Philosophy Now Recipe

[rainrdx]

I'm very honored to find out that Kovid Goyal quickly included my previous recipes (The New Republic, Psychology Today and Smithsonian) in Calibre. So I am uploading another one. This one requires subscription. Hopefully someone finds this helpful.

import re
from calibre.web.feeds.recipes import BasicNewsRecipe
from collections import OrderedDict

class PhilosophyNow(BasicNewsRecipe):

    title       = 'Philosophy Now'
    __author__  = 'Rick Shang'

#    description = 'Philosophy Now is a lively magazine for everyone interested in ideas. It isn't afraid to tackle all the major questions of life, the universe and everything. Published every two months, it tries to corrupt innocent citizens by convincing them that philosophy can be exciting, worthwhile and comprehensible, and also to provide some enjoyable reading matter for those already ensnared by the muse, such as philosophy students and academics.'
    language = 'en'
    category = 'news'
    encoding = 'UTF-8'
    
    keep_only_tags = [dict(attrs={'id':'fullMainColumn'})]
    remove_tags = [dict(attrs={'class':'articleTools'})]
    no_javascript = True
    no_stylesheets = True
    needs_subscription = True

    def get_browser(self):
        br = BasicNewsRecipe.get_browser()
        br.open('https://philosophynow.org/auth/login')
        br.select_form(nr = 1)
        br['username'] = self.username
        br['password'] = self.password
        br.submit()
        return br

    def parse_index(self):

	#Go to the issue
        soup0 = self.index_to_soup('http://philosophynow.org/')
        issue = soup0.find('div',attrs={'id':'navColumn'})

	#Find date & cover
	cover = issue.find('div', attrs={'id':'cover'})
	date = self.tag_to_string(cover.find('h3')).strip()
	self.timefmt = u' [%s]'%date
	img=cover.find('img',src=True)['src']
	self.cover_url = 'http://philosophynow.org' + re.sub('medium','large',img)
	issuenum = re.sub('/media/images/covers/medium/issue','',img)
	issuenum = re.sub('.jpg','',issuenum)

        #Go to the main body
	current_issue_url = 'http://philosophynow.org/issues/' + issuenum
        soup = self.index_to_soup(current_issue_url)
	div = soup.find ('div', attrs={'class':'articlesColumn'})

        feeds = OrderedDict()
	

        for post in div.findAll('h3'):
		articles = []
		a=post.find('a',href=True)
		if a is not None:
			url="http://philosophynow.org" + a['href']
			title=self.tag_to_string(a).strip()
			s=post.findPrevious('h4')
			section_title = self.tag_to_string(s).strip()
			d=post.findNext('p')
			desc = self.tag_to_string(d).strip()
			articles.append({'title':title, 'url':url, 'description':desc, 'date':''})

			if articles:
				if section_title not in feeds:
					feeds[section_title] = []
				feeds[section_title] += articles
        ans = [(key, val) for key, val in feeds.iteritems()]
        return ans

[tadswana]

Hi, Can't seem to get this recipe working (I have an active digital subscription to Philosophy Now and can log on to the website okay).

I've entered the details however get the below - any ideas?

----------------

calibre, version 0.9.13 (win32, isfrozen: True)
Conversion Error: Failed: Fetch news from Philosophy Now

