def getCover_small(number): # 从avsox获取封面图
htmlcode = get_html('https://avsox.host/cn/search/' + number)
html = etree.fromstring(htmlcode,
etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
if result == '' or result == 'null' or result == 'None':
htmlcode = get_html('https://avsox.host/cn/search/' +
number.replace('-', '_'))
html = etree.fromstring(
htmlcode, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result = str(
html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
if result == '' or result == 'null' or result == 'None':
htmlcode = get_html('https://avsox.host/cn/search/' +
number.replace('_', ''))
html = etree.fromstring(htmlcode, etree.HTMLParser())
counts = len(html.xpath("//div[@id='waterfall']/div/a/div"))
if counts == 0:
return ''
for count in range(1, counts + 1): # 遍历搜索结果，找到需要的番号
number_get = html.xpath(
"//div[@id='waterfall']/div[" + str(count) +
"]/a/div[@class='photo-info']/span/date[1]/text()")
if len(number_get) > 0 and number_get[0] == number:
cover_small = html.xpath(
"//div[@id='waterfall']/div[" + str(count) +
"]/a/div[@class='photo-frame']/img/@src")[0]
return cover_small
return ''
def find_number(number):
# =======================================================================有码搜索
if not (re.match('^\d{4,}', number) or re.match('n\d{4}', number) or 'HEYZO' in number.upper()):
htmlcode = get_html('https://www.javbus.com/search/' + number + '&type=1')
html = etree.fromstring(htmlcode, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
counts = len(html.xpath("//div[@id='waterfall']/div[@id='waterfall']/div"))
if counts != 0:
for count in range(1, counts + 1): # 遍历搜索结果，找到需要的番号
number_get = html.xpath("//div[@id='waterfall']/div[@id='waterfall']/div[" + str(count) + "]/a[@class='movie-box']/div[@class='photo-info']/span/date[1]/text()")[0]
number_get = number_get.upper()
number = number.upper()
if number_get == number or number_get == number.replace('-', '') or number_get == number.replace('_', ''):
result_url = html.xpath(
"//div[@id='waterfall']/div[@id='waterfall']/div[" + str(count) + "]/a[@class='movie-box']/@href")[0]
return result_url
# =======================================================================无码搜索
htmlcode = get_html('https://www.javbus.com/uncensored/search/' + number + '&type=1')
html = etree.fromstring(htmlcode, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
counts = len(html.xpath("//div[@id='waterfall']/div[@id='waterfall']/div"))
if counts == 0:
return 'not found'
for count in range(1, counts + 1): # 遍历搜索结果，找到需要的番号
number_get = html.xpath("//div[@id='waterfall']/div[@id='waterfall']/div[" + str(count) + "]/a[@class='movie-box']/div[@class='photo-info']/span/date[1]/text()")[0]
number_get = number_get.upper()
number = number.upper()
if number_get == number or number_get == number.replace('-', '') or number_get == number.replace('_', ''):
result_url = html.xpath(
"//div[@id='waterfall']/div[@id='waterfall']/div[" + str(count) + "]/a[@class='movie-box']/@href")[0]
return result_url
elif number_get == number.replace('-', '_') or number_get == number.replace('_', '-'):
result_url = html.xpath(
"//div[@id='waterfall']/div[@id='waterfall']/div[" + str(count) + "]/a[@class='movie-box']/@href")[0]
return result_url
return 'not found'
def getOutlineScore(number): # 获取简介
outline = ''
score = ''
try:
response = post_html("https://www.jav321.com/search", query={"sn": number})
detail_page = etree.fromstring(response, etree.HTMLParser())
outline = str(detail_page.xpath('/html/body/div[2]/div[1]/div[1]/div[2]/div[3]/div/text()')).strip(" ['']")
if re.search(r'<b>评分</b>: <img data-original="/img/(\d+).gif" />', response):
score = re.findall(r'<b>评分</b>: <img data-original="/img/(\d+).gif" />', response)[0]
score = str(float(score) / 10.0)
else:
score = str(re.findall(r'<b>评分</b>: ([^<]+)<br>', response)).strip(" [',']").replace('\'', '')
if outline == '':
dmm_htmlcode = get_html(
