'ja'
cover_url = 'http://www.jiji.com/img/top_header_logo2.gif'
masthead_url = 'http://jen.jiji.com/images/logo_jijipress.gif'
feeds = [(u'\u30cb\u30e5\u30fc\u30b9', u'http://www.jiji.com/rss/ranking.rdf')]
remove_tags_after = dict(id="ad_google")

View File

@ -0,0 +1,26 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
'''
www.mainichi.jp
'''
from calibre.web.feeds.news import BasicNewsRecipe
class MainichiDailyNews(BasicNewsRecipe):
title = u'\u6bce\u65e5\u65b0\u805e'
__author__ = 'Hiroshi Miura'
oldest_article = 2
max_articles_per_feed = 20
description = 'Japanese traditional newspaper Mainichi Daily News'
publisher = 'Mainichi Daily News'
category = 'news, japan'
language = 'ja'
feeds = [(u'daily news', u'http://mainichi.jp/rss/etc/flash.rss')]
remove_tags_before = {'class':"NewsTitle"}
remove_tags = [{'class':"RelatedArticle"}]
remove_tags_after = {'class':"Credit"}

View File

@ -0,0 +1,18 @@
from calibre.web.feeds.news import BasicNewsRecipe
class MainichiDailyITNews(BasicNewsRecipe):
title = u'\u6bce\u65e5\u65b0\u805e(IT&\u5bb6\u96fb)'
__author__ = 'Hiroshi Miura'
oldest_article = 2
max_articles_per_feed = 100
description = 'Japanese traditional newspaper Mainichi Daily News - IT and electronics'
publisher = 'Mainichi Daily News'
category = 'news, Japan, IT, Electronics'
language = 'ja'
feeds = [(u'IT News', u'http://mainichi.pheedo.jp/f/mainichijp_electronics')]
remove_tags_before = {'class':"NewsTitle"}
remove_tags = [{'class':"RelatedArticle"}]
remove_tags_after = {'class':"Credit"}

View File

@ -0,0 +1,24 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
'''
sankei.jp.msn.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class MSNSankeiNewsProduct(BasicNewsRecipe):
title = u'MSN\u7523\u7d4c\u30cb\u30e5\u30fc\u30b9(\u65b0\u5546\u54c1)'
__author__ = 'Hiroshi Miura'
description = 'Products release from Japan'
oldest_article = 7
max_articles_per_feed = 100
encoding = 'Shift_JIS'
language = 'ja'
feeds = [(u'\u65b0\u5546\u54c1', u'http://sankei.jp.msn.com/rss/news/release.xml')]
remove_tags_before = dict(id="__r_article_title__")
remove_tags_after = dict(id="ajax_release_news")
remove_tags = [{'class':"parent chromeCustom6G"}]