Fetch news from Philosophy Now
Resolved conversion options
calibre version: 0.9.13
{'asciiize': False,
'author_sort': None,
'authors': None,
'base_font_size': 0,
'book_producer': None,
'change_justification': 'original',
'chapter': None,
'chapter_mark': 'pagebreak',
'comments': None,
'cover': None,
'debug_pipeline': None,
'dehyphenate': True,
'delete_blank_paragraphs': True,
'disable_font_rescaling': False,
'dont_compress': False,
'dont_download_recipe': False,
'duplicate_links_in_toc': False,
'embed_font_family': None,
'enable_heuristics': False,
'extra_css': None,
'extract_to': None,
'filter_css': None,
'fix_indents': True,
'font_size_mapping': None,
'format_scene_breaks': True,
'html_unwrap_factor': 0.4,
'input_encoding': None,
'input_profile': <calibre.customize.profiles.InputProfile object at 0x000000000499E278>,
'insert_blank_line': False,
'insert_blank_line_size': 0.5,
'insert_metadata': False,
'isbn': None,
'italicize_common_cases': True,
'keep_ligatures': False,
'language': None,
'level1_toc': None,
'level2_toc': None,
'level3_toc': None,
'line_height': 0,
'linearize_tables': False,
'lrf': False,
'margin_bottom': 5.0,
'margin_left': 5.0,
'margin_right': 5.0,
'margin_top': 5.0,
'markup_chapter_headings': True,
'max_toc_links': 50,
'minimum_line_height': 120.0,
'mobi_file_type': 'old',
'mobi_ignore_margins': False,
'mobi_keep_original_images': False,
'mobi_toc_at_start': False,
'no_chapters_in_toc': False,
'no_inline_navbars': True,
'no_inline_toc': False,
'output_profile': <calibre.customize.profiles.KindleDXOutput object at 0x000000000499E860>,
'page_breaks_before': None,
'personal_doc': '[PDOC]',
'prefer_author_sort': False,
'prefer_metadata_cover': False,
'pretty_print': False,
'pubdate': None,
'publisher': None,
'rating': None,
'read_metadata_from_opf': None,
'remove_fake_margins': True,
'remove_first_image': False,
'remove_paragraph_spacing': False,
'remove_paragraph_spacing_indent_size': 1.5,
'renumber_headings': True,
'replace_scene_breaks': '',
'search_replace': None,
'series': None,
'series_index': None,
'share_not_sync': False,
'smarten_punctuation': False,
'sr1_replace': '',
'sr1_search': '',
'sr2_replace': '',
'sr2_search': '',
'sr3_replace': '',
'sr3_search': '',
'start_reading_at': None,
'subset_embedded_fonts': False,
'tags': None,
'test': False,
'timestamp': None,
'title': None,
'title_sort': None,
'toc_filter': None,
'toc_threshold': 6,
'toc_title': None,
'unsmarten_punctuation': False,
'unwrap_lines': True,
'use_auto_toc': False,
'verbose': 2}
InputFormatPlugin: Recipe Input running
Using custom recipe
Python function terminated unexpectedly
no control matching name 'username' (Error Code: 1)
Traceback (most recent call last):
File "site.py", line 132, in main
File "site.py", line 109, in run_entry_point
File "site-packages\calibre\utils\ipc\worker.py", line 186, in main
File "site-packages\calibre\gui2\convert\gui_conversion.py", line 25, in gui_convert
File "site-packages\calibre\ebooks\conversion\plumber.py", line 1009, in run
File "site-packages\calibre\customize\conversion.py", line 239, in __call__
File "site-packages\calibre\ebooks\conversion\plugins\recipe_ input.py", line 108, in convert
File "site-packages\calibre\web\feeds\news.py", line 787, in __init__
File "<string>", line 31, in get_browser
File "site-packages\mechanize-0.2.5-py2.7.egg\mechanize\_form.py", line 2780, in __setitem__
File "site-packages\mechanize-0.2.5-py2.7.egg\mechanize\_form.py", line 3101, in find_control
File "site-packages\mechanize-0.2.5-py2.7.egg\mechanize\_form.py", line 3185, in _find_control
mechanize._form.ControlNotFoundError: no control matching name 'username'

[rainrdx]

Thanks for informing me

This is an update, which should fix all problems

import re
from calibre.web.feeds.recipes import BasicNewsRecipe
from collections import OrderedDict

class PhilosophyNow(BasicNewsRecipe):

    title       = 'Philosophy Now'
    __author__  = 'Rick Shang'

#    description = 'Philosophy Now is a lively magazine for everyone interested in ideas. It isn't afraid to tackle all the major questions of life, the universe and everything. Published every two months, it tries to corrupt innocent citizens by convincing them that philosophy can be exciting, worthwhile and comprehensible, and also to provide some enjoyable reading matter for those already ensnared by the muse, such as philosophy students and academics.'
    language = 'en'
    category = 'news'
    encoding = 'UTF-8'
    
    keep_only_tags = [dict(attrs={'id':'fullMainColumn'})]
    remove_tags = [dict(attrs={'class':'articleTools'})]
    no_javascript = True
    no_stylesheets = True
    needs_subscription = True

    def get_browser(self):
        br = BasicNewsRecipe.get_browser()
        br.open('https://philosophynow.org/auth/login')
        br.select_form(name="loginForm")
        br['username'] = self.username
        br['password'] = self.password
        br.submit()
        return br

    def parse_index(self):

	#Go to the issue
        soup0 = self.index_to_soup('http://philosophynow.org/')
        issue = soup0.find('div',attrs={'id':'navColumn'})

	#Find date & cover
	cover = issue.find('div', attrs={'id':'cover'})
	date = self.tag_to_string(cover.find('h3')).strip()
	self.timefmt = u' [%s]'%date
	img=cover.find('img',src=True)['src']
	self.cover_url = 'http://philosophynow.org' + re.sub('medium','large',img)
	issuenum = re.sub('/media/images/covers/medium/issue','',img)
	issuenum = re.sub('.jpg','',issuenum)

        #Go to the main body
	current_issue_url = 'http://philosophynow.org/issues/' + issuenum
        soup = self.index_to_soup(current_issue_url)
	div = soup.find ('div', attrs={'class':'contentsColumn'})

        feeds = OrderedDict()
	

        for post in div.findAll('h1'):
		articles = []
		a=post.find('a',href=True)
		if a is not None:
			url="http://philosophynow.org" + a['href']
			title=self.tag_to_string(a).strip()
			s=post.findPrevious('h3')
			section_title = self.tag_to_string(s).strip()
			d=post.findNext('h2')
			desc = self.tag_to_string(d).strip()
			articles.append({'title':title, 'url':url, 'description':desc, 'date':''})

			if articles:
				if section_title not in feeds:
					feeds[section_title] = []
				feeds[section_title] += articles
        ans = [(key, val) for key, val in feeds.iteritems()]
        return ans

    def cleanup(self):
        self.browser.open('http://philosophynow.org/auth/logout')