def GET(self):
template_name = "code/view_source.html"
path = xutils.get_argument("path", "")
key = xutils.get_argument("key", "")
if path == "":
return xtemplate.render(template_name, error = "path is empty")
else:
error = ""
try:
path = xutils.get_real_path(path)
content = xutils.readfile(path)
# 使用JavaScript来处理搜索关键字高亮问题
# if key != "":
# content = xutils.html_escape(content)
# key = xhtml_escape(key)
# content = textutil.replace(content, key, htmlutil.span("?", "search-key"), ignore_case=True, use_template=True)
return xtemplate.render(template_name,
pathlist = xutils.splitpath(path),
name = os.path.basename(path),
path = path,
content = content, lines = content.count("\n")+1)
except Exception as e:
xutils.print_stacktrace()
error = e
return xtemplate.render(template_name, error = error, lines = 0, content="")
def load_mapping(pattern, func_str):
global _mappings
try:
mod, func_name = func_str.rsplit('.', 1)
# mod = __import__(mod, None, None, [''])
mod = six._import_module(mod)
func = getattr(mod, func_name)
_mappings.append(r"^%s\Z" % pattern)
_mappings.append(func)
except Exception as e:
xutils.print_stacktrace()
def POST(self):
name = xutils.get_argument("name", "")
tags = xutils.get_argument("tags", "")
key = xutils.get_argument("key", "")
content = xutils.get_argument("content", "")
type = xutils.get_argument("type", "post")
_type = xutils.get_argument("_type", "")
parent_id = xutils.get_argument("parent_id", 0, type=int)
if key == "":
key = time.strftime("%Y.%m.%d")
file = FileDO(name)
file.atime = dateutil.get_seconds()
file.satime = dateutil.format_time()
file.mtime = dateutil.get_seconds()
file.smtime = dateutil.format_time()
file.ctime = dateutil.get_seconds()
file.sctime = dateutil.format_time()
file.creator = xauth.get_current_name()
# 默认私有
file.groups = file.creator
file.parent_id = parent_id
file.type = type
file.content = content
code = "fail"
error = ""
try:
if name != '':
f = dao.get_by_name(name)
if f != None:
key = name
raise Exception(u"%s 已存在" % name)
# 分组提前
if file.type == "group":
file.priority = 1
f = dao.insert(file)
inserted = dao.get_by_name(name)
if _type == "json":
return dict(code="success", id=inserted.id)
raise web.seeother("/file/view?id={}".format(inserted.id))
except web.HTTPError as e1:
raise e1
except Exception as e:
xutils.print_stacktrace()
error = str(e)
return xtemplate.render("file/add.html",
key="",
name=key,
tags=tags,
error=error,
message=error,
code=code)
def POST(self):
path = xutils.get_argument("path", "")
dirname = xutils.get_argument("dirname", "")
if path == "":
return dict(code="fail", message="path is empty")
newpath = os.path.join(path, dirname)
try:
os.makedirs(newpath)
return dict(code="success")
except Exception as e:
xutils.print_stacktrace()
return dict(code="fail", message=str(e))
def default_request(self):
content = xutils.get_argument("content")
try:
xutils.say(content)
return dict(code="success")
except Exception as e:
xutils.print_stacktrace()
return dict(code="fail", message=str(e))
finally:
# 报异常
# voice.Release()
# return "OK"
pass
def POST(self):
try:
args = web.input(file={}, download_res="off")
file = args.file
download_res = args.download_res == "on"
address = xutils.get_argument("address", "")
filename = file.filename
if not isempty(address):
html = readhttp(address)
else:
html = ""
for chunk in file.file:
html += chunk.decode("utf-8")
print("Read html, filename={}, length={}".format(
filename, len(html)))
soup = BeautifulSoup(html, "html.parser")
# import pdb
# pdb.set_trace()
images = soup.find_all("img")
links = soup.find_all("a")
csses = soup.find_all("link")
scripts = soup.find_all("script")
# texts = soup.find_all(["p", "span", "div", "h1", "h2", "h3", "h4"])
h = HTML2Text(baseurl=address)
text = h.handle(html)
texts = [text]
images = get_addr_list(images)
scripts = get_addr_list(scripts)
# texts = get_text_list(texts)
if download_res:
download_res_list(images, filename)
return xtemplate.render("tools/analyze_html.html",
images=images,
links=links,
csses=csses,
scripts=scripts,
texts=texts,
address=address)
except Exception as e:
xutils.print_stacktrace()
return xtemplate.render("tools/analyze_html.html", error=str(e))
def read_range(self, path, http_range, blocksize):
xutils.trace("Download", "==> HTTP_RANGE %s" % http_range)
range_list = http_range.split("bytes=")
if len(range_list) == 2:
# 包含完整的范围
range_list = range_list[1]
try:
range_start, range_end = range_list.split('-')
