def test_article_with_filename_metadata(self):
page = self.read_file(path='2012-11-30_md_w_filename_meta#foo-bar.md',
FILENAME_METADATA=None)
expected = {
'category': 'yeah',
'author': 'Alexis Métaireau',
}
for key, value in expected.items():
self.assertEqual(value, page.metadata[key], key)
page = self.read_file(
path='2012-11-30_md_w_filename_meta#foo-bar.md',
FILENAME_METADATA='(?P<date>\d{4}-\d{2}-\d{2}).*')
expected = {
'category': 'yeah',
'author': 'Alexis Métaireau',
'date': SafeDatetime(2012, 11, 30),
}
for key, value in expected.items():
self.assertEqual(value, page.metadata[key], key)
page = self.read_file(
path='2012-11-30_md_w_filename_meta#foo-bar.md',
FILENAME_METADATA=('(?P<date>\d{4}-\d{2}-\d{2})'
'_(?P<Slug>.*)'
'#(?P<MyMeta>.*)-(?P<author>.*)'))
expected = {
'category': 'yeah',
'author': 'Alexis Métaireau',
'date': SafeDatetime(2012, 11, 30),
'slug': 'md_w_filename_meta',
'mymeta': 'foo',
}
for key, value in expected.items():
self.assertEqual(value, page.metadata[key], key)
def test_article_with_metadata(self):
page = self.read_file(path='article_with_metadata.rst')
expected = {
'category':
'yeah',
'author':
'Alexis Métaireau',
'title':
'This is a super article !',
'summary':
'<p class="first last">Multi-line metadata should be'
' supported\nas well as <strong>inline'
' markup</strong> and stuff to "typogrify'
'"...</p>\n',
'date':
SafeDatetime(2010, 12, 2, 10, 14),
'modified':
SafeDatetime(2010, 12, 2, 10, 20),
'tags': ['foo', 'bar', 'foobar'],
'custom_field':
'http://notmyidea.org',
}
for key, value in expected.items():
self.assertEqual(value, page.metadata[key], key)
def test_article_with_filename_metadata(self):
page = self.read_file(path='2012-11-30_md_w_filename_meta#foo-bar.md',
FILENAME_METADATA=None)
expected = {
'category': 'yeah',
'author': 'Alexis Métaireau',
}
self.assertDictHasSubset(page.metadata, expected)
page = self.read_file(
path='2012-11-30_md_w_filename_meta#foo-bar.md',
FILENAME_METADATA=r'(?P<date>\d{4}-\d{2}-\d{2}).*')
expected = {
'category': 'yeah',
'author': 'Alexis Métaireau',
'date': SafeDatetime(2012, 11, 30),
}
self.assertDictHasSubset(page.metadata, expected)
page = self.read_file(
path='2012-11-30_md_w_filename_meta#foo-bar.md',
FILENAME_METADATA=(r'(?P<date>\d{4}-\d{2}-\d{2})'
r'_(?P<Slug>.*)'
r'#(?P<MyMeta>.*)-(?P<author>.*)'))
expected = {
'category': 'yeah',
'author': 'Alexis Métaireau',
'date': SafeDatetime(2012, 11, 30),
'slug': 'md_w_filename_meta',
'mymeta': 'foo',
}
self.assertDictHasSubset(page.metadata, expected)
def test_article_with_metadata(self):
reader = readers.MarkdownReader(settings=get_settings())
content, metadata = reader.read(_path('article_with_md_extension.md'))
expected = {
'category': 'test',
'title': 'Test md File',
'summary': '<p>I have a lot to test</p>',
'date': SafeDatetime(2010, 12, 2, 10, 14),
'modified': SafeDatetime(2010, 12, 2, 10, 20),
'tags': ['foo', 'bar', 'foobar'],
}
self.assertDictHasSubset(metadata, expected)
content, metadata = reader.read(
_path('article_with_markdown_and_nonascii_summary.md'))
expected = {
'title': 'マックOS X 10.8でパイソンとVirtualenvをインストールと設定',
'summary': '<p>パイソンとVirtualenvをまっくでインストールする方法について明確に説明します。</p>',
'category': '指導書',
'date': SafeDatetime(2012, 12, 20),
'modified': SafeDatetime(2012, 12, 22),
'tags': ['パイソン', 'マック'],
'slug': 'python-virtualenv-on-mac-osx-mountain-lion-10.8',
}
self.assertDictHasSubset(metadata, expected)
def test_readfile_path_metadata_explicit_dates(self):
test_file = 'article_with_metadata_explicit_dates.html'
page = self.read_file(path=test_file, DEFAULT_DATE='fs')
expected = {
'date': SafeDatetime(2010, 12, 2, 10, 14),
'modified': SafeDatetime(2010, 12, 31, 23, 59)
}
self.assertDictHasSubset(page.metadata, expected)
def test_readfile_path_metadata_implicit_date_explicit_modified(self):
test_file = 'article_with_metadata_implicit_date_explicit_modified.html'
page = self.read_file(path=test_file, DEFAULT_DATE='fs')
expected = {
'date':
SafeDatetime.fromtimestamp(os.stat(_path(test_file)).st_mtime),
'modified': SafeDatetime(2010, 12, 2, 10, 14),
}
self.assertDictHasSubset(page.metadata, expected)
def blogger2fields(xml):
"""Opens a blogger XML file, and yield Pelican fields"""
soup = xml_to_soup(xml)
entries = soup.feed.findAll('entry')
for entry in entries:
raw_kind = entry.find('category', {
'scheme': 'http://schemas.google.com/g/2005#kind'
}).get('term')
if raw_kind == 'http://schemas.google.com/blogger/2008/kind#post':
kind = 'article'
elif raw_kind == 'http://schemas.google.com/blogger/2008/kind#comment':
kind = 'comment'
elif raw_kind == 'http://schemas.google.com/blogger/2008/kind#page':
kind = 'page'
else:
continue
try:
assert kind != 'comment'
filename = entry.find('link', {'rel': 'alternate'})['href']
filename = os.path.splitext(os.path.basename(filename))[0]
except (AssertionError, TypeError, KeyError):
filename = entry.find('id').string.split('.')[-1]
title = entry.find('title').string or ''
content = entry.find('content').string
raw_date = entry.find('published').string
if hasattr(SafeDatetime, 'fromisoformat'):
date_object = SafeDatetime.fromisoformat(raw_date)
else:
date_object = SafeDatetime.strptime(raw_date[:23],
'%Y-%m-%dT%H:%M:%S.%f')
date = date_object.strftime('%Y-%m-%d %H:%M')
author = entry.find('author').find('name').string
# blogger posts only have tags, no category
tags = [
tag.get('term') for tag in entry.findAll(
'category', {'scheme': 'http://www.blogger.com/atom/ns#'})
]
# Drafts have <app:control><app:draft>yes</app:draft></app:control>
status = 'published'
try:
if entry.find('control').find('draft').string == 'yes':
status = 'draft'
except AttributeError:
pass
yield (title, content, filename, date, author, None, tags, status,
kind, 'html')
def blogger2fields(xml):
"""Opens a blogger XML file, and yield Pelican fields"""
soup = xml_to_soup(xml)
entries = soup.feed.findAll('entry')
for entry in entries:
raw_kind = entry.find(
'category', {'scheme': 'http://schemas.google.com/g/2005#kind'}
).get('term')
if raw_kind == 'http://schemas.google.com/blogger/2008/kind#post':
kind = 'article'
elif raw_kind == 'http://schemas.google.com/blogger/2008/kind#comment':
kind = 'comment'
elif raw_kind == 'http://schemas.google.com/blogger/2008/kind#page':
kind = 'page'
else:
continue
try:
assert kind != 'comment'
filename = entry.find('link', {'rel': 'alternate'})['href']
filename = os.path.splitext(os.path.basename(filename))[0]
except (AssertionError, TypeError, KeyError):
filename = entry.find('id').string.split('.')[-1]
title = entry.find('title').string or ''
