varia/etherpump
14
0
Fork 0
Code Issues 15 Pull Requests Releases Activity

merged roels unicsss.py code

Browse Source
This commit is contained in:
Michael Murtaugh 2015-08-27 17:02:05 +02:00
parent 30c9247518
commit 6260572237
2 changed files with 52 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
etherdump
View File

@ -1,4 +1,7 @@
#!/usr/bin/env python #!/usr/bin/env python
# License: AGPL
#
from __future__ import print_function from __future__ import print_function
# stdlib # stdlib
import json, sys, os, re import json, sys, os, re
@ -47,9 +50,10 @@ p.add_argument("--showurls", default=False, action="store_true", help="flag to d
p.add_argument("--hidepaths", default=False, action="store_true", help="flag to not display paths") p.add_argument("--hidepaths", default=False, action="store_true", help="flag to not display paths")
p.add_argument("--pretend", default=False, action="store_true", help="flag to not actually save") p.add_argument("--pretend", default=False, action="store_true", help="flag to not actually save")
p.add_argument("--add-images", default=False, action="store_true", help="flag to add image tags") p.add_argument("--add-images", default=False, action="store_true", help="flag to add image tags")
p.add_argument("--authors-css", default="authors.css", help="filename to save collected authorship css (nb: etherdump will overwrite this file!)")
# TODO css from pad --- ie specify a padid for a stylesheet!!!!!! # TODO css from pad --- ie specify a padid for a stylesheet!!!!!!
p.add_argument("--css", default="styles.css", help="padid of stylesheet") # p.add_argument("--css", default="styles.css", help="padid of stylesheet")
args = p.parse_args() args = p.parse_args()
@ -77,6 +81,7 @@ todo = args.padid
done = set() done = set()
count = 0 count = 0
data = {} data = {}
authors_css_rules = {}
data['apikey'] = info['apikey'] data['apikey'] = info['apikey']
if args.allpads: if args.allpads:
@ -245,7 +250,15 @@ while len(todo) > 0:
# extract the style tag (with authorship colors) # extract the style tag (with authorship colors)
style = t.find(".//style") style = t.find(".//style")
if style != None: if style != None:
style = ET.tostring(style, method="html") if args.authors_css:
for i in style.text.splitlines():
if len(i):
selector, rule = i.split(' ',1)
authors_css_rules[selector] = rule
style = '' # strip the individual style tag from each page (only exports to authors-css file)
# nb: it's up to the template to refer to the authors-css file
else:
style = ET.tostring(style, method="html")
else: else:
style = "" style = ""
# and extract the contents of the body # and extract the contents of the body
@ -273,4 +286,10 @@ while len(todo) > 0:
if args.limit and count >= args.limit: if args.limit and count >= args.limit:
break break
except TypeError: except TypeError:
print ("ERROR, skipping!", file=sys.stderr) print ("ERROR, skipping!", file=sys.stderr)
# Write the unified CSS with authors
if args.authors_css:
with open(args.authors_css, 'w') as css:
for selector, rule in sorted(authors_css_rules.items()):
css.write(selector+' '+rule+'\n')

52
linkify.py
View File

@ -3,39 +3,47 @@ import re, sys
def strip_tags (text): def strip_tags (text):
return re.sub(r"<.*?>", "", text) return re.sub(r"<.*?>", "", text)
def urlify (t, ext=".html"): def urlify (t, ext=".html"):
return t.replace(" ", "_") + ext return t.replace(" ", "_") + ext
def filename_to_padid (t): def filename_to_padid (t):
t = t.replace("_", " ") t = t.replace("_", " ")
t = re.sub(r"\.html$", "", t) t = re.sub(r"\.html$", "", t)
return t return t
def normalize_pad_name (n):
if '?' in n:
n = n.split('?', 1)[0]
if '/' in n:
n = n.split('/', 1)[0]
return n
def linkify (src, urlify=urlify): def linkify (src, urlify=urlify):
collect = [] collect = []
def s (m): def s (m):
contents = strip_tags(m.group(1)) contents = strip_tags(m.group(1))
collect.append(contents) contents = normalize_pad_name(contents)
link = urlify(contents) collect.append(contents)
# link = link.split("?", 1)[0] link = urlify(contents)
return "[[<a class=\"wikilink\" href=\"{0}\">{1}</a>]]".format(link, contents) # link = link.split("?", 1)[0]
return "[[<a class=\"wikilink\" href=\"{0}\">{1}</a>]]".format(link, contents)
# src = re.sub(r"\[\[([\w_\- ,]+?)\]\]", s, src) # src = re.sub(r"\[\[([\w_\- ,]+?)\]\]", s, src)
## question marks are ignored by etherpad, so split/strip it ## question marks are ignored by etherpad, so split/strip it
## strip slashes as well!! (/timeslider) ## strip slashes as well!! (/timeslider)
src = re.sub(r"\[\[(.+?)(\/.*)?(\?.*)?\]\]", s, src) src = re.sub(r"\[\[(.+?)\]\]", s, src)
return (src, collect) return (src, collect)
if __name__ == "__main__": if __name__ == "__main__":
src = sys.stdin.read() src = sys.stdin.read()
src, links = linkify(src) src, links = linkify(src)
for l in links: for l in links:
print (l) print (l)
print (src) print (src)