range_start = int(range_start)
total_size = os.stat(path).st_size
if range_end != "":
range_end = int(range_end)
else:
range_end = total_size - 1
web.header("Content-Length", total_size)
content_range = "bytes %s-%s/%s" % (range_start, range_end,
total_size)
# 设置HTTP响应状态
web.ctx.status = "206 Partial Content"
# 发送HTTP首部
web.header("Accept-Ranges", "bytes")
web.header("Content-Range", content_range)
xutils.trace("Download",
"<== Content-Range:%s" % content_range)
# 发送数据
fp = open(path, "rb")
try:
fp.seek(range_start)
rest = range_end - range_start + 1
readsize = min(rest, blocksize)
while readsize > 0:
# print("%s send %s K" % (time.ctime(), readsize))
yield fp.read(readsize)
rest -= readsize
readsize = min(rest, blocksize)
finally:
# 基本上和with等价，这里打印出来
xutils.trace("Download", "close %s" % path)
fp.close()
except Exception as e:
# 其他未知异常
xutils.print_stacktrace()
# yield最好不要和return混用
yield self.read_all(path, blocksize)
else:
# 处理不了，返回所有的数据
yield self.read_all(path, blocksize)
def full_search(self, key):
global _mappings
mappings = _mappings
words = textutil.split_words(key)
files = []
for i in range(0, len(mappings), 2):
pattern = mappings[i]
func = mappings[i + 1]
m = re.match(pattern, key)
if m:
try:
results = func(*m.groups())
if results is not None:
files += results
except Exception as e:
xutils.print_stacktrace()
return files
def POST(self):
try:
file = xutils.get_argument("file", {})
address = xutils.get_argument("url", "")
name = xutils.get_argument("name", "")
filename = ""
if hasattr(file, "filename"):
filename = file.filename
plain_text = ""
if not isempty(address):
html = readhttp(address)
else:
# 读取文件
html = ""
for chunk in file.file:
html += chunk.decode("utf-8")
print("Read html, filename={}, length={}".format(
filename, len(html)))
soup = BeautifulSoup(html, "html.parser")
element_list = soup.find_all(["script", "style"])
for element in element_list:
element.extract()
plain_text = soup.get_text(separator=" ")
plain_text = clean_whitespace(plain_text)
images = soup.find_all("img")
links = soup.find_all("a")
csses = soup.find_all("link")
scripts = soup.find_all("script")
# texts = soup.find_all(["p", "span", "div", "h1", "h2", "h3", "h4"])
h = HTML2Text(baseurl=address)
text = "From %s\n\n" % address + h.handle(html)
texts = [text]
images = get_addr_list(images)
scripts = get_addr_list(scripts)
if name != "" and name != None:
dirname = os.path.join(xconfig.DATA_DIR,
time.strftime("archive/%Y/%m/%d"))
xutils.makedirs(dirname)
path = os.path.join(
dirname, "%s_%s.md" % (name, time.strftime("%H%M%S")))
xutils.savetofile(path, text)
print("save file %s" % path)
if False:
user_name = xauth.get_current_name()
xutils.call("note.create",
name=name,
content=content,
type="md",
tags=["来自网络"],
creator=user_name)
return xtemplate.render(self.template_path,
show_aside=False,
images=images,
links=links,
csses=csses,
scripts=scripts,
texts=texts,
address=address,
url=address,
plain_text=plain_text)
except Exception as e:
xutils.print_stacktrace()
return xtemplate.render(self.template_path,
show_aside=False,
error=str(e))
def POST(self):
try:
file = xutils.get_argument("file", {})
address = xutils.get_argument("url", "")
name = xutils.get_argument("name", "")
filename = ""
if hasattr(file, "filename"):
filename = file.filename
plain_text = ""
if not isempty(address):
html = readhttp(address)
else:
# 读取文件
html = ""
for chunk in file.file:
html += chunk.decode("utf-8")
print("Read html, filename={}, length={}".format(filename, len(html)))
soup = BeautifulSoup(html, "html.parser")
element_list = soup.find_all(["script", "style"])
for element in element_list:
element.extract()
plain_text = soup.get_text(separator=" ")
plain_text = clean_whitespace(plain_text)
images = soup.find_all("img")
links = soup.find_all("a")
csses = soup.find_all("link")
scripts = soup.find_all("script")
title = get_html_title(soup)
h = HTML2Text(baseurl = address)
text = "From %s\n\n" % address + h.handle(html)
texts = [text]
images = get_addr_list(images)
scripts = get_addr_list(scripts)
if name != "" and name != None:
save_to_archive_dir(name)
return xtemplate.render(self.template_path,
show_aside = False,
images = images,
links = links,
csses = csses,
scripts = scripts,
texts = texts,
address = address,
url = address,
article_title = title,
plain_text = plain_text)
except Exception as e:
xutils.print_stacktrace()
return xtemplate.render(self.template_path,
show_aside = False,
error = str(e))