content = entry.find('content').string
raw_date = entry.find('published').string
if hasattr(SafeDatetime, 'fromisoformat'):
date_object = SafeDatetime.fromisoformat(raw_date)
else:
date_object = SafeDatetime.strptime(
raw_date[:23], '%Y-%m-%dT%H:%M:%S.%f')
date = date_object.strftime('%Y-%m-%d %H:%M')
author = entry.find('author').find('name').string
# blogger posts only have tags, no category
tags = [tag.get('term') for tag in entry.findAll(
'category', {'scheme': 'http://www.blogger.com/atom/ns#'})]
# Drafts have <app:control><app:draft>yes</app:draft></app:control>
status = 'published'
try:
if entry.find('control').find('draft').string == 'yes':
status = 'draft'
except AttributeError:
pass
yield (title, content, filename, date, author, None, tags, status,
kind, 'html')
def __init__(self, *args, **kwargs):
super(Article, self).__init__(*args, **kwargs)
# handle WITH_FUTURE_DATES (designate article to draft based on date)
if not self.settings['WITH_FUTURE_DATES'] and hasattr(self, 'date'):
if self.date.tzinfo is None:
now = SafeDatetime.now()
else:
now = SafeDatetime.utcnow().replace(tzinfo=pytz.utc)
if self.date > now:
self.status = 'draft'
# if we are a draft and there is no date provided, set max datetime
if not hasattr(self, 'date') and self.status == 'draft':
self.date = SafeDatetime.max
def __init__(self, *args, **kwargs):
super(Article, self).__init__(*args, **kwargs)
# handle WITH_FUTURE_DATES (designate article to draft based on date)
if not self.settings['WITH_FUTURE_DATES'] and hasattr(self, 'date'):
if self.date.tzinfo is None:
now = SafeDatetime.now()
else:
now = SafeDatetime.utcnow().replace(tzinfo=pytz.utc)
if self.date > now:
self.status = 'draft'
# if we are a draft and there is no date provided, set max datetime
if not hasattr(self, 'date') and self.status == 'draft':
self.date = SafeDatetime.max
def path_metadata(full_path, source_path, settings=None):
metadata = {}
if settings:
if settings.get("DEFAULT_DATE", None) == "fs":
metadata["date"] = SafeDatetime.fromtimestamp(os.stat(full_path).st_ctime)
metadata.update(settings.get("EXTRA_PATH_METADATA", {}).get(source_path, {}))
return metadata
def posterous2fields(api_token, email, password):
"""Imports posterous posts"""
import base64
from datetime import timedelta
try:
# py3k import
import json
except ImportError:
# py2 import
import simplejson as json
try:
# py3k import
import urllib.request as urllib_request
except ImportError:
# py2 import
import urllib2 as urllib_request
def get_posterous_posts(api_token, email, password, page=1):
base64string = base64.encodestring(("%s:%s" % (email, password)).encode("utf-8")).replace("\n", "")
url = ("http://posterous.com/api/v2/users/me/sites/primary/" "posts?api_token=%s&page=%d") % (api_token, page)
request = urllib_request.Request(url)
request.add_header("Authorization", "Basic %s" % base64string.decode())
handle = urllib_request.urlopen(request)
posts = json.loads(handle.read().decode("utf-8"))
return posts
page = 1
posts = get_posterous_posts(api_token, email, password, page)
while len(posts) > 0:
posts = get_posterous_posts(api_token, email, password, page)
page += 1
for post in posts:
slug = post.get("slug")
if not slug:
slug = slugify(post.get("title"))
tags = [tag.get("name") for tag in post.get("tags")]
raw_date = post.get("display_date")
date_object = SafeDatetime.strptime(raw_date[:-6], "%Y/%m/%d %H:%M:%S")
offset = int(raw_date[-5:])
delta = timedelta(hours=(offset / 100))
date_object -= delta
date = date_object.strftime("%Y-%m-%d %H:%M")
kind = "article" # TODO: Recognise pages
status = "published" # TODO: Find a way for draft posts
yield (
post.get("title"),
post.get("body_cleaned"),
slug,
date,
post.get("user").get("display_name"),
[],
tags,
status,
kind,
"html",
)
def merge_date_url(value, url):
"""
Given a Pelican setting URL that contains a placeholder for a date, and a
date, it will combine the two to return the resulting URL.
Args
----
value (datetime.datetime): a date
url (string): a Pelican URL setting
Returns
-------
string: combined URL
"""
try:
return url.format(date=value)
except ValueError:
# will throw a "ValueError" if the value is a datetime.datetime and the url
# contains a "-" (e.g. "{date:%-d}") (used in Pelican to strip the leading
# zero)
try:
return url.format(
date=SafeDatetime(value.year, value.month, value.day))
except ValueError as e:
logger.error(
"%s ValueError. value: %s, type(value): %s, url: %s",
LOG_PREFIX,
value,
type(value),
url,
)
raise e
def test_article_extra_path_metadata_dont_overwrite(self):
# EXTRA_PATH_METADATA['author'] should get ignored
# since we don't overwrite already set values
input_file_path = '2012-11-29_rst_w_filename_meta#foo-bar.rst'
page = self.read_file(
path=input_file_path,
FILENAME_METADATA=(r'(?P<date>\d{4}-\d{2}-\d{2})'
r'_(?P<Slug>.*)'
r'#(?P<MyMeta>.*)-(?P<orginalauthor>.*)'),
EXTRA_PATH_METADATA={
input_file_path: {
'author': 'Charlès Overwrite',
'key-1b': 'value-1b'
}
})
expected = {
'category': 'yeah',
'author': 'Alexis Métaireau',
'title': 'Rst with filename metadata',
'date': SafeDatetime(2012, 11, 29),
'slug': 'rst_w_filename_meta',
'mymeta': 'foo',
'reader': 'rst',
'key-1b': 'value-1b'
}
self.assertDictHasSubset(page.metadata, expected)
def wp2fields(xml, wp_custpost=False):
"""Opens a wordpress XML file, and yield Pelican fields"""
soup = xml_to_soup(xml)
items = soup.rss.channel.findAll('item')
for item in items:
if item.find('status').string in ["publish", "draft"]:
try:
# Use HTMLParser due to issues with BeautifulSoup 3
title = unescape(item.title.contents[0])
except IndexError:
title = 'No title [%s]' % item.find('post_name').string
logger.warning('Post "%s" is lacking a proper title', title)
post_name = item.find('post_name').string
post_id = item.find('post_id').string
filename = get_filename(post_name, post_id)
content = item.find('encoded').string
raw_date = item.find('post_date').string
if raw_date == u'0000-00-00 00:00:00':
date = None
else:
date_object = SafeDatetime.strptime(raw_date,
'%Y-%m-%d %H:%M:%S')
date = date_object.strftime('%Y-%m-%d %H:%M')
author = item.find('creator').string
categories = [
cat.string
for cat in item.findAll('category', {'domain': 'category'})
]
tags = [
tag.string
for tag in item.findAll('category', {'domain': 'post_tag'})
]
# To publish a post the status should be 'published'
status = 'published' if item.find('status').string == "publish" \
else item.find('status').string
kind = 'article'
post_type = item.find('post_type').string
if post_type == 'page':
kind = 'page'
elif wp_custpost:
if post_type == 'post':