"https://www.dmm.co.jp/search/=/searchstr=" + number.replace('-', '') + "/sort=ranking/")
if 'に一致する商品は見つかりませんでした' not in dmm_htmlcode:
dmm_page = etree.fromstring(dmm_htmlcode, etree.HTMLParser())
url_detail = str(dmm_page.xpath('//*[@id="list"]/li[1]/div/p[2]/a/@href')).split(',', 1)[0].strip(
" ['']")
if url_detail != '':
dmm_detail = get_html(url_detail)
html = etree.fromstring(dmm_detail, etree.HTMLParser())
outline = str(html.xpath('//*[@class="mg-t0 mg-b20"]/text()')).strip(" ['']").replace('\\n', '').replace('\n', '')
except Exception as error_info:
print('Error in javbus.getOutlineScore : ' + str(error_info))
return outline, score
def main(number):
htmlcode = get_html(
'https://www.dmm.co.jp/digital/videoa/-/detail/=/cid=' + number)
url = 'https://www.dmm.co.jp/digital/videoa/-/detail/=/cid=' + number
if '404 Not Found' in htmlcode:
htmlcode = get_html('https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=' +
number)
url = 'https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=' + number
if '404 Not Found' in htmlcode:
dic = {
'title': '',
'website': '',
}
js = json.dumps(dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':')) # .encode('UTF-8')
return js
try:
actor = getActor(htmlcode)
dic = {
'title': getTitle(htmlcode).strip(getActor(htmlcode)),
'studio': getStudio(htmlcode),
'publisher': getPublisher(htmlcode),
'outline': getOutline(htmlcode),
'runtime': getRuntime(htmlcode),
'director': getDirector(htmlcode),
'actor': actor,
'release': getRelease(htmlcode),
'number': getNum(htmlcode),
'cover': getCover(htmlcode, number),
'imagecut': 1,
'tag': getTag(htmlcode),
'series': getSeries(htmlcode),
'year': getYear(getRelease(
htmlcode)), # str(re.search('\d{4}',getRelease(a)).group()),
'actor_photo': getActorPhoto(actor),
'website': url,
'source': 'dmm.py',
}
except:
if htmlcode == 'ProxyError':
dic = {
'title': '',
'website': 'timeout',
}
else:
dic = {
'title': '',
'website': '',
}
js = json.dumps(dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':')) # .encode('UTF-8')
return js
def getOutline(number): # 获取简介
try:
dww_htmlcode = get_html('https://www.dmm.co.jp/digital/videoa/-/detail/=/cid=' + number.replace("-", '00'))
if '404 Not Found' in dww_htmlcode:
dww_htmlcode = get_html('https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=' + number.replace("-", '00'))
except:
dww_htmlcode = ''
html = etree.fromstring(dww_htmlcode, etree.HTMLParser())
result = str(html.xpath("//div[@class='mg-b20 lh4']/text()")).strip(" ['']")
return result.replace('\n', '').replace('\\n', '').replace('\'', '').replace(',', '').replace(' ', '')
def getOutlineScore(number): # 获取简介
dmm_htmlcode = get_html("https://www.dmm.co.jp/search/=/searchstr=" + number + "/sort=ranking/")
dmm_page = etree.fromstring(dmm_htmlcode, etree.HTMLParser())
dmm_detail = get_html(str(dmm_page.xpath('//*[@id="list"]/li[1]/div/p[2]/a/@href')).split(',',1)[0].strip(" ['']"))
html = etree.fromstring(dmm_detail, etree.HTMLParser())
outline = str(html.xpath('//*[@class="mg-t0 mg-b20"]/text()')).strip(" ['']")
if outline.strip() == "":
response = post_html("https://www.jav321.com/search", query={"sn": number})
detail_page = etree.fromstring(response, etree.HTMLParser())
outline = str(detail_page.xpath('/html/body/div[2]/div[1]/div[1]/div[2]/div[3]/div/text()')).strip(" ['']")
score = str(html.xpath('//*[@class="d-review__average"]/strong/text()')).strip(" ['']点")
return outline, score
def main(number):
try:
htmlcode = get_html(
'https://www.dmm.co.jp/digital/videoa/-/detail/=/cid=' + number)
url = 'https://www.dmm.co.jp/digital/videoa/-/detail/=/cid=' + number
if '404 Not Found' in htmlcode:
htmlcode = get_html(
'https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=' + number)
url = 'https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=' + number
if '404 Not Found' in htmlcode:
raise Exception('Movie Data not found in dmm!')
