def wca_url_request_handler(self, target_url, post_data, timeout,
target_page_word, logpath):
"""Universal URL request format handler
@@API that allows external calls
If no need log, set log path to None
:param target_url: target request url
:param post_data: post way data
:param timeout: request timeout, suggest 30s
:param target_page_word: target page symbol word
:param logpath: log save path
:return: request result response(raw)
"""
try:
response = self.opener.open(fullurl=target_url,
data=post_data,
timeout=timeout)
except Exception as e:
log_content = dl.BR_CB('%s response failed, error: %s' %
(target_page_word, str(e)))
self.wca_logprowork(logpath, log_content)
exit(dl.PUB_E_RESPONSE_FAIL) # can't process error, directly exit
if response.getcode() == dl.HTTP_REP_OK_CODE:
log_content = target_page_word + ' response ok'
else:
log_content = dl.BR_CB(target_page_word +
' return code %d' % response.getcode())
self.wca_logprowork(logpath, log_content)
return response
def wca_camouflage_login(self):
"""Camouflage browser to login
If login failed, program will exit here
@@API that allows external calls
:return: status code
"""
if WkvCwApi._login_once_flag:
return dl.PUB_E_OK
else:
WkvCwApi._login_once_flag = True
if self._gatherpostkey() != dl.PUB_E_OK:
exit(dl.PUB_E_RESPONSE_FAIL)
cookie_jar = self._get_chrome_cookie(dl.local_cache_cookie_path,
dl.HTTPS_HOST_URL)
self.cookieHandler = urllib.request.HTTPCookieProcessor(cookie_jar)
self.opener = urllib.request.build_opener(self.cookieHandler)
urllib.request.install_opener(self.opener)
response = self.wca_url_request_handler(
target_url=dl.LOGIN_REQUEST_API_URL,
post_data=self.postway_data,
timeout=30,
target_page_word='login',
logpath=None)
if response == dl.PUB_E_RESPONSE_FAIL:
dl.LT_PRINT(
dl.BR_CB('login response return a boolean FALSE, exit'))
exit(dl.PUB_E_RESPONSE_FAIL)
web_src = response.read().decode("UTF-8", "ignore")
dl.LT_PRINT(
dl.BY_CB('response source: %s' %
web_src.encode("UTF-8").decode("unicode_escape")))
login_info_pattern = re.compile(dl.LOGIN_INFO_REGEX, re.S)
response_info = re.findall(login_info_pattern, web_src)
if response_info:
if response_info[0] != 'false':
# error false means no error
dl.LT_PRINT(dl.BR_CB('login confirm raise a error, exit'))
exit(dl.PUB_E_RESPONSE_FAIL)
else:
dl.LT_PRINT('login check response right')
else:
dl.LT_PRINT('login confirm response no error status')
exit(dl.PUB_E_RESPONSE_FAIL)
def rtn_gather_essential_info(page_opt, whole_nbr):
"""Get input image count
If user input number more than whole number, set target count is whole number
Only intercative mode call this function
:param page_opt: select ranktop ordinary or r18 mode
:param whole_nbr: whole ranking crawl count
:return: crawl images count
"""
img_cnt = 0
if page_opt == dl.PAGE_ORDINARY:
label = 'ordinary'
elif page_opt == dl.PAGE_R18:
label = 'r18'
elif page_opt == dl.PAGE_R18G:
label = 'r18g'
else:
dl.nolog_raise_arguerr()
return dl.PUB_E_PARAM_FAIL
img_str = dl.LT_INPUT(dl.HL_CY('crawl %s valid target %d, enter you want: ' % (label, whole_nbr)))
while not img_str.isdigit():
img_str = dl.LT_INPUT(dl.HL_CY('input error, enter again(max is %d): ' % whole_nbr))
img_cnt = int(img_str)
if img_cnt <= 0:
dl.LT_PRINT(dl.BR_CB('what the f**k is wrong with you?'))