pass
# Old behaviour was to name everything not a page as an
# article.Theoretically all attachments have status == inherit
# so no attachments should be here. But this statement is to
# maintain existing behaviour in case that doesn't hold true.
elif post_type == 'attachment':
pass
else:
kind = post_type
yield (title, content, filename, date, author, categories, tags,
status, kind, 'wp-html')
def test_article_with_footnote(self):
settings = get_settings()
ec = settings['MARKDOWN']['extension_configs']
ec['markdown.extensions.footnotes'] = {'SEPARATOR': '-'}
reader = readers.MarkdownReader(settings)
content, metadata = reader.read(
_path('article_with_markdown_and_footnote.md'))
expected_content = (
'<p>This is some content'
'<sup id="fnref-1"><a class="footnote-ref" href="#fn-1"'
'>1</a></sup>'
' with some footnotes'
'<sup id="fnref-footnote"><a class="footnote-ref" '
'href="#fn-footnote">2</a></sup></p>\n'
'<div class="footnote">\n'
'<hr>\n<ol>\n<li id="fn-1">\n'
'<p>Numbered footnote '
'<a class="footnote-backref" href="#fnref-1" '
'title="Jump back to footnote 1 in the text">↩</a></p>\n'
'</li>\n<li id="fn-footnote">\n'
'<p>Named footnote '
'<a class="footnote-backref" href="#fnref-footnote"'
' title="Jump back to footnote 2 in the text">↩</a></p>\n'
'</li>\n</ol>\n</div>')
expected_metadata = {
'title':
'Article with markdown containing footnotes',
'summary': ('<p>Summary with <strong>inline</strong> markup '
'<em>should</em> be supported.</p>'),
'date':
SafeDatetime(2012, 10, 31),
'modified':
SafeDatetime(2012, 11, 1),
'multiline': [
'Line Metadata should be handle properly.',
'See syntax of Meta-Data extension of '
'Python Markdown package:',
'If a line is indented by 4 or more spaces,',
'that line is assumed to be an additional line of the value',
'for the previous keyword.',
'A keyword may have as many lines as desired.',
]
}
self.assertEqual(content, expected_content)
self.assertDictHasSubset(metadata, expected_metadata)
def path_metadata(full_path, source_path, settings=None):
metadata = {}
if settings:
if settings.get('DEFAULT_DATE', None) == 'fs':
metadata['date'] = SafeDatetime.fromtimestamp(
os.stat(full_path).st_mtime)
metadata.update(settings.get('EXTRA_PATH_METADATA', {}).get(
source_path, {}))
return metadata
def path_metadata(full_path, source_path, settings=None):
metadata = {}
if settings:
if settings.get('DEFAULT_DATE', None) == 'fs':
metadata['date'] = SafeDatetime.fromtimestamp(
os.stat(full_path).st_mtime)
metadata.update(
settings.get('EXTRA_PATH_METADATA', {}).get(source_path, {}))
return metadata
def test_article_with_footnote(self):
reader = readers.MarkdownReader(settings=get_settings())
content, metadata = reader.read(
_path('article_with_markdown_and_footnote.md'))
expected_content = (
'<p>This is some content'
'<sup id="fnref:1"><a class="footnote-ref" href="#fn:1" '
'rel="footnote">1</a></sup>'
' with some footnotes'
'<sup id="fnref:footnote"><a class="footnote-ref" '
'href="#fn:footnote" rel="footnote">2</a></sup></p>\n'
'<div class="footnote">\n'
'<hr />\n<ol>\n<li id="fn:1">\n'
'<p>Numbered footnote '
'<a class="footnote-backref" href="#fnref:1" rev="footnote" '
'title="Jump back to footnote 1 in the text">↩</a></p>\n'
'</li>\n<li id="fn:footnote">\n'
'<p>Named footnote '
'<a class="footnote-backref" href="#fnref:footnote" rev="footnote"'
' title="Jump back to footnote 2 in the text">↩</a></p>\n'
'</li>\n</ol>\n</div>')
expected_metadata = {
'title':
'Article with markdown containing footnotes',
'summary': ('<p>Summary with <strong>inline</strong> markup '
'<em>should</em> be supported.</p>'),
'date':
SafeDatetime(2012, 10, 31),
'modified':
SafeDatetime(2012, 11, 1),
'slug':
'article-with-markdown-containing-footnotes',
'multiline': [
'Line Metadata should be handle properly.',
'See syntax of Meta-Data extension of Python Markdown package:',
'If a line is indented by 4 or more spaces,',
'that line is assumed to be an additional line of the value',
'for the previous keyword.',
'A keyword may have as many lines as desired.',
]
}
self.assertEqual(content, expected_content)
for key, value in metadata.items():
self.assertEqual(value, expected_metadata[key], key)
def test_datetime(self):
# If DATETIME is set to a tuple, it should be used to override LOCALE
dt = SafeDatetime(2015, 9, 13)
page_kwargs = self._copy_page_kwargs()
# set its date to dt
page_kwargs['metadata']['date'] = dt
page = Page(**page_kwargs)
# page.locale_date is a unicode string in both python2 and python3
dt_date = dt.strftime(DEFAULT_CONFIG['DEFAULT_DATE_FORMAT'])
# dt_date is a byte string in python2, and a unicode string in python3
# Let's make sure it is a unicode string (relies on python 3.3 supporting the u prefix)
if type(dt_date) != type(u''):
# python2:
dt_date = unicode(dt_date, 'utf8')
self.assertEqual(page.locale_date, dt_date)
page_kwargs['settings'] = get_settings()
# I doubt this can work on all platforms ...
if platform == "win32":
locale = 'jpn'
else:
locale = 'ja_JP.utf8'
page_kwargs['settings']['DATE_FORMATS'] = {
'jp': (locale, '%Y-%m-%d(%a)')
}
page_kwargs['metadata']['lang'] = 'jp'
import locale as locale_module
try:
page = Page(**page_kwargs)
self.assertEqual(page.locale_date, '2015-09-13(\u65e5)')
except locale_module.Error:
# The constructor of ``Page`` will try to set the locale to
# ``ja_JP.utf8``. But this attempt will failed when there is no
# such locale in the system. You can see which locales there are
# in your system with ``locale -a`` command.
#
# Until we find some other method to test this functionality, we
# will simply skip this test.
unittest.skip("There is no locale %s in this system." % locale)
def wp2fields(xml, wp_custpost=False):
"""Opens a wordpress XML file, and yield Pelican fields"""
soup = xml_to_soup(xml)
items = soup.rss.channel.findAll('item')
for item in items:
if item.find('status').string in ["publish", "draft"]:
try:
# Use HTMLParser due to issues with BeautifulSoup 3
title = unescape(item.title.contents[0])
except IndexError:
title = 'No title [%s]' % item.find('post_name').string
logger.warning('Post "%s" is lacking a proper title', title)
post_name = item.find('post_name').string
post_id = item.find('post_id').string
filename = get_filename(post_name, post_id)
content = item.find('encoded').string
raw_date = item.find('post_date').string
if raw_date == u'0000-00-00 00:00:00':
date = None
else:
date_object = SafeDatetime.strptime(
raw_date, '%Y-%m-%d %H:%M:%S')
date = date_object.strftime('%Y-%m-%d %H:%M')
author = item.find('creator').string
categories = [cat.string for cat
in item.findAll('category', {'domain': 'category'})]
tags = [tag.string for tag
in item.findAll('category', {'domain': 'post_tag'})]
# To publish a post the status should be 'published'
status = 'published' if item.find('status').string == "publish" \
else item.find('status').string
kind = 'article'
post_type = item.find('post_type').string
if post_type == 'page':
kind = 'page'
elif wp_custpost:
if post_type == 'post':
pass
# Old behaviour was to name everything not a page as an
# article.Theoretically all attachments have status == inherit
# so no attachments should be here. But this statement is to
# maintain existing behaviour in case that doesn't hold true.
elif post_type == 'attachment':
pass
else:
kind = post_type
yield (title, content, filename, date, author, categories,
tags, status, kind, 'wp-html')
def test_datetime(self):
# If DATETIME is set to a tuple, it should be used to override LOCALE
dt = SafeDatetime(2015, 9, 13)
page_kwargs = self._copy_page_kwargs()
# set its date to dt
page_kwargs['metadata']['date'] = dt
page = Page(**page_kwargs)
# page.locale_date is a unicode string in both python2 and python3
dt_date = dt.strftime(DEFAULT_CONFIG['DEFAULT_DATE_FORMAT'])
# dt_date is a byte string in python2, and a unicode string in python3
# Let's make sure it is a unicode string (relies on python 3.3 supporting the u prefix)
if type(dt_date) != type(u''):
# python2:
dt_date = unicode(dt_date, 'utf8')
self.assertEqual(page.locale_date, dt_date )
page_kwargs['settings'] = get_settings()
# I doubt this can work on all platforms ...
if platform == "win32":
locale = 'jpn'
else:
locale = 'ja_JP.utf8'
page_kwargs['settings']['DATE_FORMATS'] = {'jp': (locale,
'%Y-%m-%d(%a)')}
page_kwargs['metadata']['lang'] = 'jp'
import locale as locale_module
try:
page = Page(**page_kwargs)
self.assertEqual(page.locale_date, '2015-09-13(\u65e5)')
except locale_module.Error:
# The constructor of ``Page`` will try to set the locale to
# ``ja_JP.utf8``. But this attempt will failed when there is no
# such locale in the system. You can see which locales there are
# in your system with ``locale -a`` command.
#
# Until we find some other method to test this functionality, we
# will simply skip this test.
unittest.skip("There is no locale %s in this system." % locale)
def datetime_from_period(value):
"""
Converts "period" into a datetime object.
On yearly/monthly/daily archive pages, a "period" object is supplied so you
know what timeperiod the particular archive page is for. This converts it
to a datetime.datetime object, so it can be further processed.
If a month is not provided (i.e. the period is for a yearly archive),
January is assumed. If a day is not provided (i.e. the period is for a
yearly or monthly archive), the 1st is assumed.
You can also generate a tuple of (up to three) integers to get a datetime
out, using the integer representation for the month (1=January, etc).
If passes a single integer, it is assumed to represent a year.
Args
----
value (tuple or int): input period
Returns
-------
datetime.datetime: value converted
"""
if isinstance(value, int):
value = (value, )
if len(value) >= 2 and isinstance(value[1], int):
placeholder_month = SafeDatetime(2021, value[1], 1).strftime("%B")
elif len(value) == 1:
placeholder_month = SafeDatetime(2021, 1, 1).strftime("%B")
else:
placeholder_month = value[1]
new_value = " ".join((
str(value[0]),
placeholder_month,
str(value[2]) if len(value) >= 3 else "1",
))
new_datetime = SafeDatetime.strptime(new_value, "%Y %B %d")
return new_datetime
def posterous2fields(api_token, email, password):
"""Imports posterous posts"""
import base64
from datetime import timedelta
try:
# py3k import
import json
except ImportError:
# py2 import
import simplejson as json
try:
# py3k import
import urllib.request as urllib_request
except ImportError:
# py2 import
import urllib2 as urllib_request
def get_posterous_posts(api_token, email, password, page=1):
base64string = base64.encodestring(
("%s:%s" % (email, password)).encode('utf-8')).replace('\n', '')
url = ("http://posterous.com/api/v2/users/me/sites/primary/"
"posts?api_token=%s&page=%d") % (api_token, page)
request = urllib_request.Request(url)
request.add_header('Authorization', 'Basic %s' % base64string.decode())
handle = urllib_request.urlopen(request)
posts = json.loads(handle.read().decode('utf-8'))
return posts
page = 1
posts = get_posterous_posts(api_token, email, password, page)
settings = read_settings()
subs = settings['SLUG_REGEX_SUBSTITUTIONS']
while len(posts) > 0:
posts = get_posterous_posts(api_token, email, password, page)
page += 1
for post in posts:
slug = post.get('slug')
if not slug:
slug = slugify(post.get('title'), regex_subs=subs)
tags = [tag.get('name') for tag in post.get('tags')]
raw_date = post.get('display_date')
date_object = SafeDatetime.strptime(
raw_date[:-6], '%Y/%m/%d %H:%M:%S')
offset = int(raw_date[-5:])
delta = timedelta(hours=(offset / 100))
date_object -= delta
date = date_object.strftime('%Y-%m-%d %H:%M')
kind = 'article' # TODO: Recognise pages
status = 'published' # TODO: Find a way for draft posts