if str(htmlcode) == 'ProxyError':
raise TimeoutError
actor = getActor(htmlcode)
dic = {
'title': getTitle(htmlcode).strip(getActor(htmlcode)),
'studio': getStudio(htmlcode),
'publisher': getPublisher(htmlcode),
'outline': getOutline(htmlcode),
'score': getScore(htmlcode),
'runtime': getRuntime(htmlcode),
'director': getDirector(htmlcode),
'actor': actor,
'release': getRelease(htmlcode),
'number': getNum(htmlcode),
'tag': getTag(htmlcode),
'series': getSeries(htmlcode).replace('-', ''),
'year': getYear(getRelease(htmlcode)),
'actor_photo': getActorPhoto(actor),
'cover': getCover(htmlcode, number),
'extrafanart': getExtraFanart(htmlcode),
'imagecut': 1,
'website': url,
'source': 'dmm.py',
}
except TimeoutError:
dic = {
'title': '',
'website': 'timeout',
}
except Exception as error_info:
print('Error in dmm.main : ' + str(error_info))
dic = {
'title': '',
'website': '',
}
js = json.dumps(dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':')) # .encode('UTF-8')
return js
def main(number):
a = get_html('https://avsox.host/cn/search/' + number)
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
if result1 == '' or result1 == 'null' or result1 == 'None':
a = get_html('https://avsox.host/cn/search/' + number.replace('-', '_'))
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
if result1 == '' or result1 == 'null' or result1 == 'None':
a = get_html('https://avsox.host/cn/search/' + number.replace('_', ''))
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
web = get_html(result1)
soup = BeautifulSoup(web, 'lxml')
info = str(soup.find(attrs={'class': 'row movie'}))
try:
dic = {
'actor': getActor(web),
'title': getTitle(web).strip(getNum(web)).strip().replace(' ', '-'),
'studio': getStudio(info),
'publisher': '',
'outline': '', #
'runtime': getRuntime(info),
'director': '', #
'release': getRelease(info),
'number': getNum(info),
'cover': getCover(web),
'cover_small': getCover_small(a, number),
'imagecut': 3,
'tag': getTag(web),
'series': getSeries(info),
'year': getYear(getRelease(info)), # str(re.search('\d{4}',getRelease(a)).group()),
'actor_photo': getActorPhoto(web),
'website': result1,
'source': 'avsox.py',
}
except:
if a == 'ProxyError':
dic = {
'title': '',
'website': 'timeout',
}
else:
dic = {
'title': '',
'website': '',
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js
def main(number, appoint_url):
try:
count, response, url = getUrl(number)
if str(response) == 'ProxyError':
raise TimeoutError
if appoint_url != '':
url = appoint_url
elif url == '':
raise Exception('Movie Data not found in avsox!')
web = get_html(url)
soup = BeautifulSoup(web, 'lxml')
info = str(soup.find(attrs={'class': 'row movie'}))
number = getNum(web)
print(1)
dic = {
'actor': getActor(web),
'title': getTitle(web).strip(number).strip().replace(' ', '-'),
'studio': getStudio(info),
'runtime': getRuntime(info),
'release': getRelease(info),
'number': getNum(info),
'tag': getTag(web),
'series': getSeries(info),
'year': getYear(getRelease(info)),
'actor_photo': getActorPhoto(web),
'cover': getCover(web),
'cover_small': getCover_small(response, count),
'extrafanart': '',
'imagecut': 3,
'director': '',
'publisher': '',
'outline': '',
'score': '',
'website': url,
'source': 'avsox.py',
}
except TimeoutError:
dic = {
'title': '',
'website': 'timeout',
}
except Exception as error_info:
print('Error in avsox.main : ' + str(error_info))
dic = {
'title': '',
'website': '',
}
js = json.dumps(
dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':'),
) # .encode('UTF-8')
return js
# print(main('051119-917'))
# print(main('032620_001'))
# print(main('032620_001', 'https://avsox.host/cn/movie/cb8d28437cff4e90'))
def main(number):
htmlcode2 = get_html(
'http://adult.contents.fc2.com/article_search.php?id=' + number +
'&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
htmlcode = get_html('https://fc2club.com//html/FC2-' + number + '.html')
actor = getActor(htmlcode)
if len(actor) == 0:
actor = 'FC2系列'
try:
dic = {
'title': getTitle(htmlcode).replace(' ', '-'),
'studio': getStudio(htmlcode),
'publisher': '',
'year': '', # str(re.search('\d{4}',getRelease(number)).group()),
'outline': getOutline(htmlcode2).replace('\n', ''),
'runtime': getYear(getRelease(htmlcode)),
'director': '',
'actor': actor.replace('/', ','),
'release': getRelease(number),
'number': 'FC2-' + number,
'cover': getCover(htmlcode, number, htmlcode2),
'imagecut': 0,
'series': '',
'tag': getTag(htmlcode),
'actor_photo': getActorPhoto(actor),
