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

handle exceptions

add-quote-import
Michael Murtaugh 9 years ago
parent
d3732a1aee
commit
30c9247518
2 changed files with 172 additions and 166 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 335
      etherdump
  2. 3
      linkify.py

335
etherdump
View File

@ -101,171 +101,176 @@ while len(todo) > 0:
except OSError: except OSError:
pass pass
# _ try:
# _ __ ___ ___| |_ __ _
# | '_ ` _ \ / _ \ __/ _` | # _
# | | | | | | __/ || (_| | # _ __ ___ ___| |_ __ _
# |_| |_| |_|\___|\__\__,_| # | '_ ` _ \ / _ \ __/ _` |
# | | | | | | __/ || (_| |
meta_out = "{0}/{1}".format(args.path, urlify(padid, ext=".json")) # |_| |_| |_|\___|\__\__,_|
if not args.hidepaths:
print (meta_out, file=sys.stderr) meta_out = "{0}/{1}".format(args.path, urlify(padid, ext=".json"))
if not args.pretend: if not args.hidepaths:
meta = {} print (meta_out, file=sys.stderr)
meta['padid'] = padid if not args.pretend:
revisions_url = apiurl+'getRevisionsCount?'+urlencode(data) meta = {}
meta['padid'] = padid
revisions_url = apiurl+'getRevisionsCount?'+urlencode(data)
if args.showurls:
print (revisions_url, file=sys.stderr)
meta['total_revisions'] = json.load(urlopen(revisions_url))['data']['revisions']
lastedited_url = apiurl+'getLastEdited?'+urlencode(data)
if args.showurls:
print (lastedited_url, file=sys.stderr)
lastedited_raw = json.load(urlopen(lastedited_url))['data']['lastEdited']
meta['lastedited_raw'] = lastedited_raw
meta['lastedited'] = datetime.fromtimestamp(int(lastedited_raw)/1000).isoformat()
# author_ids (unfortunately, this is a list of internal etherpad author ids -- not the names ppl type)
authors_url = apiurl+'listAuthorsOfPad?'+urlencode(data)
if args.showurls:
print (authors_url, file=sys.stderr)
meta['author_ids'] = json.load(urlopen(authors_url))['data']['authorIDs']
with open(meta_out, "w") as f:
json.dump(meta, f)
# _ __ __ ___ __
# | '__/ _` \ \ /\ / /
# | | | (_| |\ V V /
# |_| \__,_| \_/\_/
raw_out = "{0}/{1}".format(args.path, urlify(padid, ext=".txt"))
if not args.hidepaths:
print (raw_out, file=sys.stderr)
text_url = apiurl+"getText?"+urlencode(data)
if args.showurls: if args.showurls:
print (revisions_url, file=sys.stderr) print (text_url, file=sys.stderr)
meta['total_revisions'] = json.load(urlopen(revisions_url))['data']['revisions'] if not args.pretend:
rawText = json.load(urlopen(text_url))['data']['text']
lastedited_url = apiurl+'getLastEdited?'+urlencode(data) with open(raw_out, "w") as f:
f.write(rawText.encode("utf-8"))
# _ _ _
# | |__ | |_ _ __ ___ | |
# | '_ \| __| '_ ` _ \| |
# | | | | |_| | | | | | |
# |_| |_|\__|_| |_| |_|_|
# todo ? -- regular HTML output
# _
# ___ ___ | | ___ _ __ ___
# / __/ _ \| |/ _ \| '__/ __|
# | (_| (_) | | (_) | | \__ \
# \___\___/|_|\___/|_| |___/
colors_out = "{0}/{1}".format(args.path, urlify(padid, ext=".html"))
if not args.hidepaths:
print (colors_out, file=sys.stderr)
data['startRev'] = "0"
colors_url = apiurl+'createDiffHTML?'+urlencode(data)
if args.showurls: if args.showurls:
print (lastedited_url, file=sys.stderr) print (colors_url, file=sys.stderr)
lastedited_raw = json.load(urlopen(lastedited_url))['data']['lastEdited'] html = json.load(urlopen(colors_url))['data']['html']
meta['lastedited_raw'] = lastedited_raw t = html5lib.parse(html, namespaceHTMLElements=False)
meta['lastedited'] = datetime.fromtimestamp(int(lastedited_raw)/1000).isoformat() trim_removed_spans(t)
html = ET.tostring(t, method="html")