View File

@ -0,0 +1,60 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
'''
www.nikkei.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class NikkeiNet(BasicNewsRecipe):
title = u'\u65e5\u7d4c\u65b0\u805e\u96fb\u5b50\u7248(Free)'
__author__ = 'Hiroshi Miura'
description = 'News and current market affairs from Japan'
cover_url = 'http://parts.nikkei.com/parts/ds/images/common/logo_r1.svg'
masthead_url = 'http://parts.nikkei.com/parts/ds/images/common/logo_r1.svg'
oldest_article = 2
max_articles_per_feed = 20
language = 'ja'
feeds = [ (u'\u65e5\u7d4c\u4f01\u696d', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=sangyo'),
(u'\u65e5\u7d4c\u88fd\u54c1', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=newpro'),
(u'internet', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=internet'),
(u'\u653f\u6cbb', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=seiji'),
(u'\u8ca1\u52d9', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=zaimu'),
(u'\u7d4c\u6e08', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=keizai'),
(u'\u56fd\u969b', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=kaigai'),
(u'\u79d1\u5b66', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=kagaku'),
(u'\u30de\u30fc\u30b1\u30c3\u30c8', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=market'),
(u'\u304f\u3089\u3057', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=kurashi'),
(u'\u30b9\u30dd\u30fc\u30c4', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=sports'),
(u'\u793e\u4f1a', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=shakai'),
(u'\u30a8\u30b3', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=eco'),
(u'\u5065\u5eb7', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=kenkou'),
(u'\u96c7\u7528', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=koyou'),
(u'\u6559\u80b2', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=kyouiku'),
(u'\u304a\u304f\u3084\u307f', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=okuyami'),
(u'\u4eba\u4e8b', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=zinzi'),
(u'\u7279\u96c6', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=special'),
(u'\u5730\u57df\u30cb\u30e5\u30fc\u30b9', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=local'),
(u'\u7d71\u8a08\u30fb\u767d\u66f8', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=report'),
(u'\u30e9\u30f3\u30ad\u30f3\u30b0', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=ranking'),
(u'\u4f1a\u898b', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=interview'),
(u'\u793e\u8aac\u30fb\u6625\u79cb', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=shasetsu'),
(u'\u30b9\u30dd\u30fc\u30c4\uff1a\u30d7\u30ed\u91ce\u7403', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=baseball'),
(u'\u30b9\u30dd\u30fc\u30c4\uff1a\u5927\u30ea\u30fc\u30b0', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=mlb'),
(u'\u30b9\u30dd\u30fc\u30c4\uff1a\u30b5\u30c3\u30ab\u30fc', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=soccer'),
(u'\u30b9\u30dd\u30fc\u30c4\uff1a\u30b4\u30eb\u30d5', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=golf'),
(u'\u30b9\u30dd\u30fc\u30c4\uff1a\u76f8\u64b2', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=sumou'),
(u'\u30b9\u30dd\u30fc\u30c4\uff1a\u7af6\u99ac', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=keiba'),
(u'\u8abf\u67fb\u30fb\u30a2\u30f3\u30b1\u30fc\u30c8', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=research')
]
remove_tags_before = dict(id="CONTENTS")
remove_tags = [
dict(name="form"),
{'class':"cmn-hide"},
]
remove_tags_after = {'class':"cmn-pr_list"}

View File

@ -0,0 +1,109 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
'''
www.nikkei.com
'''
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
import mechanize
from calibre.ptempfile import PersistentTemporaryFile
class NikkeiNet_sub_economy(BasicNewsRecipe):
title = u'\u65e5\u7d4c\u65b0\u805e\u96fb\u5b50\u7248(\u7d4c\u6e08)'
__author__ = 'Hiroshi Miura'
description = 'News and current market affairs from Japan'
cover_url = 'http://parts.nikkei.com/parts/ds/images/common/logo_r1.svg'
masthead_url = 'http://parts.nikkei.com/parts/ds/images/common/logo_r1.svg'
needs_subscription = True
oldest_article = 2
max_articles_per_feed = 20
language = 'ja'
remove_javascript = False
temp_files = []
remove_tags_before = {'class':"cmn-section cmn-indent"}
remove_tags = [
{'class':"JSID_basePageMove JSID_baseAsyncSubmit cmn-form_area JSID_optForm_utoken"},
{'class':"cmn-article_keyword cmn-clearfix"},
{'class':"cmn-print_headline cmn-clearfix"},
]
remove_tags_after = {'class':"cmn-pr_list"}
feeds = [ (u'\u653f\u6cbb', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=seiji'),
(u'\u8ca1\u52d9', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=zaimu'),
(u'\u7d4c\u6e08', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=keizai'),
(u'\u30de\u30fc\u30b1\u30c3\u30c8', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=market'),
(u'\u96c7\u7528', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=koyou'),
(u'\u6559\u80b2', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=kyouiku'),
(u'\u304a\u304f\u3084\u307f', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=okuyami'),
(u'\u4eba\u4e8b', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=zinzi'),
]
def get_browser(self):
br = BasicNewsRecipe.get_browser()
cj = mechanize.LWPCookieJar()
br.set_cookiejar(cj)
#br.set_debug_http(True)
#br.set_debug_redirects(True)
#br.set_debug_responses(True)
if self.username is not None and self.password is not None:
#print "----------------------------get login form--------------------------------------------"
# open login form
br.open('https://id.nikkei.com/lounge/nl/base/LA0010.seam')
response = br.response()
#print "----------------------------get login form---------------------------------------------"
#print "----------------------------set login form---------------------------------------------"
# remove disabled input which brings error on mechanize
response.set_data(response.get_data().replace("<input id=\"j_id48\"", "<!-- "))
response.set_data(response.get_data().replace("gm_home_on.gif\" />", " -->"))
br.set_response(response)
br.select_form(name='LA0010Form01')
br['LA0010Form01:LA0010Email'] = self.username
br['LA0010Form01:LA0010Password'] = self.password
br.form.find_control(id='LA0010Form01:LA0010AutoLoginOn',type="checkbox").get(nr=0).selected = True
br.submit()
br.response()
#print "----------------------------send login form---------------------------------------------"
#print "----------------------------open news main page-----------------------------------------"
# open news site
br.open('http://www.nikkei.com/')
br.response()
#print "----------------------------www.nikkei.com BODY --------------------------------------"
#print response2.get_data()
#print "-------------------------^^-got auto redirect form----^^--------------------------------"
# forced redirect in default
br.select_form(nr=0)
br.submit()
response3 = br.response()
# return some cookie which should be set by Javascript
#print response3.geturl()
raw = response3.get_data()
#print "---------------------------response to form --------------------------------------------"
# grab cookie from JS and set it
redirectflag = re.search(r"var checkValue = '(\d+)';", raw, re.M).group(1)
br.select_form(nr=0)
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write("#LWP-Cookies-2.0\n")
self.temp_files[-1].write("Set-Cookie3: Cookie-dummy=Cookie-value; domain=\".nikkei.com\"; path=\"/\"; path_spec; secure; expires=\"2029-12-21 05:07:59Z\"; version=0\n")
self.temp_files[-1].write("Set-Cookie3: redirectFlag="+redirectflag+"; domain=\".nikkei.com\"; path=\"/\"; path_spec; secure; expires=\"2029-12-21 05:07:59Z\"; version=0\n")
self.temp_files[-1].close()
cj.load(self.temp_files[-1].name)
br.submit()
#br.set_debug_http(False)
#br.set_debug_redirects(False)
#br.set_debug_responses(False)
return br

