def main_uncensored(number):
htmlcode = get_html('https://www.javbus.com/ja/' + number)
if getTitle(htmlcode) == '':
htmlcode = get_html('https://www.javbus.com/ja/' +
number.replace('-', '_'))
try:
dww_htmlcode = fanza.main_htmlcode(getCID(htmlcode))
except:
dww_htmlcode = ''
dic = {
'title':
str(re.sub('\w+-\d+-', '',
getTitle(htmlcode))).replace(getNum(htmlcode) + '-', ''),
'studio':
getStudio(htmlcode),
'year':
getYear(htmlcode),
'outline':
getOutline(dww_htmlcode),
'runtime':
getRuntime(htmlcode),
'director':
getDirector(htmlcode),
'actor':
getActor(htmlcode),
'release':
getRelease(htmlcode),
'number':
getNum(htmlcode),
'cover':
getCover(htmlcode),
'tag':
getTag(htmlcode),
'extrafanart':
getExtrafanart(htmlcode),
'label':
getSerise(htmlcode),
'imagecut':
0,
'actor_photo':
'',
'website':
'https://www.javbus.com/ja/' + number,
'source':
'javbus.py',
'series':
getSerise(htmlcode),
}
js = json.dumps(
dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':'),
) # .encode('UTF-8')
return js
def main(number):
try:
try:
try:
htmlcode = get_html('https://www.fanbus.us/' + number)
except:
htmlcode = get_html('https://www.javbus.com/' + number)
try:
dww_htmlcode = fanza.main_htmlcode(getCID(htmlcode))
except:
dww_htmlcode = ''
dic = {
'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
'studio': getStudio(htmlcode),
'year': str(re.search('\d{4}', getYear(htmlcode)).group()),
'outline': getOutline(dww_htmlcode),
'runtime': getRuntime(htmlcode),
'director': getDirector(htmlcode),
'actor': getActor(htmlcode),
'release': getRelease(htmlcode),
'number': getNum(htmlcode),
'cover': getCover(htmlcode),
'imagecut': 1,
'tag': getTag(htmlcode),
'extrafanart': getExtrafanart(htmlcode),
'label': getSerise(htmlcode),
'actor_photo': getActorPhoto(htmlcode),
'website': 'https://www.javbus.com/' + number,
'source': 'javbus.py',
'series': getSerise(htmlcode),
}
js = json.dumps(
dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':'),
) # .encode('UTF-8')
return js
except:
return main_uncensored(number)
except:
data = {
"title": "",
}
js = json.dumps(data,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(",", ":"))
return js
def main(number):
try:
number = number.upper()
# raw_cookies, user_agent = get_javdb_cookie()
#
# if not raw_cookies:
# return json.dumps({}, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'))
#
# s_cookie = SimpleCookie()
# s_cookie.load(raw_cookies)
# cookies = {}
# for key, morsel in s_cookie.items():
# cookies[key] = morsel.value
#
# correct_url = ''
time.sleep(3)
try:
# 先尝试使用ajax
query_result = get_html(
'https://javdb.com/videos/search_autocomplete.json?q=' +
number)
items = json.loads(query_result)
links = []
titles = []
for item in items:
if item['number'].upper() == number:
links.append('/v/' + item['uid'])
titles.append(item['title'])
if len(links) > 1:
for i, link in enumerate(links):
print(str(i + 1) + ": " + titles[i])
print('https://javdb.com' + link)
index = int(input("input index: ")) - 1
if index < 0 or index >= len(links):
raise ValueError("out of range")
correct_url = links[index]
else:
correct_url = links[0]
except:
ok = 0
for i in range(1, 10):
try:
query_result = get_html('https://javdb.com/search?q=' +
number + '&f=all')
except:
query_result = get_html('https://javdb4.com/search?q=' +
number + '&f=all')
html = etree.fromstring(
query_result,
etree.HTMLParser()) # //table/tr[1]/td[1]/text()
if str(
html.xpath(
'/html/body/section/div/div[4]/article/div/text()')
).strip(" ['']") == '':
ok = 1
break
print("请求过于频繁，重试：" + str(i))
time.sleep(30)
if ok == 0:
raise ValueError("retry max")
# javdb sometime returns multiple results,
# and the first elememt maybe not the one we are looking for
# iterate all candidates and find the match one
urls = html.xpath('//*[@id="videos"]/div/div/a/@href')
ids = html.xpath(
'//*[@id="videos"]/div/div/a/div[contains(@class, "uid")]/text()'
)
allTitles = html.xpath(
'//*[@id="videos"]/div/div/a/div[contains(@class, "video-title")]/text()'
