def get_brief(mcs, code):
url = "https://avsox.host/cn/search/" + code
rsp = requests.get(url, proxies=proxy)
html = rsp.text
match = re.search(mcs.__url_pattern, html)
if not match:
return None
url = match.group(1)
rsp = requests.get(url, proxies=proxy)
html = rsp.text
bs = bs4.BeautifulSoup(html, "lxml")
movie = bs.select(".movie")[0]
brief = Brief()
brief.code = code
img = movie.select(".screencap", limit=1)[0].a.img
brief.title = img.attrs["title"]
brief.release_date = noexcept(
lambda: re.search(mcs.__release_date_pattern, str(movie)).group(1),
"")
brief.actress = ", ".join(x.text for x in bs.select(
"#avatar-waterfall", limit=1)[0].find_all("span"))
rsp = requests.get(img.attrs["src"], proxies=proxy)
if 300 <= rsp.status_code <= 400:
if "location" in rsp.headers:
brief.preview_img_url = rsp.headers["location"]
elif rsp.status_code == 200:
brief.preview_img_url = img.attrs["src"]
return brief
def release_date(self, date: Union[str, datetime.datetime]):
if isinstance(date, datetime.datetime):
self.__release_date = date
else:
self.__release_date = noexcept(
lambda: datetime.datetime.strptime(date, "%Y-%m-%d"), None
)
def __get_brief_from_tr(mcs, tr):
brief = Brief()
brief.preview_img_url = noexcept(lambda: tr.attrs["data-img"])
if brief.preview_img_url and brief.preview_img_url.startswith("/"):
brief.preview_img_url = "http://warashi-asian-pornstars.fr" + brief.preview_img_url
tds = tr.select("td")
brief.title = tds[1].text.strip()
brief.code = tds[2].text.upper()
brief.release_date = tds[5].text.strip()
return brief
def get_history_names_by_li(mcs, li):
url = noexcept(
lambda: re.search(Etigoya.url_pattern, str(li)).group(0))
if not url:
return []
html = requests.get(url, proxies=proxy).text
names = [
re.sub(Etigoya.purify_pattern, "", s).strip()
for s in re.findall(Etigoya.name_pattern, html)
]
return names
def get_brief_from_a_card(card_tag):
release_date = noexcept(lambda: datetime.datetime.strptime(
re.search(r"\d\d\d\d-\d\d-\d\d", card_tag.text).group(0),
"%Y-%m-%d"))
actress = list(
map(lambda x: x.text,
card_tag.find_all(name="a", attrs={"class": "btn-danger"})))
img = noexcept(lambda: card_tag.find(name="img").attrs["data-src"])
if not img.startswith("http"):
img = "http:" + img
brief = Brief()
brief.preview_img_url = img
brief.title = noexcept(lambda: card_tag.find(name="h5").text.strip(),
"")
brief.actress = ", ".join(actress)
brief.release_date = release_date
brief.code = card_tag.find(name="h4").text.strip()
return brief
def __check_name_in_box(mcs, name, box):
if name not in box.text.lower():
return None
title = box.find(name="p").text.lower()
jp_name = title.split("-")[1].strip()
if not jp_name:
return None
# cache for later parsing actress info, None for no url
url = noexcept(lambda: box.a.attrs["href"])
detail_url = "http://warashi-asian-pornstars.fr/%s" % url
mcs.__actress_detail_url[name] = detail_url
mcs.__actress_detail_url[jp_name] = detail_url
return jp_name
def __get_brief_from_card(card):
code = card.select(".tag.is-link.is-light")[0].text.strip()
actress = ", ".join(
(x.text.strip() for x in card.select(".tag.is-primary.is-light")))
h5 = card.select(".title")[0]
title = h5.text.strip()
img = noexcept(lambda: h5.a.attrs["rel"][0])
release_date = card.select("footer")[0].p.text.strip()
brief = Brief()
brief.title = title
brief.preview_img_url = img
brief.code = code
brief.actress = actress
brief.release_date = release_date
return brief
def __get_brief_by_card(card):
columns = card.select(".column")
if not columns: # like 飯岡かなこ
return None
code = columns[4].next.strip()
actress = ", ".join(
(x.text.strip() for x in columns[2].find_all(name="span")))
title = columns[3].text.strip()
img = noexcept(lambda: columns[3].a.attrs["rel"][0])
release_date = columns[1].text.strip()
brief = Brief()
brief.title = title
brief.preview_img_url = img
brief.code = code
brief.actress = actress
brief.release_date = release_date
return brief
def search_by_code(mcs, code):
url = "http://www5.javmost.com/" + code + "/"
main_rsp = mcs.__client.get(url, proxies=proxy)
if main_rsp.status_code != 200:
return None
img = noexcept(
lambda: re.search(r"<meta property=\"og:image\" content=\"(.+?)\"",
main_rsp.text).group(1))
if not img:
return None
# Nov. 13 adding: https://www5.javmost.com/IENE-623/
if not img.startswith("http:"):
img = "http:" + img
bs = bs4.BeautifulSoup(main_rsp.text, "lxml")
buttons = bs.select(".tab-overflow")[0].find_all(name="li")[1:-1]
var_value = re.search("'value':(.+?),", main_rsp.text).group(1)
value = re.search("var %s = '(.+?)'" % var_value,
main_rsp.text).group(1)
url = wait_until([
submit(mcs.__try_one_button, button, value, main_rsp)
for button in buttons
])
if not url:
return None
av = AV()
av.preview_img_url = img
av.video_url = url
av.code = code
return av
def processor(*x, **kwx):
_args = args
for i in args_place_holders:
_args[i] = x[i]
return noexcept(lambda: func(*_args, **fixed_kwargs, **kwx))