View File

@ -0,0 +1,108 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
'''
www.nikkei.com
'''
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
import mechanize
from calibre.ptempfile import PersistentTemporaryFile
class NikkeiNet_sub_industory(BasicNewsRecipe):
title = u'\u65e5\u7d4c\u65b0\u805e\u96fb\u5b50\u7248(\u7523\u696d)'
__author__ = 'Hiroshi Miura'
description = 'News and current market affairs from Japan'
cover_url = 'http://parts.nikkei.com/parts/ds/images/common/logo_r1.svg'
masthead_url = 'http://parts.nikkei.com/parts/ds/images/common/logo_r1.svg'
needs_subscription = True
oldest_article = 2
max_articles_per_feed = 20
language = 'ja'
remove_javascript = False
temp_files = []
remove_tags_before = {'class':"cmn-section cmn-indent"}
remove_tags = [
{'class':"JSID_basePageMove JSID_baseAsyncSubmit cmn-form_area JSID_optForm_utoken"},
{'class':"cmn-article_keyword cmn-clearfix"},
{'class':"cmn-print_headline cmn-clearfix"},
]
remove_tags_after = {'class':"cmn-pr_list"}
feeds = [ (u'\u65e5\u7d4c\u4f01\u696d', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=sangyo'),
(u'\u65e5\u7d4c\u88fd\u54c1', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=newpro'),
(u'internet', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=internet'),
(u'\u56fd\u969b', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=kaigai'),
(u'\u79d1\u5b66', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=kagaku'),
]
def get_browser(self):
br = BasicNewsRecipe.get_browser()
cj = mechanize.LWPCookieJar()
br.set_cookiejar(cj)
#br.set_debug_http(True)
#br.set_debug_redirects(True)
#br.set_debug_responses(True)
if self.username is not None and self.password is not None:
#print "----------------------------get login form--------------------------------------------"
# open login form
br.open('https://id.nikkei.com/lounge/nl/base/LA0010.seam')
response = br.response()
#print "----------------------------get login form---------------------------------------------"
#print "----------------------------set login form---------------------------------------------"
# remove disabled input which brings error on mechanize
response.set_data(response.get_data().replace("<input id=\"j_id48\"", "<!-- "))
response.set_data(response.get_data().replace("gm_home_on.gif\" />", " -->"))
br.set_response(response)
br.select_form(name='LA0010Form01')
br['LA0010Form01:LA0010Email'] = self.username
br['LA0010Form01:LA0010Password'] = self.password
br.form.find_control(id='LA0010Form01:LA0010AutoLoginOn',type="checkbox").get(nr=0).selected = True
br.submit()
br.response()
#print "----------------------------send login form---------------------------------------------"
#print "----------------------------open news main page-----------------------------------------"
# open news site
br.open('http://www.nikkei.com/')
br.response()
#print "----------------------------www.nikkei.com BODY --------------------------------------"
#print response2.get_data()
#print "-------------------------^^-got auto redirect form----^^--------------------------------"
# forced redirect in default
br.select_form(nr=0)
br.submit()
response3 = br.response()
# return some cookie which should be set by Javascript
#print response3.geturl()
raw = response3.get_data()
#print "---------------------------response to form --------------------------------------------"
# grab cookie from JS and set it
redirectflag = re.search(r"var checkValue = '(\d+)';", raw, re.M).group(1)
br.select_form(nr=0)
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write("#LWP-Cookies-2.0\n")
self.temp_files[-1].write("Set-Cookie3: Cookie-dummy=Cookie-value; domain=\".nikkei.com\"; path=\"/\"; path_spec; secure; expires=\"2029-12-21 05:07:59Z\"; version=0\n")
self.temp_files[-1].write("Set-Cookie3: redirectFlag="+redirectflag+"; domain=\".nikkei.com\"; path=\"/\"; path_spec; secure; expires=\"2029-12-21 05:07:59Z\"; version=0\n")
self.temp_files[-1].close()
cj.load(self.temp_files[-1].name)
br.submit()
#br.set_debug_http(False)
#br.set_debug_redirects(False)
#br.set_debug_responses(False)
return br