return dl.PUB_E_PARAM_FAIL
if img_cnt > whole_nbr:
img_cnt = whole_nbr
return img_cnt
def wca_commit_spansizer(whole_pattern, info_pattern, web_src):
"""A sizer for all of images in once commit item
@@API that allows external calls
After Pixiv 20181002 update, this method only support mode rtn
:param whole_pattern: whole info data regex compile pattern
:param info_pattern: image info regex compile pattern
:param web_src: webpage source
:return: original target url list & image info list dict
"""
img_info_lst = []
tgt_url_lst = []
datasrc_pattern = re.compile(dl.DATASRC_REGEX, re.S)
span_pattern = re.compile(dl.SPAN_REGEX, re.S)
img_whole_info = re.findall(whole_pattern, web_src)
# image have 3 format: jpg/png/gif
# this crawler will give gif format up and crawl png or jpg
# pixiv one repertory maybe have multi-images
for item in img_whole_info:
tmp_thumbnail = re.findall(datasrc_pattern, item)
if not tmp_thumbnail:
dl.LT_PRINT(dl.BR_CB('span sizer regex cannot get valid info'))
return dl.PUB_E_FAIL
thumbnail = tmp_thumbnail[0]
judge_word = thumbnail[-18:]
# check jpg/png or gif
if judge_word == dl.JUDGE_NOGIF_WORD:
span_word = re.findall(span_pattern, item)
vaild_word = thumbnail[44:-18]
# try to check multi-span images
if len(span_word) != 0:
for _px in range(int(span_word[0])):
info = re.findall(info_pattern, item)[0]
img_info_lst.append(info)
# more pages point, range 0~span-1
target_url = dl.ORIGINAL_IMAGE_HEAD + vaild_word + dl.ORIGINAL_IMAGE_TAIL(
_px)
tgt_url_lst.append(target_url)
# just only one picture in a commit
else:
info = re.findall(info_pattern, item)[0]
img_info_lst.append(info)
# only _p0 page
target_url = dl.ORIGINAL_IMAGE_HEAD + vaild_word + dl.ORIGINAL_IMAGE_TAIL(
0)
tgt_url_lst.append(target_url)
# give up gif format, or list is empty
else:
pass
return {'url lst': tgt_url_lst, 'info lst': img_info_lst}
def rtn_gather_rankingdata(self):
"""Crawl dailyRank list
:return: status code
"""
response = self.wkv_cw_api.wca_url_request_handler(target_url=self.rtn_req_url,
post_data=self.wkv_cw_api.getway_data,
timeout=30,
target_page_word='rankpage',
logpath=self.logpath)
# size info in webpage source
web_src = response.read().decode("UTF-8", "ignore")
imgitem_pattern = re.compile(dl.RANKING_SECTION_REGEX, re.S)
info_pattern = re.compile(dl.RANKING_INFO_REGEX, re.S)
sizer_result = self.wkv_cw_api.wca_commit_spansizer(imgitem_pattern, info_pattern, web_src)
if sizer_result == dl.PUB_E_FAIL:
return dl.PUB_E_FAIL
url_lst = sizer_result['url lst']
img_info_lst = sizer_result['info lst']
# cut need image count to be target list
valid_url_cnt = len(url_lst)
if self.ir_mode == dl.MODE_INTERACTIVE:
img_nbr = self.rtn_gather_essential_info(self.page_opt, valid_url_cnt)
if img_nbr == dl.PUB_E_PARAM_FAIL:
return dl.PUB_E_FAIL
elif self.ir_mode == dl.MODE_SERVER:
img_nbr = valid_url_cnt # server mode directly get all of alive targets
dl.LT_PRINT(dl.BY_CB('server mode auto crawl all of alive targets'))
self.rtn_target_urls = url_lst[:img_nbr]
log_content = dl.BY_CB('crawl ranking top ' + str(img_nbr) + ', target table:')
self.wkv_cw_api.wca_logprowork(self.logpath, log_content)
image_info_table = PrettyTable(
["ImageNumber", "ImageID", "ImageTitle", "ImageID+PageNumber", "AuthorID", "AuthorName"])