# author_ids (unfortunately, this is a list of internal etherpad author ids -- not the names ppl type)
authors_url = apiurl+'listAuthorsOfPad?'+urlencode(data) # Stage 1: Process as text
if args.showurls: # Process [[wikilink]] style links
print (authors_url, file=sys.stderr) # and (optionally) add linked page names to spider todo list
meta['author_ids'] = json.load(urlopen(authors_url))['data']['authorIDs'] html, links = linkify(html)
if args.spider:
with open(meta_out, "w") as f: for l in links:
json.dump(meta, f) if l not in todo and l not in done:
if l.startswith("http://") or l.startswith("https://"):
# _ __ __ ___ __
# | '__/ _` \ \ /\ / /
# | | | (_| |\ V V /
# |_| \__,_| \_/\_/
raw_out = "{0}/{1}".format(args.path, urlify(padid, ext=".txt"))
if not args.hidepaths:
print (raw_out, file=sys.stderr)
text_url = apiurl+"getText?"+urlencode(data)
if args.showurls:
print (text_url, file=sys.stderr)
if not args.pretend:
rawText = json.load(urlopen(text_url))['data']['text']
with open(raw_out, "w") as f:
f.write(rawText.encode("utf-8"))
# _ _ _
# | |__ | |_ _ __ ___ | |
# | '_ \| __| '_ ` _ \| |
# | | | | |_| | | | | | |
# |_| |_|\__|_| |_| |_|_|
# todo ? -- regular HTML output
# _
# ___ ___ | | ___ _ __ ___
# / __/ _ \| |/ _ \| '__/ __|
# | (_| (_) | | (_) | | \__ \
# \___\___/|_|\___/|_| |___/
colors_out = "{0}/{1}".format(args.path, urlify(padid, ext=".html"))
if not args.hidepaths:
print (colors_out, file=sys.stderr)
data['startRev'] = "0"
colors_url = apiurl+'createDiffHTML?'+urlencode(data)
if args.showurls:
print (colors_url, file=sys.stderr)
html = json.load(urlopen(colors_url))['data']['html']
t = html5lib.parse(html, namespaceHTMLElements=False)
trim_removed_spans(t)
html = ET.tostring(t, method="html")
# Stage 1: Process as text
# Process [[wikilink]] style links
# and (optionally) add linked page names to spider todo list
html, links = linkify(html)
if args.spider:
for l in links:
if l not in todo and l not in done:
if l.startswith("http://") or l.startswith("https://"):
print ("Ignoring absolute URL in [[ link ]] form", file=sys.stderr)
continue
# if args.verbose:
# print (" link: {0}".format(l), file=sys.stderr)
todo.append(l)
# Stage 2: Process as ElementTree
#
t = html5lib.parse(html, namespaceHTMLElements=False)
# apply linkpats
for a in t.findall(".//a"):
href = a.attrib.get("href")
original_href = href
if href:
# if args.verbose:
# print ("searching for PADLINK: {0}".format(href))
for pat in padlinkpats:
if re.search(pat, href) != None:
# if args.verbose:
# print (" found PADLINK: {0}".format(href))
href = re.sub(pat, "\\1.html", href)
padid = filename_to_padid(href)
set_text_contents(a, "[[{0}]]".format(padid))
if padid not in todo and padid not in done:
if args.verbose: if args.verbose:
print (" link: {0}".format(padid), file=sys.stderr) print ("Ignoring absolute URL in [[ link ]] form", file=sys.stderr)
todo.append(padid) continue
# apply linkpats # if args.verbose:
for s, r in linkpats: # print (" link: {0}".format(l), file=sys.stderr)
href = re.sub(s, r, href) todo.append(l)
if href != original_href:
old_contents = text_contents(a) # Stage 2: Process as ElementTree
# print ("OLD_CONTENTS {0}".format(old_contents)) #
if old_contents == original_href: t = html5lib.parse(html, namespaceHTMLElements=False)
if args.verbose: # apply linkpats
print (" Updating href IN TEXT", file=sys.stderr) for a in t.findall(".//a"):
set_text_contents(a, href) href = a.attrib.get("href")
original_href = href