View File

@ -0,0 +1,109 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
'''
www.nikkei.com
'''
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
import mechanize
from calibre.ptempfile import PersistentTemporaryFile
class NikkeiNet_sub_life(BasicNewsRecipe):
title = u'\u65e5\u7d4c\u65b0\u805e\u96fb\u5b50\u7248(\u751f\u6d3b)'
__author__ = 'Hiroshi Miura'
description = 'News and current market affairs from Japan'
cover_url = 'http://parts.nikkei.com/parts/ds/images/common/logo_r1.svg'
masthead_url = 'http://parts.nikkei.com/parts/ds/images/common/logo_r1.svg'
needs_subscription = True
oldest_article = 2
max_articles_per_feed = 20
language = 'ja'
remove_javascript = False
temp_files = []
remove_tags_before = {'class':"cmn-section cmn-indent"}
remove_tags = [
{'class':"JSID_basePageMove JSID_baseAsyncSubmit cmn-form_area JSID_optForm_utoken"},
{'class':"cmn-article_keyword cmn-clearfix"},
{'class':"cmn-print_headline cmn-clearfix"},
]
remove_tags_after = {'class':"cmn-pr_list"}
feeds = [ (u'\u304f\u3089\u3057', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=kurashi'),
(u'\u30b9\u30dd\u30fc\u30c4', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=sports'),
(u'\u793e\u4f1a', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=shakai'),
(u'\u30a8\u30b3', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=eco'),
(u'\u5065\u5eb7', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=kenkou'),
(u'\u7279\u96c6', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=special'),
(u'\u30e9\u30f3\u30ad\u30f3\u30b0', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=ranking')
]
def get_browser(self):
br = BasicNewsRecipe.get_browser()
cj = mechanize.LWPCookieJar()
br.set_cookiejar(cj)
#br.set_debug_http(True)
#br.set_debug_redirects(True)
#br.set_debug_responses(True)
if self.username is not None and self.password is not None:
#print "----------------------------get login form--------------------------------------------"
# open login form
br.open('https://id.nikkei.com/lounge/nl/base/LA0010.seam')
response = br.response()
#print "----------------------------get login form---------------------------------------------"
#print "----------------------------set login form---------------------------------------------"
# remove disabled input which brings error on mechanize
response.set_data(response.get_data().replace("<input id=\"j_id48\"", "<!-- "))
response.set_data(response.get_data().replace("gm_home_on.gif\" />", " -->"))
br.set_response(response)
br.select_form(name='LA0010Form01')
br['LA0010Form01:LA0010Email'] = self.username
br['LA0010Form01:LA0010Password'] = self.password
br.form.find_control(id='LA0010Form01:LA0010AutoLoginOn',type="checkbox").get(nr=0).selected = True
br.submit()
br.response()
#print "----------------------------send login form---------------------------------------------"
#print "----------------------------open news main page-----------------------------------------"
# open news site
br.open('http://www.nikkei.com/')
br.response()
#print "----------------------------www.nikkei.com BODY --------------------------------------"
#print response2.get_data()
#print "-------------------------^^-got auto redirect form----^^--------------------------------"
# forced redirect in default
br.select_form(nr=0)
br.submit()
response3 = br.response()
# return some cookie which should be set by Javascript
#print response3.geturl()
raw = response3.get_data()
#print "---------------------------response to form --------------------------------------------"
# grab cookie from JS and set it
redirectflag = re.search(r"var checkValue = '(\d+)';", raw, re.M).group(1)
br.select_form(nr=0)
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write("#LWP-Cookies-2.0\n")
self.temp_files[-1].write("Set-Cookie3: Cookie-dummy=Cookie-value; domain=\".nikkei.com\"; path=\"/\"; path_spec; secure; expires=\"2029-12-21 05:07:59Z\"; version=0\n")
self.temp_files[-1].write("Set-Cookie3: redirectFlag="+redirectflag+"; domain=\".nikkei.com\"; path=\"/\"; path_spec; secure; expires=\"2029-12-21 05:07:59Z\"; version=0\n")
self.temp_files[-1].close()
cj.load(self.temp_files[-1].name)
br.submit()
#br.set_debug_http(False)
#br.set_debug_redirects(False)
#br.set_debug_responses(False)
return br