for k, i in enumerate(img_info_lst[:img_nbr]):
self.rtn_basepages.append(dl.BASEPAGE_URL(i[3])) # url request header use
image_info_table.add_row([(k + 1), i[3], i[1], dl.FROM_URL_GET_IMG_NAME(self.rtn_target_urls[k]), i[4], i[2]])
# damn emoji, maybe dump failed
try:
self.wkv_cw_api.wca_logprowork(self.logpath, str(image_info_table), False)
except Exception as e:
dl.LT_PRINT(dl.BR_CB('error: %s, dump prettytable interrupt' % str(e)))
return dl.PUB_E_OK
def create(self):
"""Create a new thread
Use built-in queue to manage threads list
:return: status flag
"""
self.lock_t.acquire()
self.queue_t.append(self)
self.lock_t.release()
# if the system has insufficient memory
# it will not be able to create more threads
# this step will fail
try:
self.start()
except Exception as e:
log_content = dl.BR_CB("Error type: " + str(e))
WkvCwApi.wca_logprowork(log_content, self.logpath)
return dl.PUB_E_FAIL
return dl.PUB_E_OK
def run(self):
"""Overwrite threading.thread run() method
:return: none
"""
try:
# package download one image thread
# default set server mode here(actually it doesn’t matter)
WkvCwApi(2)._save_oneimage(self.index, self.url,
self.basepages, self.workdir, self.logpath)
except Exception as e:
log_content = dl.BR_CB("Error type: " + str(e))
WkvCwApi.wca_logprowork(log_content, self.logpath)
self.lock_t.acquire() # thread queue adjust, lock it
self.queue_t.remove(self) # remove end thread from list
if len(self.queue_t) == dl.SYSTEM_MAX_THREADS - 1:
self.event_t.set()
self.event_t.clear()
self.lock_t.release()
def wca_download_alltarget(self, logpath, urls, basepages, workdir):
"""Multi-process download all image
@@API that allows external calls
:param urls: all original images urls
:param basepages: all referer basic pages
:param workdir: work directory
:param logpath: log save path
:return: none
"""
thread_block_flag = False # thread blocking flag
alive_thread_cnt = queueLength = len(urls)
log_content = dl.BY_CB('hit %d target(s), start download task(s)' %
queueLength)
self.wca_logprowork(logpath, log_content)
# capture timeout and the user interrupt fault and exit the failed thread
try:
for i, one_url in enumerate(urls):
self._MultiThreading.lock_t.acquire()
if len(self._MultiThreading.queue_t) > dl.SYSTEM_MAX_THREADS:
thread_block_flag = True
self._MultiThreading.lock_t.release()
# if the number of created threads reach max limit
# program will stop here, wait all of threads have been created over
# when one thread executed over, create next one
self._MultiThreading.event_t.wait()
else:
self._MultiThreading.lock_t.release()
# build overwrite threading.Thread object
sub_thread = self._MultiThreading(i, one_url, basepages,
workdir, logpath)
# set every download sub-process daemon property
# set false, then if you exit one thread, others threads will not end
# set true, quit one is quit all
sub_thread.setDaemon(True)
# if create this sub-thread failed from function
if sub_thread.create() == dl.PUB_E_FAIL:
log_content = dl.BR_CB('create a new sub-thread failed')
print(log_content)
return dl.PUB_E_FAIL
if thread_block_flag == False:
log_content = dl.BY_CB(
'created {:d} download target object(s)')
else:
log_content = dl.BY_CB(
'created {:d} download target object(s), thread creation is blocked, please wait'
