def urlopen_get_url_image(self, url, path, view=False):
headers = {
'User-Agent': '%s' % USER_AGENTS['AppleWebKit/537.36'],
'GET' : url,
'Referer' : self._com,
}
return WebContent.urlopen_get_url_file(url, path,
ssl=WebContent.url_is_https(url),
headers=headers, view=view)
def get_url_of_pages(self, num):
url = list(
map(
lambda x: WebContent.set_url_base_and_num(
self._url_base, '%d_%d' % (int(self._url), x)),
range(2, num + 1)))
url.insert(0, WebContent.set_url_base_and_num(self._url_base,
self._url))
return url
def get_title(self, html, pattern=None):
title = WebContent.get_url_title(html, pattern)
if title:
if type(title) != str:
title = title.decode()
if self._redundant_title:
for rt in self._redundant_title:
title = title.replace(rt, '')
return title
def urlopen_get_url_image(self, url, path, view=False):
headers = {
'User-Agent': '%s' % USER_AGENTS['AppleWebKit/537.36'],
'GET': url,
'Referer': 'https://m.mzitu.com/',
}
return WebContent.urlopen_get_url_file(url, path,
ssl=True,
headers=headers, view=view)
def get_user_input(self, args=None):
if not args:
args = Base.get_user_input('hu:n:p:x:m:i:R:t:vdD')
if '-h' in args:
Base.print_help(self.help_menu)
if '-u' in args:
self._url = re.sub('/$', '', args['-u'])
if '-n' in args:
self._num = int(args['-n'])
if '-p' in args:
self._path = os.path.abspath(args['-p'])
if '-R' in args:
self._ex_re_image_url = os.path.abspath(args['-R'])
if '-t' in args:
try:
n = int(args['-t'])
except ValueError as e:
Base.print_exit('%s, -h for help!' % str(e))
if n:
self._thread_max = n
if '-v' in args:
self._view = True
self._pr.set_pr_level(self._pr.get_pr_level() | Print.PR_LVL_WARN)
if '-x' in args:
self._xval = args['-x']
if '-m' in args:
dl_image_funcs = {
'wget': self.wget_url_image,
'rtrv' : self.retrieve_url_image,
'rget' : self.requests_get_url_image,
'uget' : self.urlopen_get_url_image,
}
if args['-m'] in dl_image_funcs.keys():
self._dl_image = dl_image_funcs[args['-m']]
if '-d' in args:
self.__dbg = 1
self._pr.set_pr_level(self._pr.get_pr_level() | Print.PR_LVL_ALL )
if '-D' in args:
self.__dbg = 2
self._pr.set_pr_level(self._pr.get_pr_level() | Print.PR_LVL_DBG)
WebContent.pr.set_pr_level(self._pr.get_pr_level() | Print.PR_LVL_DBG)
# check url
if self._url:
base, num = WebContent.get_url_base_and_num(self._url)
if base:
self._url_base = base
if num:
self._url = num
self._pr.pr_dbg('get base: %s, url: %s' % (base, self._url))
else:
Base.print_exit('[WebImage] Error, no set url, -h for help!')
if self._url_base:
www_com = re.match('http[s]?://.+\.(com|cn|net)', self._url_base)
if www_com:
self._com = www_com.group()
return args
def convert_url_to_title(self, url):
return WebContent.convert_url_to_title(url)
def get_pages(self, html, pattern=None):
return WebContent.get_url_pages(html, pattern)
def get_url_content(self, url, view=False):
return WebContent.get_url_content(url=url, view=view)
def requests_get_url_image(self, url, path, view=False):
return WebContent.requests_get_url_file(url, path, view=view)
def wget_url_image(self, url, path, view=False):
return WebContent.wget_url_file(url,
path,
view=view,
config="-c -t 3 -T 10 -U \'%s\'" %
USER_AGENTS['AppleWebKit/537.36'])
def retrieve_url_image(self, url, path, view=False):
return WebContent.retrieve_url_file(url, path, view=view)
def get_url_address(self, url_base, url):
return WebContent.set_url_base_and_num(url_base, url)
def get_url_content(self, url, view=False):
url_content = WebContent.get_url_content(url=url, view=view)
if url_content:
return re.sub(b'\\\\', b'', url_content)