'website': 'https://fc2club.com//html/FC2-' + number + '.html',
'source': 'fc2fans_club.py',
}
except:
if htmlcode2 == 'ProxyError':
dic = {
'title': '',
'website': 'timeout',
}
else:
dic = {
'title': '',
'website': '',
}
js = json.dumps(
dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':'),
) # .encode('UTF-8')
return js
def getActorPhoto(htmlcode):
soup = BeautifulSoup(htmlcode, 'lxml')
a = soup.find_all(attrs={'class': 'star-name'})
d = {}
for i in a:
l = i.a['href']
t = i.get_text()
html = etree.fromstring(get_html(l), etree.HTMLParser())
p = str(html.xpath('//*[@id="waterfall"]/div[1]/div/div[1]/img/@src')).strip(" ['']")
p2 = {t: p}
d.update(p2)
return d
def find_number(number):
htmlcode = get_html('https://xcity.jp/result_published/?q=' +
number.replace('-', ''))
if '該当する作品はみつかりませんでした' in htmlcode:
return 'not found', ''
html = etree.fromstring(htmlcode,
etree.HTMLParser()) # //table/tr[1]/td[1]/text()
counts = len(
html.xpath("//div[@id='searchResult']/table[@class='resultList']/tr"))
if counts >= 2:
for count in range(2, counts + 1): # 遍历搜索结果，找到需要的番号
result_url = 'https://xcity.jp' + html.xpath(
"//div[@id='searchResult']/table[@class='resultList']/tr[" +
str(count) + "]/td[1]/a/@href")[0]
detail_page = get_html(result_url)
detail_page_html = etree.fromstring(detail_page,
etree.HTMLParser())
number_get = str(
detail_page_html.xpath("//span[@id='hinban']/text()")[0])
if number_get.upper() == number.replace('-', '').upper():
return result_url, detail_page
return 'not found', ''
def main(number, appoint_url):
try:
url = 'https://fc2club.com//html/FC2-' + number + '.html'
if appoint_url:
url = appoint_url
htmlcode = get_html(url)
if str(htmlcode) == 'ProxyError':
raise TimeoutError
actor = getActor(htmlcode)
if len(actor) == 0:
actor = 'FC2系列'
dic = {
'title': getTitle(htmlcode).strip(' '),
'studio': getStudio(htmlcode),
'score': getScore(htmlcode),
'runtime': getYear(getRelease(htmlcode)),
'actor': actor.replace('/', ','),
'release': getRelease(number),
'number': 'FC2-' + number,
'tag': getTag(htmlcode),
'actor_photo': getActorPhoto(actor),
'cover': getCover(htmlcode),
'extrafanart': getExtraFanart(htmlcode),
'imagecut': 0,
'director': '',
'series': '',
'publisher': '',
'year': '',
'outline': '',
'website': 'https://fc2club.com//html/FC2-' + number + '.html',
'source': 'fc2fans_club.py',
}
except TimeoutError:
dic = {
'title': '',
'website': 'timeout',
}
except Exception as error_info:
print('Error in fc2fans_club.main : ' + str(error_info))
dic = {
'title': '',
'website': '',
}
js = json.dumps(
dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':'),
)
return js
def main_uncensored(number):
try:
result_url = find_number(number)
if result_url == 'not found':
raise Exception('Movie Data not found in javbus.main_uncensored!')
htmlcode = get_html(result_url)
if str(htmlcode) == 'ProxyError':
raise TimeoutError
number = getNum(htmlcode)
outline = ''
score = ''
if 'HEYZO' in number.upper():
outline, score = getOutlineScore(number)
dic = {
'title': getTitle(htmlcode).replace(number, '').strip().replace(' ', '-'),
'studio': getStudio(htmlcode),
'publisher': '',
'year': getYear(getRelease(htmlcode)),
'outline': outline,
'score': score,
'runtime': getRuntime(htmlcode).replace('分鐘', '').strip(),
'director': getDirector(htmlcode),
'actor': getActor(htmlcode),
'release': getRelease(htmlcode),
'number': getNum(htmlcode),
'cover': getCover(htmlcode),
'extrafanart': getExtraFanart(htmlcode),
'tag': getTag(htmlcode),
'series': getSeries(htmlcode),
'imagecut': 3,
'cover_small': getCover_small(number),
'actor_photo': getActorPhoto(htmlcode),
'website': result_url,
'source': 'javbus.py',
}
if dic['cover_small'] == '':
dic['imagecut'] = 0
except TimeoutError:
dic = {
'title': '',
'website': 'timeout',
}
except Exception as error_info:
print('Error in javbus.main_uncensored : ' + str(error_info))
dic = {
'title': '',
'website': '',
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js
def getCover_small(number): # 从avsox获取封面图
try:
htmlcode = get_html('https://avsox.host/cn/search/' + number)
html = etree.fromstring(htmlcode, etree.HTMLParser())
counts = len(html.xpath("//div[@id='waterfall']/div/a/div"))
if counts == 0:
return ''
for count in range(1, counts + 1): # 遍历搜索结果，找到需要的番号
number_get = html.xpath("//div[@id='waterfall']/div[" + str(count) + "]/a/div[@class='photo-info']/span/date[1]/text()")
if len(number_get) > 0 and number_get[0].upper() == number.upper():
