def harvest(filespec):
'''
Get content and metadata from HTML files. Return a single metadata
dictionary if a single path is given as input, or a dictionary
mapping filenames to metadata dictionaries if multiple paths are
given.
'''
if isinstance(filespec, basestring):
return harvest_metadata(filespec)
elif isinstance(filespec, list):
return dict([(f, harvest_metadata(f)) for f in filespec])
else:
assert False, 'Unknown filespec "{0}"'.format(filespec)
def harvest(filespec):
'''
Get content and metadata from HTML files. Return a single metadata
dictionary if a single path is given as input, or a dictionary
mapping filenames to metadata dictionaries if multiple paths are
given.
'''
if isinstance(filespec, basestring):
return harvest_metadata(filespec)
elif isinstance(filespec, list):
return dict([(f, harvest_metadata(f)) for f in filespec])
else:
assert False, 'Unknown filespec "{0}"'.format(filespec)
def harvest_blog(config):
'''Harvest metadata for all blog entries.'''
all_meta = []
for folder in glob.glob('blog/????/??'):
for post in glob.glob('{0}/*.html'.format(folder)):
m = harvest_metadata(post)
m['folder'] = folder
all_meta.append(m)
all_meta.sort(lambda x, y: cmp(x['date'], y['date']) or cmp(x['time'], y['time']))
return all_meta
def harvest_blog(config):
'''Harvest metadata for all blog entries.'''
all_meta = []
for folder in glob.glob('blog/????/??'):
for post in glob.glob('{0}/*.html'.format(folder)):
m = harvest_metadata(post)
m['folder'] = folder
fill_optional_metadata(m, 'favorite')
all_meta.append(m)
all_meta.sort(lambda x, y: cmp(x['date'], y['date']) or cmp(x['time'], y['time']))
return all_meta
def harvest_blog(config):
'''Harvest metadata for all blog entries.
Note that the YAML parser reads times with a leading 0 like '09:00:00' as strings,
not as times, so we have to convert manually.
'''
all_meta = []
for folder in glob.glob('blog/????/??'):
for post in glob.glob('{0}/*.html'.format(folder)):
m = harvest_metadata(post)
m['folder'] = folder
fill_optional_metadata(m, 'favorite')
all_meta.append(m)
decorated = [(x['date'], x['time'], x) for x in all_meta]
decorated.sort()
all_meta = [x[2] for x in decorated]
return all_meta
def harvest_blog(config):
'''Harvest metadata for all blog entries.
Note that the YAML parser reads times with a leading 0 like '09:00:00' as strings,
not as times, so we have to convert manually.
'''
all_meta = []
for folder in glob.glob('blog/????/??'):
for post in glob.glob('{0}/*.html'.format(folder)):
m = harvest_metadata(post)
m['folder'] = folder
fill_optional_metadata(m, 'favorite')
all_meta.append(m)
decorated = [(x['date'], x['time'], x) for x in all_meta]
decorated.sort()
all_meta = [x[2] for x in decorated]
return all_meta
#!/usr/bin/env python
"""
Display all the categories used in blog posts.
Usage: categories.py $(ls blog/????/??/*.html)
"""
import sys
from collections import defaultdict
from util import harvest_metadata
show_count, filenames = False, sys.argv[1:]
if filenames[0] == '-n':
show_count, filenames = True, filenames[1:]
categories = defaultdict(set)
for f in filenames:
these = harvest_metadata(f)['category']
for t in these:
categories[t].add(f)
for k in sorted(categories.keys()):
if show_count:
print '{0}: {1}'.format(len(categories[k]), k)
else:
print '{0}: {1}'.format(k, len(categories[k]))
"""
Display all the categories used in blog posts.
Usage: categories.py $(ls blog/????/??/*.html)
"""
import sys
import traceback
from collections import defaultdict
from util import harvest_metadata
show_count, filenames = False, sys.argv[1:]
if filenames[0] == '-n':
show_count, filenames = True, filenames[1:]
categories = defaultdict(set)
for f in filenames:
try:
these = harvest_metadata(f)['category']
for t in these:
categories[t].add(f)
except Exception as e:
print >> sys.stderr, 'Failed in {0}'.format(f)
traceback.print_exc(None, sys.stderr)
sys.exit(1)
for k in sorted(categories.keys()):
if show_count:
print '{0}: {1}'.format(len(categories[k]), k)
else:
print '{0}: {1}'.format(k, len(categories[k]))
#!/usr/bin/env python
"""
Display all the author names used in blog posts.
Usage: authors.py $(ls blog/????/??/*.html)
"""
import sys
from util import harvest_metadata
names = set()
for filename in sys.argv[1:]:
names.add(harvest_metadata(filename)['author'])
for n in sorted(names):
print n
#!/usr/bin/env python
"""
Display all the author names used in blog posts.
Usage: authors.py $(ls blog/????/??/*.html)
"""
import sys
from util import harvest_metadata
names = set()
for filename in sys.argv[1:]:
names.add(harvest_metadata(filename)['author'])
for n in sorted(names):
print n
#!/usr/bin/env python
"""
Display all the categories used in blog posts.
Usage: categories.py $(ls blog/????/??/*.html)
"""
import sys
from collections import defaultdict
from util import harvest_metadata
categories = defaultdict(set)
for filename in sys.argv[1:]:
these = harvest_metadata(filename)['category']
for t in these:
categories[t].add(filename)
for k in sorted(categories.keys()):
print '{0}: {1}'.format(k, ', '.join(categories[k]))
#!/usr/bin/env python3
"""
Display all the author names used in blog posts.
Usage: authors.py $(ls blog/????/??/*.html)
"""
import sys
from util import harvest_metadata
names = set()
for filename in sys.argv[1:]:
names.add(harvest_metadata(filename)["author"])
for n in sorted(names):
print(n)
#!/usr/bin/env python
"""
Display all the categories used in blog posts.
Usage: categories.py $(ls blog/????/??/*.html)
"""
import sys
from collections import defaultdict
from util import harvest_metadata
categories = defaultdict(set)
for filename in sys.argv[1:]:
these = harvest_metadata(filename)['category']
for t in these:
categories[t].add(filename)
for k in sorted(categories.keys()):
print '{0}: {1}'.format(k, ', '.join(categories[k]))