yield (post.get('title'), post.get('body_cleaned'),
slug, date, post.get('user').get('display_name'),
[], tags, status, kind, 'html')
def posterous2fields(api_token, email, password):
"""Imports posterous posts"""
import base64
from datetime import timedelta
try:
# py3k import
import json
except ImportError:
# py2 import
import simplejson as json
try:
# py3k import
import urllib.request as urllib_request
except ImportError:
# py2 import
import urllib2 as urllib_request
def get_posterous_posts(api_token, email, password, page=1):
base64string = base64.encodestring(
("%s:%s" % (email, password)).encode('utf-8')).replace('\n', '')
url = ("http://posterous.com/api/v2/users/me/sites/primary/"
"posts?api_token=%s&page=%d") % (api_token, page)
request = urllib_request.Request(url)
request.add_header('Authorization', 'Basic %s' % base64string.decode())
handle = urllib_request.urlopen(request)
posts = json.loads(handle.read().decode('utf-8'))
return posts
page = 1
posts = get_posterous_posts(api_token, email, password, page)
settings = read_settings()
subs = settings['SLUG_REGEX_SUBSTITUTIONS']
while len(posts) > 0:
posts = get_posterous_posts(api_token, email, password, page)
page += 1
for post in posts:
slug = post.get('slug')
if not slug:
slug = slugify(post.get('title'), regex_subs=subs)
tags = [tag.get('name') for tag in post.get('tags')]
raw_date = post.get('display_date')
date_object = SafeDatetime.strptime(raw_date[:-6],
'%Y/%m/%d %H:%M:%S')
offset = int(raw_date[-5:])
delta = timedelta(hours=(offset / 100))
date_object -= delta
date = date_object.strftime('%Y-%m-%d %H:%M')
kind = 'article' # TODO: Recognise pages
status = 'published' # TODO: Find a way for draft posts
yield (post.get('title'), post.get('body_cleaned'), slug, date,
post.get('user').get('display_name'), [], tags, status,
kind, 'html')
def test_typed_metadata():
content, metadata = read_content_metadata('metadata.md')
expected = {
'title': 'Metadata',
'list': ['a', 'b', 'c'],
'date': SafeDatetime(2017, 1, 6, 22, 24),
'int': 42,
'bool': False,
'summary': '<p>a summary</p>',
}
assert_dict_contains(metadata, expected)
def default_metadata(settings=None, process=None):
metadata = {}
if settings:
if 'DEFAULT_CATEGORY' in settings:
value = settings['DEFAULT_CATEGORY']
if process:
value = process('category', value)
metadata['category'] = value
if settings.get('DEFAULT_DATE', None) and settings['DEFAULT_DATE'] != 'fs':
metadata['date'] = SafeDatetime(*settings['DEFAULT_DATE'])
return metadata
def test_article_with_metadata_and_contents_attrib(self):
page = self.read_file(path='article_with_metadata_and_contents.html')
expected = {
'category': 'yeah',
'author': 'Alexis Métaireau',
'title': 'This is a super article !',
'summary': 'Summary and stuff',
'date': SafeDatetime(2010, 12, 2, 10, 14),
'tags': ['foo', 'bar', 'foobar'],
'custom_field': 'http://notmyidea.org',
}
self.assertDictHasSubset(page.metadata, expected)
def posterous2fields(api_token, email, password):
"""Imports posterous posts"""
import base64
from datetime import timedelta
try:
# py3k import
import json
except ImportError:
# py2 import
import simplejson as json
try:
# py3k import
import urllib.request as urllib_request
except ImportError:
# py2 import
import urllib2 as urllib_request
def get_posterous_posts(api_token, email, password, page=1):
base64string = base64.encodestring(
("%s:%s" % (email, password)).encode('utf-8')).replace(b'\n', b'')
url = "http://posterous.com/api/v2/users/me/sites/primary/posts?api_token=%s&page=%d" % (
api_token, page)
request = urllib_request.Request(url)
request.add_header("Authorization", "Basic %s" % base64string.decode())
handle = urllib_request.urlopen(request)
posts = json.loads(handle.read().decode('utf-8'))
return posts
page = 1
posts = get_posterous_posts(api_token, email, password, page)
while len(posts) > 0:
posts = get_posterous_posts(api_token, email, password, page)
page += 1
for post in posts:
slug = post.get('slug')
if not slug:
slug = slugify(post.get('title'))
tags = [tag.get('name') for tag in post.get('tags')]
raw_date = post.get('display_date')
date_object = SafeDatetime.strptime(raw_date[:-6],
"%Y/%m/%d %H:%M:%S")
offset = int(raw_date[-5:])
delta = timedelta(hours=offset / 100)
date_object -= delta
date = date_object.strftime("%Y-%m-%d %H:%M")
kind = 'article' # TODO: Recognise pages
yield (post.get('title'), post.get('body_cleaned'), slug, date,
post.get('user').get('display_name'), [], tags, kind,
"html")
def url_format(self):
"""Returns the URL, formatted with the proper values"""
metadata = copy.copy(self.metadata)
path = self.metadata.get('path', self.get_relative_source_path())
metadata.update({
'path': path_to_url(path),
'slug': getattr(self, 'slug', ''),
'lang': getattr(self, 'lang', 'en'),
'date': getattr(self, 'date', SafeDatetime.now()),
'author': self.author.slug if hasattr(self, 'author') else '',
'category': self.category.slug if hasattr(self, 'category') else ''
})
return metadata
def url_format(self):
"""Returns the URL, formatted with the proper values"""
metadata = copy.copy(self.metadata)
path = self.metadata.get('path', self.get_relative_source_path())
metadata.update({
'path': path_to_url(path),
'slug': getattr(self, 'slug', ''),
'lang': getattr(self, 'lang', 'en'),
'date': getattr(self, 'date', SafeDatetime.now()),
'author': self.author.slug if hasattr(self, 'author') else '',
'category': self.category.slug if hasattr(self, 'category') else ''
})
return metadata
def test_article_with_metadata(self):
page = self.read_file(path='article_with_metadata.html')
expected = {
'category': 'yeah',
'author': 'Alexis Métaireau',
'title': 'This is a super article !',
'summary': 'Summary and stuff',
'date': SafeDatetime(2010, 12, 2, 10, 14),
'tags': ['foo', 'bar', 'foobar'],
'custom_field': 'http://notmyidea.org',
}
for key, value in expected.items():
self.assertEqual(value, page.metadata[key], key)
def test_article_with_optional_filename_metadata(self):
page = self.read_file(path='2012-11-30_md_w_filename_meta#foo-bar.md',
FILENAME_METADATA='(?P<date>\d{4}-\d{2}-\d{2})?')
expected = {
'date': SafeDatetime(2012, 11, 30),
'reader': 'markdown',
}
self.assertDictHasSubset(page.metadata, expected)
page = self.read_file(path='empty.md',
FILENAME_METADATA='(?P<date>\d{4}-\d{2}-\d{2})?')
expected = {
'reader': 'markdown',
}
self.assertDictHasSubset(page.metadata, expected)
self.assertNotIn('date', page.metadata, 'Date should not be set.')