cover_small = html.xpath("//div[@id='waterfall']/div[" + str(count) + "]/a/div[@class='photo-frame']/img/@src")[0]
return cover_small
except Exception as error_info:
print('Error in javbus.getCover_small : ' + str(error_info))
return ''
def getUrl(number):
response = get_html('https://avsox.website/cn/search/' + number)
html = etree.fromstring(response,
etree.HTMLParser()) # //table/tr[1]/td[1]/text()
url_list = html.xpath('//*[@id="waterfall"]/div/a/@href')
if len(url_list) > 0:
for i in range(1, len(url_list) + 1):
number_get = str(
html.xpath('//*[@id="waterfall"]/div[' + str(i) +
']/a/div[@class="photo-info"]/span/date[1]/text()')
).strip(" ['']")
if number.upper() == number_get.upper():
page_url = 'https:' + url_list[i - 1]
return i, response, page_url
return 0, response, ''
def main(number):
try:
number = number.upper()
htmlcode = str(
get_html('https://www.mgstage.com/product/product_detail/' + str(number) + '/', cookies={'adc': '1'}))
htmlcode = htmlcode.replace('ahref', 'a href') # 针对a标签、属性中间未分开
if str(htmlcode) == 'ProxyError':
raise TimeoutError
actor = getActor(htmlcode).replace(' ', '')
dic = {
'title': getTitle(htmlcode).replace("\\n", '').replace(' ', '').strip(','),
'studio': getStudio(htmlcode).strip(','),
'publisher': getPublisher(htmlcode).strip(','),
'outline': getOutline(htmlcode).replace('\n', '').strip(','),
'score': getScore(htmlcode).strip(','),
'runtime': getRuntime(htmlcode).strip(','),
'actor': actor.strip(','),
'release': getRelease(htmlcode).strip(','),
'number': getNum(htmlcode).strip(','),
'cover': getCover(htmlcode).strip(','),
'extrafanart': getExtraFanart(htmlcode).strip(','),
'imagecut': 0,
'tag': getTag(htmlcode).strip(','),
'series': getSeries(htmlcode).strip(','),
'year': getYear(getRelease(htmlcode)).strip(','),
'actor_photo': getActorPhoto(actor.split(',')),
'director': '',
'website': 'https://www.mgstage.com/product/product_detail/' + str(number) + '/',
'source': 'mgstage.py',
}
except TimeoutError:
dic = {
'title': '',
'website': 'timeout',
}
except Exception as error_info:
print('Error in mgstage.main : ' + str(error_info))
dic = {
'title': '',
'website': '',
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js
def main(number):
number = number.upper()
htmlcode = str(
get_html('https://www.mgstage.com/product/product_detail/' +
str(number) + '/',
cookies={'adc': '1'}))
soup = BeautifulSoup(htmlcode, 'lxml')
a = str(soup.find(attrs={'class': 'detail_data'})).replace(
'\n ',
'').replace(' ',
'').replace('\n ',
'').replace('\n ', '')
try:
actor = getActor(a).replace(' ', '')
dic = {
'title':
getTitle(htmlcode).replace("\\n", '').replace(' ', ''),
'studio':
getStudio(a),
'publisher':
getPublisher(a),
'outline':
getOutline(htmlcode).replace('\n', ''),
'runtime':
getRuntime(a),
'director':
'',
'actor':
actor,
'release':
getRelease(a),
'number':
getNum(a),
'cover':
getCover(htmlcode),
'imagecut':
0,
'tag':
getTag(a).strip(','),
'series':
getSeries(a).strip(','),
'year':
getYear(getRelease(
a)), # str(re.search('\d{4}',getRelease(a)).group()),
'actor_photo':
getActorPhoto(actor.split(',')),
'website':
'https://www.mgstage.com/product/product_detail/' + str(number) +
'/',
'source':
'mgstage.py',
}
except:
if htmlcode == 'ProxyError':
dic = {
'title': '',
'website': 'timeout',
}
else:
dic = {
'title': '',
'website': '',
}
js = json.dumps(
dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':'),
) # .encode('UTF-8')
return js
def main_us(number):
try:
htmlcode = get_html('https://www.javbus.zone/search/' + number)
if str(htmlcode) == 'ProxyError':
raise TimeoutError
html = etree.fromstring(htmlcode, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
counts = len(html.xpath("//div[@class='row']/div[@id='waterfall']/div"))
if counts == 0:
raise Exception('Movie Data not found in javbus.main_us!')
result_url = ''
cover_small = ''
for count in range(1, counts + 1): # 遍历搜索结果，找到需要的番号
number_get = html.xpath("//div[@id='waterfall']/div[" + str(
count) + "]/a[@class='movie-box']/div[@class='photo-info']/span/date[1]/text()")[0]
if number_get.upper() == number.upper() or number_get.replace('-', '').upper() == number.upper():
result_url = html.xpath(
"//div[@id='waterfall']/div[" + str(count) + "]/a[@class='movie-box']/@href")[0]
cover_small = html.xpath(
"//div[@id='waterfall']/div[" + str(
count) + "]/a[@class='movie-box']/div[@class='photo-frame']/img[@class='img']/@src")[0]
break
if result_url == '':
raise Exception('Movie Data not found in javbus.main_us!')