)
dl.LT_FLUSH(log_content, i + 1)
print(dl.BY_CB(', all threads have been loaded OK'))
thread_block_flag = False
# parent thread wait all sub-thread end
# the count of all threads is 1 parent thread and n sub-thread(s)
# when all pictures have been downloaded over, thread count is 1
while alive_thread_cnt > 1:
# global variable update
self.alivethread_counter = threading.active_count()
# when alive thread count change, print its value
if alive_thread_cnt != self.alivethread_counter:
alive_thread_cnt = self.alivethread_counter # update alive thread count
# display alive sub-thread count
# its number wouldn't more than thread max count
log_content = dl.BY_CB(
'currently remaining sub-thread(s):({:4d}/{:4d}), completed:({:4.1%})|({:5.2f}MB)'
)
dl.LT_FLUSH(log_content, alive_thread_cnt - 1, queueLength,
((queueLength -
(alive_thread_cnt - 1)) / queueLength),
(float(WkvCwApi._datastream_pool / 1024)))
print(dl.BY_CB(', sub-threads execute finished'))
except KeyboardInterrupt:
print(dl.BY_CB(', user interrupt a thread, exit all threads'))
def rtn_target_confirm(self):
"""Input option and confirm target
:return: status code
"""
req_url = None # request target ranking url
rank_word = None # ranking word
dwm_opt = None # daily/weekly/monthly
if self.ir_mode == dl.MODE_INTERACTIVE:
page_opt = dl.LT_INPUT(dl.HL_CY('select ranking type, ordinary(1) | r18(2) | r18g(3): '))
sex_opt = dl.LT_INPUT(dl.HL_CY('select sex favor, normal(0) | male(1) | female(2): '))
elif self.ir_mode == dl.MODE_SERVER:
page_opt = self.rtn_r18_arg
sex_opt = self.rtn_sex_opt
else:
dl.nolog_raise_arguerr()
return dl.PUB_E_PARAM_FAIL
if page_opt == dl.PAGE_ORDINARY:
if self.ir_mode == dl.MODE_INTERACTIVE:
dwm_opt = dl.LT_INPUT(dl.HL_CY('select daily(1) | weekly(2) | monthly(3) ordinary ranking type: '))
elif self.ir_mode == dl.MODE_SERVER:
dwm_opt = self.rtn_rank_type
else:
dl.nolog_raise_arguerr()
return dl.PUB_E_PARAM_FAIL
if dwm_opt == dl.RANK_DAILY:
if sex_opt == dl.SEX_NORMAL:
req_url = dl.RANK_DAILY_URL
rank_word = dl.DAILY_WORD
elif sex_opt == dl.SEX_MALE:
req_url = dl.RANK_DAILY_MALE_URL
rank_word = dl.MALE_WORD
elif sex_opt == dl.SEX_FEMALE:
req_url = dl.RANK_DAILY_FEMALE_URL
rank_word = dl.FEMALE_WORD
else:
dl.nolog_raise_arguerr()
return dl.PUB_E_PARAM_FAIL
elif dwm_opt == dl.RANK_WEEKLY:
req_url = dl.RANK_WEEKLY_URL
rank_word = dl.WEEKLY_WORD
elif dwm_opt == dl.RANK_MONTHLY:
req_url = dl.RANK_MONTHLY_URL
rank_word = dl.MONTHLY_WORD
else:
dl.nolog_raise_arguerr()
return dl.PUB_E_PARAM_FAIL
elif page_opt == dl.PAGE_R18:
if self.ir_mode == dl.MODE_INTERACTIVE:
dwm_opt = dl.LT_INPUT(dl.HL_CY('select daily(1)/weekly(2) R18 ranking type: '))
elif self.ir_mode == dl.MODE_SERVER:
dwm_opt = self.rtn_rank_type
else:
dl.nolog_raise_arguerr()
return dl.PUB_E_PARAM_FAIL
if dwm_opt == dl.RANK_DAILY:
if sex_opt == dl.SEX_NORMAL:
req_url = dl.RANK_DAILY_R18_URL
rank_word = dl.DAILY_WORD
elif sex_opt == dl.SEX_MALE:
req_url = dl.RANK_DAILY_MALE_R18_URL
rank_word = dl.MALE_WORD
elif sex_opt == dl.SEX_FEMALE:
req_url = dl.RANK_DAILY_FEMALE_R18_URL
rank_word = dl.FEMALE_WORD
else:
dl.nolog_raise_arguerr()
return dl.PUB_E_PARAM_FAIL
elif dwm_opt == dl.RANK_WEEKLY:
req_url = dl.RANK_WEEKLY_R18_URL
rank_word = dl.WEEKLY_WORD
else:
dl.nolog_raise_arguerr()
return dl.PUB_E_PARAM_FAIL
elif page_opt == dl.PAGE_R18G:
req_url = dl.RANK_R18G_URL
rank_word = dl.R18G_WORD
dl.LT_PRINT(dl.BR_CB('warning: you choose the r18g rank, hope you know what it means'))
else:
dl.nolog_raise_arguerr()
return dl.PUB_E_PARAM_FAIL
log_content = dl.BY_CB('base select option, set rank target url: [%s]' % req_url)
self.wkv_cw_api.wca_logprowork(self.logpath, log_content)
self.rtn_req_url = req_url
self.page_opt = page_opt
return dl.PUB_E_OK
def ira_crawl_allpage_target(self):
"""Package all gather urls
:return: status code
"""
require_page_cnt = 0
if self.ira_max_cnt <= dl.ONE_PAGE_COMMIT:
require_page_cnt = 1
else:
require_page_cnt = int(self.ira_max_cnt / dl.ONE_PAGE_COMMIT)
# remainder decision
if self.ira_max_cnt % dl.ONE_PAGE_COMMIT != 0:
require_page_cnt += 1
# build the json data url
iid_string_tail = ''
subpage_url_list = []
for ix in range(require_page_cnt):
# one subpage only include 6*8 valid image, others are invalid
tmp_tail_nbr = dl.ONE_PAGE_COMMIT * (ix + 1)
tmp_tail_nbr = self.ira_max_cnt if tmp_tail_nbr > self.ira_max_cnt else tmp_tail_nbr
for index in self.ira_pure_idlist[(dl.ONE_PAGE_COMMIT * ix):tmp_tail_nbr]:
iid_string_tail += dl.IDS_UNIT(index)
subpage_url_list.append(dl.ALLREPOINFO_URL(self.user_input_id, iid_string_tail, 1 if ix == 0 else 0))
iid_string_tail = '' # clear last cache
# get all data from response xhr page into a temp list
tmp_receive_list = []
tmp_ret = []
for i in range(require_page_cnt):
tmp_ret = self.ira_crawl_subpage_data(i + 1, subpage_url_list[i])
if not isinstance(tmp_ret, list):
return dl.PUB_E_FAIL
tmp_receive_list += tmp_ret
repo_target_all_list = []
for i in range(len(tmp_receive_list)):
tmp_receive_list[i][1] = dl.UNICODE_ESCAPE(tmp_receive_list[i][1])
tmp_receive_list[i][1] = dl.EMOJI_REPLACE(tmp_receive_list[i][1])
# build original url without image format
tmp = tmp_receive_list[i][2]
tmp = tmp.replace('\\', '')
tmp_receive_list[i][2] = dl.ORIGINAL_IMAGE_HEAD + tmp[-39:-7] + '.png' # first original url
repo_target_all_list.append(tmp_receive_list[i])
# add other original image url by pageCount
tmp_page_count_str = tmp_receive_list[i][3]
if tmp_page_count_str.isdigit():
index_page_count = int(tmp_page_count_str)
if index_page_count != 1:
for px in range(index_page_count):
insert_item = [tmp_receive_list[i][0],
tmp_receive_list[i][1],
tmp_receive_list[i][2][:-5] + str(px) + '.png',
tmp_receive_list[i][3]]
repo_target_all_list.append(insert_item)
else:
log_content = dl.BR_CB('page count process error')
self.wkv_cw_api.wca_logprowork(self.logpath, log_content)
return dl.PUB_E_FAIL
del tmp_receive_list
alive_target_cnt = len(repo_target_all_list)
require_img_nbr = 0
if self.ir_mode == dl.MODE_INTERACTIVE:
require_img_str = dl.LT_INPUT(dl.HL_CY('crawl all repo %d, whole target(s): %d, enter you want count: '
% (self.ira_max_cnt, alive_target_cnt)))
# if user input isn't number
while not require_img_str.isdigit():
dl.LT_PRINT(dl.BR_CB('input error, your input content was not a decimal number'))
require_img_str = dl.LT_INPUT(dl.HL_CY('enter again(max is %d): ' % alive_target_cnt))
require_img_nbr = int(require_img_str)
if require_img_nbr <= 0:
dl.LT_PRINT(dl.BR_CB('what the f**k is wrong with you?'))
