def check_update(local_version):
try:
data = json.loads(get_html("https://api.github.com/repos/yoshiko2/AV_Data_Capture/releases/latest"))
except:
print("[-]Failed to update! Please check new version manually:")
print("[-] https://github.com/yoshiko2/AV_Data_Capture/releases")
print("[*]======================================================")
return
remote = int(data["tag_name"].replace(".",""))
local_version = int(local_version.replace(".", ""))
if local_version < remote:
print("[*]" + ("* New update " + str(data["tag_name"]) + " *").center(54))
print("[*]" + "↓ Download ↓".center(54))
print("[*]https://github.com/yoshiko2/AV_Data_Capture/releases")
print("[*]======================================================")
def check_update(local_version):
htmlcode = ""
try:
htmlcode = get_html(
"https://api.github.com/repos/yoshiko2/Movie_Data_Capture/releases/latest"
)
except:
print("===== Failed to connect to github =====")
print("========== AUTO EXIT IN 60s ===========")
time.sleep(60)
os._exit(-1)
data = json.loads(htmlcode)
remote = int(data["tag_name"].replace(".", ""))
local_version = int(local_version.replace(".", ""))
if local_version < remote:
print("[*]" +
("* New update " + str(data["tag_name"]) + " *").center(54))
print("[*]" + "↓ Download ↓".center(54))
print("[*]https://github.com/yoshiko2/Movie_Data_Capture/releases")
print("[*]======================================================")
def main(number: str):
raw_cookies, user_agent = get_javlib_cookie()
# Blank cookies mean javlib site return error
if not raw_cookies:
return json.dumps({},
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':'))
# Manually construct a dictionary
s_cookie = SimpleCookie()
s_cookie.load(raw_cookies)
cookies = {}
for key, morsel in s_cookie.items():
cookies[key] = morsel.value
# Scraping
result = get_html(
"http://www.m45e.com/cn/vl_searchbyid.php?keyword={}".format(number),
cookies=cookies,
ua=user_agent,
return_type="object")
soup = BeautifulSoup(result.text, "html.parser")
lx = html.fromstring(str(soup))
if "/?v=jav" in result.url:
dic = {
"title":
get_title(lx, soup),
"studio":
get_table_el_single_anchor(soup, "video_maker"),
"year":
get_table_el_td(soup, "video_date")[:4],
"outline":
"",
"director":
get_table_el_single_anchor(soup, "video_director"),
"cover":
get_cover(lx),
"imagecut":
1,
"actor_photo":
"",
"website":
result.url,
"source":
"javlib.py",
"actor":
get_table_el_multi_anchor(soup, "video_cast"),
"label":
get_table_el_td(soup, "video_label"),
"tag":
get_table_el_multi_anchor(soup, "video_genres"),
"number":
get_table_el_td(soup, "video_id"),
"release":
get_table_el_td(soup, "video_date"),
"runtime":
get_from_xpath(
lx, '//*[@id="video_length"]/table/tr/td[2]/span/text()'),
"series":
'',
}
else:
dic = {}
return json.dumps(dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':'))
def main(number: str):
raw_cookies, user_agent = get_javlib_cookie()
# Blank cookies mean javlib site return error
if not raw_cookies:
return json.dumps({}, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'))
# Manually construct a dictionary
s_cookie = SimpleCookie()
s_cookie.load(raw_cookies)
cookies = {}
for key, morsel in s_cookie.items():
cookies[key] = morsel.value
# Scraping
result = get_html(
"http://www.javlibrary.com/cn/vl_searchbyid.php?keyword={}".format(number),
cookies=cookies,
ua=user_agent,
return_type="object"
)
soup = BeautifulSoup(result.text, "html.parser")
lx = html.fromstring(str(soup))
fanhao_pather = re.compile(r'<a href=".*?".*?><div class="id">(.*?)</div>')
fanhao = fanhao_pather.findall(result.text)
if "/?v=jav" in result.url:
dic = {
"title": get_title(lx, soup),
"studio": get_table_el_single_anchor(soup, "video_maker"),
"year": get_table_el_td(soup, "video_date")[:4],
"outline": get_outline(number),
"director": get_table_el_single_anchor(soup, "video_director"),
"cover": get_cover(lx),
"imagecut": 1,
"actor_photo": "",
"website": result.url,
"source": "javlib.py",
"actor": get_table_el_multi_anchor(soup, "video_cast"),
"label": get_table_el_td(soup, "video_label"),
"tag": get_table_el_multi_anchor(soup, "video_genres"),
"number": get_table_el_td(soup, "video_id"),
"release": get_table_el_td(soup, "video_date"),
"runtime": get_from_xpath(lx, '//*[@id="video_length"]/table/tr/td[2]/span/text()'),
"series":'',
}
elif number.upper() in fanhao:
url_pather = re.compile(r'<a href="(.*?)".*?><div class="id">(.*?)</div>')
s = {}
url_list = url_pather.findall(result.text)
for url in url_list:
s[url[1]] = 'http://www.javlibrary.com/cn/' + url[0].lstrip('.')