htmlcode = get_html(result_url)
if str(htmlcode) == 'ProxyError':
raise TimeoutError
number = getNum(htmlcode)
dic = {
'title': getTitle(htmlcode).replace(number, '').strip(),
'studio': getStudio(htmlcode),
'year': getYear(getRelease(htmlcode)),
'runtime': getRuntime(htmlcode).replace('分鐘', '').strip(),
'director': getDirector(htmlcode),
'actor': getActor(htmlcode),
'release': getRelease(htmlcode),
'number': getNum(htmlcode),
'tag': getTag(htmlcode),
'series': getSeries(htmlcode),
'cover': getCover(htmlcode),
'cover_small': cover_small,
'imagecut': 3,
'actor_photo': getActorPhoto(htmlcode),
'publisher': '',
'outline': '',
'score': '',
'website': result_url,
'source': 'javbus.py',
}
except TimeoutError:
dic = {
'title': '',
'website': 'timeout',
}
except Exception as error_info:
print('Error in javbus.main_us : ' + str(error_info))
dic = {
'title': '',
'website': '',
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js
def main(number, appoint_url=''):
# fanza allow letter + number + underscore, normalize the input here
# @note: I only find the usage of underscore as h_test123456789
fanza_search_number = number
# AV_Data_Capture.py.getNumber() over format the input, restore the h_ prefix
if fanza_search_number.startswith("h-"):
fanza_search_number = fanza_search_number.replace("h-", "h_")
fanza_search_number = re.sub(r"[^0-9a-zA-Z_]", "", fanza_search_number).lower()
fanza_urls = [
"https://www.dmm.co.jp/digital/videoa/-/detail/=/cid=",
"https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=",
"https://www.dmm.co.jp/digital/anime/-/detail/=/cid=",
"https://www.dmm.co.jp/mono/anime/-/detail/=/cid=",
"https://www.dmm.co.jp/digital/videoc/-/detail/=/cid=",
"https://www.dmm.co.jp/digital/nikkatsu/-/detail/=/cid=",
"https://www.dmm.co.jp/rental/-/detail/=/cid=",
]
chosen_url = ""
htmlcode = ''
if appoint_url:
chosen_url = appoint_url
htmlcode = get_html(
"https://www.dmm.co.jp/age_check/=/declared=yes/?{}".format(
urlencode({"rurl": appoint_url})
))
else:
for url in fanza_urls:
chosen_url = url + fanza_search_number
final_url = "https://www.dmm.co.jp/age_check/=/declared=yes/?{}".format(
urlencode({"rurl": chosen_url})
)
htmlcode = get_html(final_url)
if "404 Not Found" not in htmlcode:
break
if "404 Not Found" in htmlcode:
return json.dumps({"title": "", 'website': ''})
try:
# for some old page, the input number does not match the page
# for example, the url will be cid=test012
# but the hinban on the page is test00012
# so get the hinban first, and then pass it to following functions
fanza_hinban = getNum(htmlcode)
release = getRelease(htmlcode)
dic = {
"title": getTitle(htmlcode).strip(),
'publisher': getPublisher(htmlcode),
'score': getScore(htmlcode),
"studio": getStudio(htmlcode),
"outline": getOutline(htmlcode),
"runtime": getRuntime(htmlcode),
"director": getDirector(htmlcode) if "anime" not in chosen_url else "",
"actor": getActor(htmlcode) if "anime" not in chosen_url else "",
"release": release,
"number": fanza_hinban,
"cover": getCover(htmlcode, fanza_hinban),
"imagecut": 1,
"tag": getTag(htmlcode),
"extrafanart": getExtrafanart(htmlcode),
"label": getLabel(htmlcode),
"year": getYear(release), # str(re.search('\d{4}',getRelease(a)).group()),
"actor_photo": "",
"website": chosen_url,
"source": "fanza.py",
"series": getSeries(htmlcode),
}
except TimeoutError:
dic = {
'title': '',
'website': 'timeout',
}
except Exception as error_info:
print('Error in dmm.main : ' + str(error_info))
dic = {
'title': '',
'website': '',
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':')) # .encode('UTF-8')
return js
def main_us(number):
try:
# ========================================================================搜索番号
htmlcode = get_html('https://javdb.com/search?q=' + number +
'&f=all').replace(u'\xa0', u' ')
if str(htmlcode) == 'ProxyError':
raise TimeoutError
html = etree.fromstring(
htmlcode, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
counts = len(
html.xpath(
'//div[@id=\'videos\']/div[@class=\'grid columns\']/div[@class=\'grid-item column\']'
))
if counts == 0:
raise Exception('Movie Data not found in javdb.main_us!')