def url_format(self):
"""Returns the URL, formatted with the proper values"""
metadata = copy.copy(self.metadata)
path = self.metadata.get("path", self.get_relative_source_path())
metadata.update(
{
"path": path_to_url(path),
"slug": getattr(self, "slug", ""),
"lang": getattr(self, "lang", "en"),
"date": getattr(self, "date", SafeDatetime.now()),
"author": self.author.slug if hasattr(self, "author") else "",
"tag": self.tag.slug if hasattr(self, "tag") else "",
"category": self.category.slug if hasattr(self, "category") else "",
}
)
return metadata
def default_metadata(settings=None, process=None):
metadata = {}
if settings:
for name, value in dict(settings.get('DEFAULT_METADATA', {})).items():
if process:
value = process(name, value)
metadata[name] = value
if 'DEFAULT_CATEGORY' in settings:
value = settings['DEFAULT_CATEGORY']
if process:
value = process('category', value)
metadata['category'] = value
if settings.get('DEFAULT_DATE', None) and \
settings['DEFAULT_DATE'] != 'fs':
metadata['date'] = SafeDatetime(*settings['DEFAULT_DATE'])
return metadata
def test_article_extra_path_metadata(self):
input_with_metadata = '2012-11-29_rst_w_filename_meta#foo-bar.rst'
page_metadata = self.read_file(
path=input_with_metadata,
FILENAME_METADATA=(
r'(?P<date>\d{4}-\d{2}-\d{2})'
r'_(?P<Slug>.*)'
r'#(?P<MyMeta>.*)-(?P<author>.*)'
),
EXTRA_PATH_METADATA={
input_with_metadata: {
'key-1a': 'value-1a',
'key-1b': 'value-1b'
}
}
)
expected_metadata = {
'category': 'yeah',
'author': 'Alexis Métaireau',
'title': 'Rst with filename metadata',
'date': SafeDatetime(2012, 11, 29),
'slug': 'rst_w_filename_meta',
'mymeta': 'foo',
'reader': 'rst',
'key-1a': 'value-1a',
'key-1b': 'value-1b'
}
self.assertDictHasSubset(page_metadata.metadata, expected_metadata)
input_file_path_without_metadata = 'article.rst'
page_without_metadata = self.read_file(
path=input_file_path_without_metadata,
EXTRA_PATH_METADATA={
input_file_path_without_metadata: {
'author': 'Charlès Overwrite'
}
}
)
expected_without_metadata = {
'category': 'misc',
'author': 'Charlès Overwrite',
'title': 'Article title',
'reader': 'rst',
}
self.assertDictHasSubset(
page_without_metadata.metadata,
expected_without_metadata)
def path_metadata(full_path, source_path, settings=None):
metadata = {}
if settings:
if settings.get('DEFAULT_DATE', None) == 'fs':
metadata['date'] = SafeDatetime.fromtimestamp(
os.stat(full_path).st_mtime)
# Apply EXTRA_PATH_METADATA for the source path and the paths of any
# parent directories. Sorting EPM first ensures that the most specific
# path wins conflicts.
epm = settings.get('EXTRA_PATH_METADATA', {})
for path, meta in sorted(epm.items()):
# Enforce a trailing slash when checking for parent directories.
# This prevents false positives when one file or directory's name
# is a prefix of another's.
dirpath = os.path.join(path, '')
if source_path == path or source_path.startswith(dirpath):
metadata.update(meta)
return metadata
def url_format(self):
"""Returns the URL, formatted with the proper values"""
metadata = copy.copy(self.metadata)
path = self.metadata.get('path', self.get_relative_source_path())
default_category = self.settings['DEFAULT_CATEGORY']
slug_substitutions = self.settings.get('SLUG_SUBSTITUTIONS', ())
metadata.update({
'path': path_to_url(path),
'slug': getattr(self, 'slug', ''),
'lang': getattr(self, 'lang', 'en'),
'date': getattr(self, 'date', SafeDatetime.now()),
'author': slugify(
getattr(self, 'author', ''),
slug_substitutions
),
'category': slugify(
getattr(self, 'category', default_category),
slug_substitutions
)
})
return metadata
def url_format(self):
"""Returns the URL, formatted with the proper values"""
metadata = copy.copy(self.metadata)
path = self.metadata.get('path', self.get_relative_source_path())
default_category = self.settings['DEFAULT_CATEGORY']
slug_substitutions = self.settings.get('SLUG_SUBSTITUTIONS', ())
metadata.update({
'path': path_to_url(path),
'slug': getattr(self, 'slug', ''),
'lang': getattr(self, 'lang', 'en'),
'date': getattr(self, 'date', SafeDatetime.now()),
'author': slugify(
getattr(self, 'author', ''),
slug_substitutions
),
'category': slugify(
getattr(self, 'category', default_category),
slug_substitutions
)
})
return metadata
def parse(self):
"""Imports posterous posts"""
from datetime import timedelta
page = 1
posts = self._get_posterous_posts(page)
settings = read_settings()
subs = settings["SLUG_REGEX_SUBSTITUTIONS"]
while len(posts) > 0:
posts = self._get_posterous_posts(page)
page += 1
for post in posts:
slug = post.get("slug")
if not slug:
slug = slugify(post.get("title"), regex_subs=subs)
tags = [tag.get("name") for tag in post.get("tags")]
raw_date = post.get("display_date")
date_object = SafeDatetime.strptime(
raw_date[:-6], "%Y/%m/%d %H:%M:%S"
)
offset = int(raw_date[-5:])
delta = timedelta(hours=(offset / 100))
date_object -= delta
date = date_object.strftime("%Y-%m-%d %H:%M")
kind = "article" # TODO: Recognise pages
status = "published" # TODO: Find a way for draft posts
yield blog2pelican.entities.content.Content(
title=post.get("title"),
content=post.get("body_cleaned"),
slug=slug,
date=date,
author=post.get("user").get("display_name"),
categories=[],
tags=tags,
status=status,
kind=kind,
markup="html",
)
def __init__(self, content, metadata=None, settings=None,
source_path=None, context=None):
if metadata is None:
metadata = {}
if settings is None:
settings = copy.deepcopy(DEFAULT_CONFIG)
self.settings = settings
self._content = content
if context is None:
context = {}
self._context = context
self.translations = []
local_metadata = dict(settings['DEFAULT_METADATA'])
local_metadata.update(metadata)
# set metadata as attributes
for key, value in local_metadata.items():
if key in ('save_as', 'url'):
key = 'override_' + key
setattr(self, key.lower(), value)
# also keep track of the metadata attributes available
self.metadata = local_metadata
#default template if it's not defined in page
self.template = self._get_template()
# First, read the authors from "authors", if not, fallback to "author"
# and if not use the settings defined one, if any.
if not hasattr(self, 'author'):
if hasattr(self, 'authors'):
self.author = self.authors[0]
elif 'AUTHOR' in settings:
self.author = Author(settings['AUTHOR'], settings)
if not hasattr(self, 'authors') and hasattr(self, 'author'):
self.authors = [self.author]