View File

@ -0,0 +1,102 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
'''
www.nikkei.com
'''
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
import mechanize
from calibre.ptempfile import PersistentTemporaryFile
class NikkeiNet_sub_main(BasicNewsRecipe):
title = u'\u65e5\u7d4c\u65b0\u805e\u96fb\u5b50\u7248(\u7dcf\u5408)'
__author__ = 'Hiroshi Miura'
description = 'News and current market affairs from Japan'
cover_url = 'http://parts.nikkei.com/parts/ds/images/common/logo_r1.svg'
masthead_url = 'http://parts.nikkei.com/parts/ds/images/common/logo_r1.svg'
needs_subscription = True
oldest_article = 2
max_articles_per_feed = 20
language = 'ja'
remove_javascript = False
temp_files = []
remove_tags_before = {'class':"cmn-section cmn-indent"}
remove_tags = [
{'class':"JSID_basePageMove JSID_baseAsyncSubmit cmn-form_area JSID_optForm_utoken"},
{'class':"cmn-article_keyword cmn-clearfix"},
{'class':"cmn-print_headline cmn-clearfix"},
]
remove_tags_after = {'class':"cmn-pr_list"}
feeds = [ (u'NIKKEI', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=main')]
def get_browser(self):
br = BasicNewsRecipe.get_browser()
cj = mechanize.LWPCookieJar()
br.set_cookiejar(cj)
#br.set_debug_http(True)
#br.set_debug_redirects(True)
#br.set_debug_responses(True)
if self.username is not None and self.password is not None:
#print "----------------------------get login form--------------------------------------------"
# open login form
br.open('https://id.nikkei.com/lounge/nl/base/LA0010.seam')
response = br.response()
#print "----------------------------get login form---------------------------------------------"
#print "----------------------------set login form---------------------------------------------"
# remove disabled input which brings error on mechanize
response.set_data(response.get_data().replace("<input id=\"j_id48\"", "<!-- "))
response.set_data(response.get_data().replace("gm_home_on.gif\" />", " -->"))
br.set_response(response)
br.select_form(name='LA0010Form01')
br['LA0010Form01:LA0010Email'] = self.username
br['LA0010Form01:LA0010Password'] = self.password
br.form.find_control(id='LA0010Form01:LA0010AutoLoginOn',type="checkbox").get(nr=0).selected = True
br.submit()
br.response()
#print "----------------------------send login form---------------------------------------------"
#print "----------------------------open news main page-----------------------------------------"
# open news site
br.open('http://www.nikkei.com/')
br.response()
#print "----------------------------www.nikkei.com BODY --------------------------------------"
#print response2.get_data()
#print "-------------------------^^-got auto redirect form----^^--------------------------------"
# forced redirect in default
br.select_form(nr=0)
br.submit()
response3 = br.response()
# return some cookie which should be set by Javascript
#print response3.geturl()
raw = response3.get_data()
#print "---------------------------response to form --------------------------------------------"
# grab cookie from JS and set it
redirectflag = re.search(r"var checkValue = '(\d+)';", raw, re.M).group(1)
br.select_form(nr=0)
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write("#LWP-Cookies-2.0\n")
self.temp_files[-1].write("Set-Cookie3: Cookie-dummy=Cookie-value; domain=\".nikkei.com\"; path=\"/\"; path_spec; secure; expires=\"2029-12-21 05:07:59Z\"; version=0\n")
self.temp_files[-1].write("Set-Cookie3: redirectFlag="+redirectflag+"; domain=\".nikkei.com\"; path=\"/\"; path_spec; secure; expires=\"2029-12-21 05:07:59Z\"; version=0\n")
self.temp_files[-1].close()
cj.load(self.temp_files[-1].name)
br.submit()
#br.set_debug_http(False)
#br.set_debug_redirects(False)
#br.set_debug_responses(False)
return br