av_url = s[number.upper()]
result = get_html(
av_url,
cookies=cookies,
ua=user_agent,
return_type="object"
)
soup = BeautifulSoup(result.text, "html.parser")
lx = html.fromstring(str(soup))
dic = {
"title": get_title(lx, soup),
"studio": get_table_el_single_anchor(soup, "video_maker"),
"year": get_table_el_td(soup, "video_date")[:4],
"outline": get_outline(number),
"director": get_table_el_single_anchor(soup, "video_director"),
"cover": get_cover(lx),
"imagecut": 1,
"actor_photo": "",
"website": result.url,
"source": "javlib.py",
"actor": get_table_el_multi_anchor(soup, "video_cast"),
"label": get_table_el_td(soup, "video_label"),
"tag": get_table_el_multi_anchor(soup, "video_genres"),
"number": get_table_el_td(soup, "video_id"),
"release": get_table_el_td(soup, "video_date"),
"runtime": get_from_xpath(lx, '//*[@id="video_length"]/table/tr/td[2]/span/text()'),
"series": '',
}
else:
dic = {"title": ""}
return json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'))
def main(number: str):
number = number.upper()
oldNumber = number
if re.match(r'^([0-9]+)ID-(.+)$', number):
g = re.search(r'^([0-9]+)ID-(.+)$', number)
number = 'ID-' + g[1] + g[2]
# raw_cookies, user_agent = get_javlib_cookie()
#
# #Blank cookies mean javlib site return error
# if not raw_cookies:
# return json.dumps({}, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'))
#
# #Manually construct a dictionary
# s_cookie = SimpleCookie()
# s_cookie.load(raw_cookies)
# cookies = {}
# for key, morsel in s_cookie.items():
# cookies[key] = morsel.value
# Scraping
result = get_html(
"http://www.b47w.com/cn/vl_searchbyid.php?keyword={}".format(number),
# cookies=cookies,
# ua=user_agent,
return_type="object")
soup = BeautifulSoup(result.text, "html.parser")
lx = html.fromstring(str(soup))
multiLabel = get_from_xpath(lx, '//*[@id="rightcolumn"]/div[1]/text()')
if multiLabel.find('识别码搜寻结果') > 0:
links = []
titles = []
for i in range(1, get_link_count(lx) + 1):
id, href, title = get_link(lx, i)
if title.count('（ブルーレイディスク）') > 0:
continue
if id.upper() == number:
links.append('http://www.b47w.com/cn' + href)
titles.append(title)
link = ''
if len(links) > 1:
for i, link in enumerate(links):
print(str(i + 1) + ": " + titles[i])
print(link)
index = int(input("input index: ")) - 1
if index < 0 or index >= len(links):
raise ValueError("out of range")
link = links[index]
else:
link = links[0]
if link == '':
raise ValueError("no match")
result = get_html(link, return_type="object")
soup = BeautifulSoup(result.text, "html.parser")
lx = html.fromstring(str(soup))
try:
dww_htmlcode = fanza.main_htmlcode(getCID(lx))
except:
dww_htmlcode = ''
realnumber = get_table_el_td(soup, "video_id")
if oldNumber != number:
realnumber = oldNumber
if "/?v=jav" in result.url:
dic = {
"title":
get_title(lx, soup),
"studio":
get_table_el_single_anchor(soup, "video_maker"),
"year":
get_table_el_td(soup, "video_date")[:4],
"outline":
getOutline(dww_htmlcode),
"director":
get_table_el_single_anchor(soup, "video_director"),
"cover":
get_cover(lx),
"imagecut":
1,
"actor_photo":
"",
"website":
result.url.replace('www.b47w.com', 'www.javlibrary.com'),
"source":
"javlib.py",
"actor":
get_table_el_multi_anchor(soup, "video_cast"),
"label":
get_table_el_single_anchor(soup, "video_label"),
"tag":
getTag(get_table_el_multi_anchor(soup, "video_genres")),
"number":
realnumber,
"release":
get_table_el_td(soup, "video_date"),
"runtime":
get_from_xpath(
lx, '//*[@id="video_length"]/table/tr/td[2]/span/text()'),
"series":
'',
}
else:
dic = {}
return json.dumps(dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':'))