return dl.PUB_E_PARAM_FAIL
require_img_nbr = alive_target_cnt if require_img_nbr > alive_target_cnt else require_img_nbr
elif self.ir_mode == dl.MODE_SERVER:
require_img_nbr = alive_target_cnt
dl.LT_PRINT(dl.BY_CB('server mode auto crawl all of alive targets'))
else:
pass
for k, i in enumerate(repo_target_all_list[:require_img_nbr]):
self.ira_target_capture.append(i[2])
self.ira_basepages.append(dl.BASEPAGE_URL(i[0]))
log_content = 'illustrator [%s] id [%s], require image(s): %d, target table:' \
% (self.ira_author_name, self.user_input_id, require_img_nbr)
self.wkv_cw_api.wca_logprowork(self.logpath, log_content)
image_info_table = PrettyTable(["ImageNumber", "ImageID", "ImageTitle", "ImagePageName"])
for k, i in enumerate(repo_target_all_list[:require_img_nbr]):
image_info_table.add_row([(k + 1), i[0], i[1], dl.FROM_URL_GET_IMG_NAME(i[2])])
# damn emoji, maybe dump failed
try:
self.wkv_cw_api.wca_logprowork(self.logpath, str(image_info_table), False)
except Exception as e:
dl.LT_PRINT(dl.BR_CB('error: %s, dump prettytable interrupt' % str(e)))
del repo_target_all_list
return dl.PUB_E_OK
def ira_crawl_subpage_data(self, index, index_url):
"""Crawl a subpage all data
:param index: request page index
:param index_url: index group url
:return: one page get info list(2-d)
"""
response = self.wkv_cw_api.wca_url_request_handler(target_url=index_url,
post_data=self.wkv_cw_api.getway_data,
timeout=30,
target_page_word='subpage %d' % index,
logpath=self.logpath)
# 20181002 event effect: cannot get web source, this web_src is server return raw json data
web_src = response.read().decode("UTF-8", "ignore")
## self.wkv_cw_api.wca_save_test_html('all-repo', 'E:\\OperationCache', web_src)
error_status_pattern = re.compile(dl.PAGE_REQUEST_SYM_REGEX, re.S)
error_status_list = re.findall(error_status_pattern, web_src)
if not error_status_list:
log_content = dl.BR_CB('regex get error status failed')
self.wkv_cw_api.wca_logprowork(self.logpath, log_content)
return dl.PUB_E_REGEX_FAIL
error_status = error_status_list[0]
if error_status == 'true':
log_content = dl.BR_CB('subpage %d response failed' % index)
self.wkv_cw_api.wca_logprowork(self.logpath, log_content)
return dl.PUB_E_RESPONSE_FAIL
# crawl one page items info
page_target_pattern = re.compile(dl.PAGE_TGT_INFO_SQUARE_REGEX, re.S)
page_tgt_info_tpe = re.findall(page_target_pattern, web_src)
if not page_tgt_info_tpe:
log_content = dl.BR_CB('regex get target page info failed')
return dl.PUB_E_REGEX_FAIL
# tuple transform to list
tmp_target_info_list = []
for i in range(len(page_tgt_info_tpe)):
tmp_target_info_list.append([])
for j in range(len(page_tgt_info_tpe[i])):
tmp_target_info_list[i] = list(page_tgt_info_tpe[i])
del page_tgt_info_tpe
# check artwork type, delete gif
tgt_info_comp_works = []
illust_type_pattern = re.compile(dl.ILLUST_TYPE_REGEX, re.S)
for k in range(len(tmp_target_info_list)):
illust_type_sym = re.findall(illust_type_pattern, tmp_target_info_list[k][2])