View File

@ -0,0 +1,109 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
'''
www.nikkei.com
'''
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
import mechanize
from calibre.ptempfile import PersistentTemporaryFile
class NikkeiNet_sub_sports(BasicNewsRecipe):
title = u'\u65e5\u7d4c\u65b0\u805e\u96fb\u5b50\u7248(\u30b9\u30dd\u30fc\u30c4)'
__author__ = 'Hiroshi Miura'
description = 'News and current market affairs from Japan'
cover_url = 'http://parts.nikkei.com/parts/ds/images/common/logo_r1.svg'
masthead_url = 'http://parts.nikkei.com/parts/ds/images/common/logo_r1.svg'
needs_subscription = True
oldest_article = 2
max_articles_per_feed = 20
language = 'ja'
remove_javascript = False
temp_files = []
remove_tags_before = {'class':"cmn-section cmn-indent"}
remove_tags = [
{'class':"JSID_basePageMove JSID_baseAsyncSubmit cmn-form_area JSID_optForm_utoken"},
{'class':"cmn-article_keyword cmn-clearfix"},
{'class':"cmn-print_headline cmn-clearfix"},
]
remove_tags_after = {'class':"cmn-pr_list"}
feeds = [
(u'\u30b9\u30dd\u30fc\u30c4\uff1a\u30d7\u30ed\u91ce\u7403', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=baseball'),
(u'\u30b9\u30dd\u30fc\u30c4\uff1a\u5927\u30ea\u30fc\u30b0', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=mlb'),
(u'\u30b9\u30dd\u30fc\u30c4\uff1a\u30b5\u30c3\u30ab\u30fc', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=soccer'),
(u'\u30b9\u30dd\u30fc\u30c4\uff1a\u30b4\u30eb\u30d5', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=golf'),
(u'\u30b9\u30dd\u30fc\u30c4\uff1a\u76f8\u64b2', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=sumou'),
(u'\u30b9\u30dd\u30fc\u30c4\uff1a\u7af6\u99ac', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=keiba')
]
def get_browser(self):
br = BasicNewsRecipe.get_browser()
cj = mechanize.LWPCookieJar()
br.set_cookiejar(cj)
#br.set_debug_http(True)
#br.set_debug_redirects(True)
#br.set_debug_responses(True)
if self.username is not None and self.password is not None:
#print "----------------------------get login form--------------------------------------------"
# open login form
br.open('https://id.nikkei.com/lounge/nl/base/LA0010.seam')
response = br.response()
#print "----------------------------get login form---------------------------------------------"
#print "----------------------------set login form---------------------------------------------"
# remove disabled input which brings error on mechanize
response.set_data(response.get_data().replace("<input id=\"j_id48\"", "<!-- "))
response.set_data(response.get_data().replace("gm_home_on.gif\" />", " -->"))
br.set_response(response)
br.select_form(name='LA0010Form01')
br['LA0010Form01:LA0010Email'] = self.username
br['LA0010Form01:LA0010Password'] = self.password
br.form.find_control(id='LA0010Form01:LA0010AutoLoginOn',type="checkbox").get(nr=0).selected = True
br.submit()
br.response()
#print "----------------------------send login form---------------------------------------------"
#print "----------------------------open news main page-----------------------------------------"
# open news site
br.open('http://www.nikkei.com/')
br.response()
#print "----------------------------www.nikkei.com BODY --------------------------------------"
#print response2.get_data()
#print "-------------------------^^-got auto redirect form----^^--------------------------------"
# forced redirect in default
br.select_form(nr=0)
br.submit()
response3 = br.response()
# return some cookie which should be set by Javascript
#print response3.geturl()
raw = response3.get_data()
#print "---------------------------response to form --------------------------------------------"
# grab cookie from JS and set it
redirectflag = re.search(r"var checkValue = '(\d+)';", raw, re.M).group(1)
br.select_form(nr=0)
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write("#LWP-Cookies-2.0\n")
self.temp_files[-1].write("Set-Cookie3: Cookie-dummy=Cookie-value; domain=\".nikkei.com\"; path=\"/\"; path_spec; secure; expires=\"2029-12-21 05:07:59Z\"; version=0\n")
self.temp_files[-1].write("Set-Cookie3: redirectFlag="+redirectflag+"; domain=\".nikkei.com\"; path=\"/\"; path_spec; secure; expires=\"2029-12-21 05:07:59Z\"; version=0\n")
self.temp_files[-1].close()
cj.load(self.temp_files[-1].name)
br.submit()
#br.set_debug_http(False)
#br.set_debug_redirects(False)
#br.set_debug_responses(False)
return br