)
links = []
titles = []
for i, id in enumerate(ids):
if id.upper() == number:
links.append(urls[i])
titles.append(allTitles[i])
if len(links) > 1:
for i, link in enumerate(links):
print(str(i + 1) + ": " + titles[i])
print('https://javdb.com' + link)
index = int(input("input index: ")) - 1
if index < 0 or index >= len(links):
raise ValueError("out of range")
correct_url = links[index]
else:
correct_url = links[0]
detail_page = get_html('https://javdb.com' + correct_url)
# # If gray image exists ,then replace with normal cover
# cover_small = getCover_small(query_result, index=ids.index(number))
# if 'placeholder' in cover_small:
# cover_small = getCover(detail_page)
try:
dww_htmlcode = fanza.main_htmlcode(getCID(detail_page))
except:
dww_htmlcode = ''
dic = {
'actor': getActor(detail_page),
'title': getTitle(detail_page).replace(getNum(detail_page),
'').strip(),
'studio': getStudio(detail_page),
'outline': getOutline(dww_htmlcode),
'runtime': getRuntime(detail_page),
'director': getDirector(detail_page),
'release': getRelease(detail_page),
'number': getNum(detail_page),
'cover': getCover(detail_page),
# 'cover_small': cover_small,
'imagecut': 1,
'tag': getTag(detail_page),
'label': getLabel(detail_page),
'year':
getYear(getRelease(detail_page)
), # str(re.search('\d{4}',getRelease(a)).group()),
'actor_photo': getActorPhoto(getActor(detail_page)),
'website': 'https://javdb.com' + correct_url,
'source': 'javdb.py',
'series': getSeries(detail_page),
}
title = dic['title']
if title.find('無碼') >= 0:
raise ValueError("unsupport")
except Exception as e:
# print(e)
dic = {"title": ""}
js = json.dumps(
dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':'),
) # .encode('UTF-8')
return js
def main(number):
try:
number = number.upper()
#htmlMultiText = get_html('https://www.javbus.com/search/' + number + '&type=1', cookies={'existmag':'all'})
htmlMultiText = get_html('https://www.javbus.com/uncensored/search/' + number + '&type=1', cookies={'existmag':'all'})
htmlMulti = etree.fromstring(htmlMultiText, etree.HTMLParser())
links = htmlMulti.xpath('//*[@id="waterfall"]/div/a/@href')
titles = htmlMulti.xpath('//*[@id="waterfall"]/div/a/div/span/text()[1]')
ids = htmlMulti.xpath('//*[@id="waterfall"]/div/a/div/span/date[1]/text()[1]')
movieList = []
for i, e in enumerate(links):
if str(ids[i]).upper().replace('_', '-') == number.replace('_', '-'):
movie = {'link':str(links[i]), 'title':str(titles[i]), 'id':str(ids[i])}
movieList.append(movie)
index = 0
if len(movieList) <= 0:
raise ValueError("no movie")
elif len(movieList) >= 2:
for i, link in enumerate(movieList):
print(str(i+1)+": "+movieList[i]['title'])
print(movieList[i]['link'])
index = int(input("input index: "))-1
if index < 0 or index >= len(movieList):
raise ValueError("out of range")
link = movieList[index]['link']
if link == '':
raise ValueError("no match")
htmlcode = get_html(link)
if isUnCensored(htmlcode) != 1:
raise ValueError("unsupport")
try:
dww_htmlcode = fanza.main_htmlcode(getCID(htmlcode))
except:
dww_htmlcode = ''
dic = {
'title': getTitle(htmlcode).replace(getNum(htmlcode),'').strip(),
'studio': getStudio(htmlcode),
'year': str(re.search('\d{4}', getYear(htmlcode)).group()),
'outline': getOutline(dww_htmlcode),
'runtime': getRuntime(htmlcode),
'director': getDirector(htmlcode).strip(),
'actor': getActor(htmlcode),
'release': getRelease(htmlcode),
'number': getNum(htmlcode),
'cover': getCover(htmlcode),
'imagecut': 1,
'tag': getTag(htmlcode),
'label': getSerise(htmlcode),
'actor_photo': getActorPhoto(htmlcode),
'website': 'https://www.javbus.com/' + number,
'source': 'javbus.py',
'series': getSerise(htmlcode),
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4,
separators=(',', ':'), ) # .encode('UTF-8')
return js
except:
data = {
"title": "",
}
js = json.dumps(
data, ensure_ascii=False, sort_keys=True, indent=4, separators=(",", ":")
)
return js
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=(',', ':'))
