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=(',', ':'))