# XXX Split all the following code into pieces, there is too much here.
# manage languages
self.in_default_lang = True
if 'DEFAULT_LANG' in settings:
default_lang = settings['DEFAULT_LANG'].lower()
if not hasattr(self, 'lang'):
self.lang = default_lang
self.in_default_lang = (self.lang == default_lang)
# create the slug if not existing, generate slug according to
# setting of SLUG_ATTRIBUTE
if not hasattr(self, 'slug'):
if settings['SLUGIFY_SOURCE'] == 'title' and hasattr(self, 'title'):
self.slug = slugify(self.title,
settings.get('SLUG_SUBSTITUTIONS', ()))
elif settings['SLUGIFY_SOURCE'] == 'basename' and source_path != None:
basename = os.path.basename(os.path.splitext(source_path)[0])
self.slug = slugify(basename,
settings.get('SLUG_SUBSTITUTIONS', ()))
self.source_path = source_path
# manage the date format
if not hasattr(self, 'date_format'):
if hasattr(self, 'lang') and self.lang in settings['DATE_FORMATS']:
self.date_format = settings['DATE_FORMATS'][self.lang]
else:
self.date_format = settings['DEFAULT_DATE_FORMAT']
if isinstance(self.date_format, tuple):
locale_string = self.date_format[0]
if sys.version_info < (3, ) and isinstance(locale_string,
six.text_type):
locale_string = locale_string.encode('ascii')
locale.setlocale(locale.LC_ALL, locale_string)
self.date_format = self.date_format[1]
# manage timezone
default_timezone = settings.get('TIMEZONE', 'UTC')
timezone = getattr(self, 'timezone', default_timezone)
if hasattr(self, 'date'):
self.date = set_date_tzinfo(self.date, timezone)
self.locale_date = strftime(self.date, self.date_format)
if hasattr(self, 'modified'):
self.modified = set_date_tzinfo(self.modified, timezone)
self.locale_modified = strftime(self.modified, self.date_format)
# manage status
if not hasattr(self, 'status'):
self.status = settings['DEFAULT_STATUS']
if not settings['WITH_FUTURE_DATES']:
if hasattr(self, 'date') and self.date > SafeDatetime.now():
self.status = 'draft'
# store the summary metadata if it is set
if 'summary' in metadata:
self._summary = metadata['summary']
signals.content_object_init.send(self)
def tumblr2fields(api_key, blogname):
""" Imports Tumblr posts (API v2)"""
try:
# py3k import
import json
except ImportError:
# py2 import
import simplejson as json
try:
# py3k import
import urllib.request as urllib_request
except ImportError:
# py2 import
import urllib2 as urllib_request
def get_tumblr_posts(api_key, blogname, offset=0):
url = ("http://api.tumblr.com/v2/blog/%s.tumblr.com/"
"posts?api_key=%s&offset=%d&filter=raw") % (
blogname, api_key, offset)
request = urllib_request.Request(url)
handle = urllib_request.urlopen(request)
posts = json.loads(handle.read().decode('utf-8'))
return posts.get('response').get('posts')
offset = 0
posts = get_tumblr_posts(api_key, blogname, offset)
settings = read_settings()
subs = settings['SLUG_REGEX_SUBSTITUTIONS']
while len(posts) > 0:
for post in posts:
title = \
post.get('title') or \
post.get('source_title') or \
post.get('type').capitalize()
slug = post.get('slug') or slugify(title, regex_subs=subs)
tags = post.get('tags')
timestamp = post.get('timestamp')
date = SafeDatetime.fromtimestamp(int(timestamp)).strftime(
"%Y-%m-%d %H:%M:%S")
slug = SafeDatetime.fromtimestamp(int(timestamp)).strftime(
"%Y-%m-%d-") + slug
format = post.get('format')
content = post.get('body')
type = post.get('type')
if type == 'photo':
if format == 'markdown':
fmtstr = ''
else:
fmtstr = '<img alt="%s" src="%s" />'
content = ''
for photo in post.get('photos'):
content += '\n'.join(
fmtstr % (photo.get('caption'),
photo.get('original_size').get('url')))
content += '\n\n' + post.get('caption')
elif type == 'quote':
if format == 'markdown':
fmtstr = '\n\n— %s'
else:
fmtstr = '<p>— %s</p>'
content = post.get('text') + fmtstr % post.get('source')
elif type == 'link':
if format == 'markdown':
fmtstr = '[via](%s)\n\n'
else:
fmtstr = '<p><a href="%s">via</a></p>\n'
content = fmtstr % post.get('url') + post.get('description')
elif type == 'audio':
if format == 'markdown':
fmtstr = '[via](%s)\n\n'
else:
fmtstr = '<p><a href="%s">via</a></p>\n'
content = fmtstr % post.get('source_url') + \
post.get('caption') + \
post.get('player')
elif type == 'video':
if format == 'markdown':
fmtstr = '[via](%s)\n\n'
else:
fmtstr = '<p><a href="%s">via</a></p>\n'
source = fmtstr % post.get('source_url')
caption = post.get('caption')
players = '\n'.join(player.get('embed_code')
for player in post.get('player'))
content = source + caption + players
elif type == 'answer':
title = post.get('question')
content = ('<p>'
'<a href="%s" rel="external nofollow">%s</a>'
': %s'
'</p>\n'
' %s' % (post.get('asking_name'),
post.get('asking_url'),
post.get('question'),
post.get('answer')))
content = content.rstrip() + '\n'
kind = 'article'
status = 'published' # TODO: Find a way for draft posts
yield (title, content, slug, date, post.get('blog_name'), [type],
tags, status, kind, format)
offset += len(posts)
posts = get_tumblr_posts(api_key, blogname, offset)
def __init__(self,
content,
metadata=None,
settings=None,
source_path=None,
context=None):
if metadata is None:
metadata = {}
if settings is None:
settings = copy.deepcopy(DEFAULT_CONFIG)
self.settings = settings
self._content = content
if context is None:
context = {}
self._context = context
self.translations = []
local_metadata = dict()
local_metadata.update(metadata)
# set metadata as attributes
for key, value in local_metadata.items():
if key in ('save_as', 'url'):
key = 'override_' + key
setattr(self, key.lower(), value)
# also keep track of the metadata attributes available
self.metadata = local_metadata
# default template if it's not defined in page
self.template = self._get_template()
# First, read the authors from "authors", if not, fallback to "author"
# and if not use the settings defined one, if any.
if not hasattr(self, 'author'):
if hasattr(self, 'authors'):
self.author = self.authors[0]
elif 'AUTHOR' in settings:
self.author = Author(settings['AUTHOR'], settings)
if not hasattr(self, 'authors') and hasattr(self, 'author'):
self.authors = [self.author]