View File

@ -13,6 +13,7 @@ class NowToronto(BasicNewsRecipe):
title = u'Now Toronto' title = u'Now Toronto'
description = u'Now Toronto' description = u'Now Toronto'
__author__ = 'Starson17' __author__ = 'Starson17'
language = 'en_CA'
conversion_options = { conversion_options = {
'no_default_epub_cover' : True 'no_default_epub_cover' : True
} }

View File

@ -0,0 +1,37 @@
from calibre.web.feeds.news import BasicNewsRecipe
import re
class ReutersJa(BasicNewsRecipe):
title = 'Reuters(Japan)'
description = 'Global news in Japanese'
__author__ = 'Hiroshi Miura'
use_embedded_content = False
language = 'ja'
max_articles_per_feed = 10
remove_javascript = True
feeds = [ ('Top Stories', 'http://feeds.reuters.com/reuters/JPTopNews?format=xml'),
('World News', 'http://feeds.reuters.com/reuters/JPWorldNews?format=xml'),
('Business News', 'http://feeds.reuters.com/reuters/JPBusinessNews?format=xml'),
('Technology News', 'http://feeds.reuters.com/reuters/JPTechnologyNews?format=xml'),
('Oddly Enough News', 'http://feeds.reuters.com/reuters/JPOddlyEnoughNews?format=xml')
]
remove_tags_before = {'class':"article primaryContent"}
remove_tags = [ dict(id="banner"),
dict(id="autilities"),
dict(id="textSizer"),
dict(id="shareFooter"),
dict(id="relatedNews"),
dict(id="editorsChoice"),
dict(id="ecArticles"),
{'class':"secondaryContent"},
{'class':"module"},
]
remove_tags_after = {'class':"assetBuddy"}
def print_version(self, url):
m = re.search('(.*idJPJAPAN-[0-9]+)', url)
return m.group(0)+'?sp=true'

View File

@ -0,0 +1,33 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
'''
www.h-online.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class TheHeiseOnline(BasicNewsRecipe):
title = u'The H'
__author__ = 'Hiroshi Miura'
oldest_article = 3
description = 'In association with Heise Online'
publisher = 'Heise Media UK Ltd.'
category = 'news, technology, security'
max_articles_per_feed = 100
language = 'en'
encoding = 'utf-8'
conversion_options = {
'comment' : description
,'tags' : category
,'publisher': publisher
,'language' : language
}
feeds = [
(u'The H News Feed', u'http://www.h-online.com/news/atom.xml')
]
def print_version(self, url):
return url + '?view=print'