if len(illust_type_sym) == 0:
log_content = dl.BR_CB('illust type process error')
self.wkv_cw_api.wca_logprowork(self.logpath, log_content)
return dl.PUB_E_FAIL
if illust_type_sym[0] == dl.GIF_TYPE_LABEL:
continue
# delete unuseful data
del tmp_target_info_list[k][2]
del tmp_target_info_list[k][-2]
tgt_info_comp_works.append(tmp_target_info_list[k])
del tmp_target_info_list
return tgt_info_comp_works
def ira_gather_preloadinfo(self):
"""Crawler need to know how many images do you want
This function will get author name base on author id
:return: status code
"""
# request all of one illustrator's artworks
response = self.wkv_cw_api.wca_url_request_handler(target_url=dl.AJAX_ALL_URL(self.user_input_id),
post_data=self.wkv_cw_api.getway_data,
timeout=30,
target_page_word='ajaxpage',
logpath=self.logpath)
# get artworks id list
web_src = response.read().decode("UTF-8", "ignore")
ajax_idlist_pattern = re.compile(dl.AJAX_ALL_IDLIST_REGEX, re.S)
ajax_idlist = re.findall(ajax_idlist_pattern, web_src)
if not ajax_idlist:
log_content = dl.BR_CB('regex get ajax id list fail')
self.wkv_cw_api.wca_logprowork(self.logpath, log_content)
return dl.PUB_E_REGEX_FAIL
number_pattern = re.compile(dl.NUMBER_REGEX, re.S)
for index in ajax_idlist:
if index.isdigit():
self.ira_pure_idlist.append(index)
else:
# id list result may include some garbages, use number regex get pure result
one_pure_id = re.findall(number_pattern, index)
if one_pure_id:
self.ira_pure_idlist.append(one_pure_id[0])
else:
pass
# website server require the descending list of sort artwork id
pure_idlist_nbr = []
for index in self.ira_pure_idlist:
pure_idlist_nbr.append(int(index))
self.wkv_cw_api.wca_quick_sort(pure_idlist_nbr, 0, len(pure_idlist_nbr) - 1)
self.ira_pure_idlist.clear()
for index in reversed(pure_idlist_nbr):
self.ira_pure_idlist.append(str(index))
del pure_idlist_nbr
self.ira_max_cnt = len(self.ira_pure_idlist)
# get author name from member-main-page
illust_mainpage_url = dl.USERS_ARTWORKS_URL(self.user_input_id)
log_content = dl.HL_CY('crawl illustrator url: [%s]' % illust_mainpage_url)
self.wkv_cw_api.wca_logprowork(self.logpath, log_content)
response = self.wkv_cw_api.wca_url_request_handler(target_url=illust_mainpage_url,
post_data=self.wkv_cw_api.getway_data,
timeout=30,
target_page_word='mainpage',
logpath=self.logpath)
# match illustrator name
web_src = response.read().decode("UTF-8", "ignore")
illust_name_pattern = re.compile(dl.ILLUST_NAME_REGEX(self.user_input_id), re.S)
author_info = re.findall(illust_name_pattern, web_src)
if not author_info:
# cannot catch illust name in mainpage if login failed
dl.LT_PRINT(dl.BR_CB("Regex parsing result error, no author info"))
return dl.PUB_E_REGEX_FAIL
self.ira_author_name = author_info[0]
log_content = dl.HL_CY('check illustrator: [%s]' % self.ira_author_name)
self.wkv_cw_api.wca_logprowork(self.logpath, log_content)
return dl.PUB_E_OK