# XXX Split all the following code into pieces, there is too much here.
# manage languages
self.in_default_lang = True
if 'DEFAULT_LANG' in settings:
default_lang = settings['DEFAULT_LANG'].lower()
if not hasattr(self, 'lang'):
self.lang = default_lang
self.in_default_lang = (self.lang == default_lang)
# create the slug if not existing, generate slug according to
# setting of SLUG_ATTRIBUTE
if not hasattr(self, 'slug'):
if (settings['SLUGIFY_SOURCE'] == 'title'
and hasattr(self, 'title')):
self.slug = slugify(self.title,
settings.get('SLUG_SUBSTITUTIONS', ()))
elif (settings['SLUGIFY_SOURCE'] == 'basename'
and source_path is not None):
basename = os.path.basename(os.path.splitext(source_path)[0])
self.slug = slugify(basename,
settings.get('SLUG_SUBSTITUTIONS', ()))
self.source_path = source_path
# manage the date format
if not hasattr(self, 'date_format'):
if hasattr(self, 'lang') and self.lang in settings['DATE_FORMATS']:
self.date_format = settings['DATE_FORMATS'][self.lang]
else:
self.date_format = settings['DEFAULT_DATE_FORMAT']
if isinstance(self.date_format, tuple):
locale_string = self.date_format[0]
if sys.version_info < (3, ) and isinstance(locale_string,
six.text_type):
locale_string = locale_string.encode('ascii')
locale.setlocale(locale.LC_ALL, locale_string)
self.date_format = self.date_format[1]
# manage timezone
default_timezone = settings.get('TIMEZONE', 'UTC')
timezone = getattr(self, 'timezone', default_timezone)
if hasattr(self, 'date'):
self.date = set_date_tzinfo(self.date, timezone)
self.locale_date = strftime(self.date, self.date_format)
if hasattr(self, 'modified'):
self.modified = set_date_tzinfo(self.modified, timezone)
self.locale_modified = strftime(self.modified, self.date_format)
# manage status
if not hasattr(self, 'status'):
self.status = settings['DEFAULT_STATUS']
if not settings['WITH_FUTURE_DATES'] and hasattr(self, 'date'):
if self.date.tzinfo is None:
now = SafeDatetime.now()
else:
now = SafeDatetime.utcnow().replace(tzinfo=pytz.utc)
if self.date > now:
self.status = 'draft'
# store the summary metadata if it is set
if 'summary' in metadata:
self._summary = metadata['summary']
signals.content_object_init.send(self)
def tumblr2fields(api_key, blogname):
""" Imports Tumblr posts (API v2)"""
try:
# py3k import
import json
except ImportError:
# py2 import
import simplejson as json
try:
# py3k import
import urllib.request as urllib_request
except ImportError:
# py2 import
import urllib2 as urllib_request
def get_tumblr_posts(api_key, blogname, offset=0):
url = ("http://api.tumblr.com/v2/blog/%s.tumblr.com/"
"posts?api_key=%s&offset=%d&filter=raw") % (blogname, api_key,
offset)
request = urllib_request.Request(url)
handle = urllib_request.urlopen(request)
posts = json.loads(handle.read().decode('utf-8'))
return posts.get('response').get('posts')
offset = 0
posts = get_tumblr_posts(api_key, blogname, offset)
settings = read_settings()
subs = settings['SLUG_REGEX_SUBSTITUTIONS']
while len(posts) > 0:
for post in posts:
title = \
post.get('title') or \
post.get('source_title') or \
post.get('type').capitalize()
slug = post.get('slug') or slugify(title, regex_subs=subs)
tags = post.get('tags')
timestamp = post.get('timestamp')
date = SafeDatetime.fromtimestamp(
int(timestamp)).strftime("%Y-%m-%d %H:%M:%S")
slug = SafeDatetime.fromtimestamp(
int(timestamp)).strftime("%Y-%m-%d-") + slug
format = post.get('format')
content = post.get('body')
type = post.get('type')
if type == 'photo':
if format == 'markdown':
fmtstr = ''
else:
fmtstr = '<img alt="%s" src="%s" />'
content = ''
for photo in post.get('photos'):
content += '\n'.join(
fmtstr % (photo.get('caption'),
photo.get('original_size').get('url')))
content += '\n\n' + post.get('caption')
elif type == 'quote':
if format == 'markdown':
fmtstr = '\n\n— %s'
else:
fmtstr = '<p>— %s</p>'
content = post.get('text') + fmtstr % post.get('source')
elif type == 'link':
if format == 'markdown':
fmtstr = '[via](%s)\n\n'
else:
fmtstr = '<p><a href="%s">via</a></p>\n'
content = fmtstr % post.get('url') + post.get('description')
elif type == 'audio':
if format == 'markdown':
fmtstr = '[via](%s)\n\n'
else:
fmtstr = '<p><a href="%s">via</a></p>\n'
content = fmtstr % post.get('source_url') + \
post.get('caption') + \
post.get('player')
elif type == 'video':
if format == 'markdown':
fmtstr = '[via](%s)\n\n'
else:
fmtstr = '<p><a href="%s">via</a></p>\n'
source = fmtstr % post.get('source_url')
caption = post.get('caption')
players = '\n'.join(
player.get('embed_code') for player in post.get('player'))
content = source + caption + players
elif type == 'answer':
title = post.get('question')
content = ('<p>'
'<a href="%s" rel="external nofollow">%s</a>'
': %s'
'</p>\n'
' %s' %
(post.get('asking_name'), post.get('asking_url'),
post.get('question'), post.get('answer')))
content = content.rstrip() + '\n'
kind = 'article'
status = 'published' # TODO: Find a way for draft posts
yield (title, content, slug, date, post.get('blog_name'), [type],
tags, status, kind, format)
offset += len(posts)
posts = get_tumblr_posts(api_key, blogname, offset)
def __init__(self, content, metadata=None, settings=None, source_path=None, context=None):
if metadata is None:
metadata = {}
if settings is None:
settings = copy.deepcopy(DEFAULT_CONFIG)
self.settings = settings
self._content = content
if context is None:
context = {}
self._context = context
self.translations = []
local_metadata = dict()
local_metadata.update(metadata)
# set metadata as attributes
for key, value in local_metadata.items():
if key in ("save_as", "url"):
key = "override_" + key
setattr(self, key.lower(), value)
# also keep track of the metadata attributes available
self.metadata = local_metadata
# default template if it's not defined in page
self.template = self._get_template()
# First, read the authors from "authors", if not, fallback to "author"
# and if not use the settings defined one, if any.
if not hasattr(self, "author"):
if hasattr(self, "authors"):
self.author = self.authors[0]
elif "AUTHOR" in settings:
self.author = Author(settings["AUTHOR"], settings)
if not hasattr(self, "authors") and hasattr(self, "author"):
self.authors = [self.author]
# XXX Split all the following code into pieces, there is too much here.
# manage languages
self.in_default_lang = True
if "DEFAULT_LANG" in settings:
default_lang = settings["DEFAULT_LANG"].lower()
if not hasattr(self, "lang"):
self.lang = default_lang
self.in_default_lang = self.lang == default_lang
# create the slug if not existing, generate slug according to
# setting of SLUG_ATTRIBUTE
if not hasattr(self, "slug"):
if settings["SLUGIFY_SOURCE"] == "title" and hasattr(self, "title"):
self.slug = slugify(self.title, settings.get("SLUG_SUBSTITUTIONS", ()))
elif settings["SLUGIFY_SOURCE"] == "basename" and source_path is not None:
basename = os.path.basename(os.path.splitext(source_path)[0])
self.slug = slugify(basename, settings.get("SLUG_SUBSTITUTIONS", ()))
self.source_path = source_path
# manage the date format
if not hasattr(self, "date_format"):
if hasattr(self, "lang") and self.lang in settings["DATE_FORMATS"]:
self.date_format = settings["DATE_FORMATS"][self.lang]
else:
self.date_format = settings["DEFAULT_DATE_FORMAT"]
if isinstance(self.date_format, tuple):
locale_string = self.date_format[0]
if sys.version_info < (3,) and isinstance(locale_string, six.text_type):
locale_string = locale_string.encode("ascii")
locale.setlocale(locale.LC_ALL, locale_string)
self.date_format = self.date_format[1]
# manage timezone
default_timezone = settings.get("TIMEZONE", "UTC")
timezone = getattr(self, "timezone", default_timezone)
if hasattr(self, "date"):
self.date = set_date_tzinfo(self.date, timezone)
self.locale_date = strftime(self.date, self.date_format)
if hasattr(self, "modified"):
self.modified = set_date_tzinfo(self.modified, timezone)
self.locale_modified = strftime(self.modified, self.date_format)
# manage status
if not hasattr(self, "status"):
self.status = settings["DEFAULT_STATUS"]
if not settings["WITH_FUTURE_DATES"] and hasattr(self, "date"):
if self.date.tzinfo is None:
now = SafeDatetime.now()
else:
now = SafeDatetime.utcnow().replace(tzinfo=pytz.utc)
if self.date > now:
self.status = "draft"
# store the summary metadata if it is set
if "summary" in metadata:
self._summary = metadata["summary"]
signals.content_object_init.send(self)