# ========================================================================遍历搜索结果，找到需要的番号所在URL
number_series = number.split('.')[0]
number_date = '20' + number.replace(number_series, '').strip('.')
number_date = number_date.replace('.', '-')
count = 1
movie_found = 0
for count in range(1, counts + 1): # 遍历搜索结果，找到需要的番号
series_get = html.xpath(
'//div[@id=\'videos\']/div[@class=\'grid columns\']/div[@class=\'grid-item column\']['
+ str(count) +
']/a[@class=\'box\']/div[@class=\'uid2\']/text()')[0]
date_get = html.xpath(
'//div[@id=\'videos\']/div[@class=\'grid columns\']/div[@class=\'grid-item column\']['
+ str(count) +
']/a[@class=\'box\']/div[@class=\'meta\']/text()')[0]
if re.search('\d{4}-\d{1,2}-\d{1,2}', date_get):
date_get = re.findall('\d{4}-\d{1,2}-\d{1,2}', date_get)[0]
series_get = series_get.replace(' ', '')
if (series_get.upper() == number_series.upper()
or series_get.replace('-', '').upper()
== number_series.upper()) and number_date == date_get:
movie_found = 1
break
if movie_found == 0:
raise Exception('Movie Data not found in javdb.main_us!')
result_url = 'https://javdb.com' + html.xpath(
'//*[@id="videos"]/div/div/a/@href')[count - 1]
# ========================================================================请求、判断结果
html_info = get_html(result_url).replace(u'\xa0', u' ')
if str(html_info) == 'ProxyError':
raise TimeoutError
# ========================================================================收集信息
actor = getActor(html_info)
number = getNumber(html_info)
dic = {
'actor':
str(actor).strip(" [',']").replace('\'', ''),
'title':
getTitle(html_info).replace('中文字幕', '').replace("\\n", '').replace(
'_', '-').replace(number, '').strip(),
'studio':
getStudio(html_info),
'publisher':
getPublisher(html_info),
'outline':
'',
'score':
getScore(html_info),
'runtime':
getRuntime(html_info).replace(' 分鍾', ''),
'director':
getDirector(html_info),
'release':
getRelease(html_info),
'number':
number,
'cover':
getCover_us(html_info),
'cover_small':
getCover_small(htmlcode, count - 1),
'extrafanart':
getExtraFanart(html_info),
'imagecut':
3,
'tag':
getTag(html_info),
'series':
getSeries(html_info),
'year':
getYear(getRelease(html_info)
), # str(re.search('\d{4}',getRelease(htmlcode)).group()),
'actor_photo':
getActorPhoto(actor),
'website':
result_url,
'source':
'javdb.py',
}
except TimeoutError:
dic = {
'title': '',
'website': 'timeout',
}
except Exception as error_info:
print('Error in javdb.main_us : ' + str(error_info))
dic = {
'title': '',
'website': '',
}
js = json.dumps(
dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':'),
) # .encode('UTF-8')
return js
def main(number, isuncensored=False):
try:
# ========================================================================搜索番号
htmlcode = get_html('https://javdb.com/search?q=' + number +
'&f=all').replace(u'\xa0', u' ')
if str(htmlcode) == 'ProxyError':
raise TimeoutError
html = etree.fromstring(
htmlcode, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
counts = len(
html.xpath(
'//div[@id=\'videos\']/div[@class=\'grid columns\']/div[@class=\'grid-item column\']'
))
if counts == 0:
raise Exception('Movie Data not found in javdb.main!')
# ========================================================================遍历搜索结果，找到需要的番号所在URL
count = 1
number_get = ''
movie_found = 0
for count in range(1, counts + 1):
number_get = html.xpath(
'//div[@id=\'videos\']/div[@class=\'grid columns\']/div[@class=\'grid-item column\']['
+ str(count) +
']/a[@class=\'box\']/div[@class=\'uid\']/text()')[0]
if number_get.upper() == number.upper():
movie_found = 1
break
if movie_found == 0:
raise Exception('Movie Data not found in javdb.main!')