if original_href != href: if href:
if args.verbose: # if args.verbose:
print (" Changed href from {0} to {1}".format(original_href, href), file=sys.stderr) # print ("searching for PADLINK: {0}".format(href))
a.attrib['href'] = href for pat in padlinkpats:
if re.search(pat, href) != None:
# SHOWIMAGES : inject img tag for (local) images # if args.verbose:
if args.add_images: # print (" found PADLINK: {0}".format(href))
ext = os.path.splitext(href)[1].lower().lstrip(".") href = re.sub(pat, "\\1.html", href)
if ext in ("png", "gif", "jpeg", "jpg"): padid = filename_to_padid(href)
# ap = _parent(a) set_text_contents(a, "[[{0}]]".format(padid))
print ("Adding img '{0}'".format(href), file=sys.stderr) if padid not in todo and padid not in done:
img = ET.SubElement(a, "img") if args.verbose:
br = ET.SubElement(a, "br") print (" link: {0}".format(padid), file=sys.stderr)
a.remove(img); a.insert(0, img) todo.append(padid)
a.remove(br); a.insert(1, br) # apply linkpats
img.attrib['src'] = href for s, r in linkpats:
href = re.sub(s, r, href)
# extract the style tag (with authorship colors) if href != original_href:
style = t.find(".//style") old_contents = text_contents(a)
if style != None: # print ("OLD_CONTENTS {0}".format(old_contents))
style = ET.tostring(style, method="html") if old_contents == original_href:
else: if args.verbose:
style = "" print (" Updating href IN TEXT", file=sys.stderr)
# and extract the contents of the body set_text_contents(a, href)
html = contents(t.find(".//body"))
if original_href != href:
if not args.pretend: if args.verbose:
with open(colors_out, "w") as f: print (" Changed href from {0} to {1}".format(original_href, href), file=sys.stderr)
# f.write(html.encode("utf-8")) a.attrib['href'] = href
f.write(colors_template.render(
html = html, # SHOWIMAGES : inject img tag for (local) images
style = style, if args.add_images:
revision = meta['total_revisions'], ext = os.path.splitext(href)[1].lower().lstrip(".")
padid = padid, if ext in ("png", "gif", "jpeg", "jpg"):
timestamp = datetime.now() # ap = _parent(a)
).encode("utf-8")) print ("Adding img '{0}'".format(href), file=sys.stderr)
img = ET.SubElement(a, "img")
# _ br = ET.SubElement(a, "br")
# | | ___ ___ _ __ a.remove(img); a.insert(0, img)
# | |/ _ \ / _ \| '_ \ a.remove(br); a.insert(1, br)
# | | (_) | (_) | |_) | img.attrib['src'] = href
# |_|\___/ \___/| .__/
# |_| # extract the style tag (with authorship colors)
style = t.find(".//style")
count += 1 if style != None:
if args.limit and count >= args.limit: style = ET.tostring(style, method="html")
break else:
style = ""
# and extract the contents of the body
html = contents(t.find(".//body"))
if not args.pretend:
with open(colors_out, "w") as f:
# f.write(html.encode("utf-8"))
f.write(colors_template.render(
html = html,
style = style,
revision = meta['total_revisions'],
padid = padid,
timestamp = datetime.now()
).encode("utf-8"))
# _
# | | ___ ___ _ __
# | |/ _ \ / _ \| '_ \
# | | (_) | (_) | |_) |
# |_|\___/ \___/| .__/
# |_|
count += 1
if args.limit and count >= args.limit:
break
except TypeError:
print ("ERROR, skipping!", file=sys.stderr)

3
linkify.py
View File

@ -26,7 +26,8 @@ def linkify (src, urlify=urlify):
# 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
src = re.sub(r"\[\[(.+?)(\?.*)?\]\]", s, src) ## strip slashes as well!! (/timeslider)
src = re.sub(r"\[\[(.+?)(\/.*)?(\?.*)?\]\]", s, src)
return (src, collect) return (src, collect)

Write Preview
Loading…
Cancel
Save