result_url = 'https://javdb.com' + html.xpath(
'//*[@id="videos"]/div/div/a/@href')[count - 1]
# ========================================================================请求、判断结果
html_info = get_html(result_url).replace(u'\xa0', u' ')
if str(html_info) == 'ProxyError':
raise TimeoutError
# ========================================================================获取评分、简介
imagecut = 1
cover_small = ''
outline = ''
if isuncensored or re.match('^\d{4,}', number) or re.match(
'n\d{4}', number): # 无码，收集封面、评分
imagecut = 3
cover_small = getCover_small(htmlcode, count - 1)
score = getScore(html_info)
elif 'HEYZO' in number.upper(): # HEYZO，收集封面、评分、简介
imagecut = 3
cover_small = getCover_small(htmlcode, count - 1)
outline, score = getOutlineScore(number)
else: # 其他，收集评分、简介
outline, score = getOutlineScore(number)
# ========================================================================收集信息
actor = getActor(html_info)
if len(actor) == 0 and 'FC2-' in number_get:
actor.append('FC2-NoActor')
dic = {
'actor':
str(actor).strip(" [',']").replace('\'', ''),
'title':
getTitle(html_info).replace('中文字幕', '').replace('無碼', '').replace(
"\\n",
'').replace('_', '-').replace(number_get, '').strip().replace(
' ', '-').replace('--', '-'),
'studio':
getStudio(html_info),
'publisher':
getPublisher(html_info),
'outline':
outline,
'score':
score,
'runtime':
getRuntime(html_info).replace(' 分鍾', ''),
'director':
getDirector(html_info),
'release':
getRelease(html_info),
'number':
number_get,
'cover':
getCover(html_info),
'cover_small':
cover_small,
'extrafanart':
getExtraFanart(html_info),
'imagecut':
imagecut,
'tag':
getTag(html_info),
'series':
getSeries(html_info),
'year':
getYear(getRelease(html_info)
), # str(re.search('\d{4}',getRelease(htmlcode)).group()),
'actor_photo':
getActorPhoto(actor),
'website':
result_url,
'source':
'javdb.py',
}
except TimeoutError:
dic = {
'title': '',
'website': 'timeout',
}
except Exception as error_info:
print('Error in javdb.main : ' + str(error_info))
dic = {
'title': '',
'website': '',
}
js = json.dumps(
dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':'),
) # .encode('UTF-8')
return js
def main(number):
try:
htmlcode = get_html('https://javdb.com/search?q=' + number + '&f=all').replace(u'\xa0', u' ')
html = etree.fromstring(htmlcode, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
counts = len(html.xpath(
'//div[@id=\'videos\']/div[@class=\'grid columns\']/div[@class=\'grid-item column\']'))
if counts == 0:
dic = {
'title': '',
'actor': '',
'website': '',
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4,
separators=(',', ':'), ) # .encode('UTF-8')
return js
count = 1
number_get = ''
movie_found = 0
result_url = ''
for count in range(1, counts + 1): # 遍历搜索结果，找到需要的番号
number_get = html.xpath(
'//div[@id=\'videos\']/div[@class=\'grid columns\']/div[@class=\'grid-item column\'][' + str(
count) + ']/a[@class=\'box\']/div[@class=\'uid\']/text()')[0]
# number_get = number_get.replace('_', '-')
if number_get == number.upper() or number_get == number.lower():
movie_found = 1
break
result_url = 'https://javdb.com' + html.xpath('//*[@id="videos"]/div/div/a/@href')[count - 1]
b = get_html(result_url).replace(u'\xa0', u' ')
actor = getActor(b)
if len(actor) == 0 and 'FC2-' in number_get:
actor.append('FC2-NoActor')
if movie_found == 1:
dic = {
'actor': str(actor).strip(" [',']").replace('\'', ''),
'title': getTitle(b).replace('中文字幕', '').replace("\\n", '').replace('_', '-').replace(number_get,
'').strip().replace(
' ', '-').replace('--', '-'),
'studio': getStudio(b),
'publisher': getPublisher(b),
'outline': getOutline(b).replace('\n', ''),
'runtime': getRuntime(b).replace(' 分鍾', ''),
'director': getDirector(b),
'release': getRelease(b),
'number': number_get,
'cover': getCover(b),
'cover_small': getCover_small(htmlcode, count - 1),
'imagecut': 3,
'tag': getTag(b),
'series': getSeries(b),
'year': getYear(getRelease(b)), # str(re.search('\d{4}',getRelease(htmlcode)).group()),
'actor_photo': getActorPhoto(actor),
'website': result_url,
'source': 'javdb.py',
}
else: # 未找到番号
dic = {
'title': '',
'actor': str(actor).strip(" [',']").replace('\'', ''),
'website': '',
}
except: # actor 用于判断ip是否被封
if htmlcode == 'ProxyError':
dic = {
'title': '',
'actor': '',
'website': 'timeout',
}
else:
dic = {
'title': '',
'actor': '',
'website': '',
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js
def main_uncensored(number):
result_url = find_number(number)
if result_url == 'not found':
dic = {
'title': '',
'actor': '',
'website': '',
}
js = json.dumps(
dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':'),
) # .encode('UTF-8')
return js
htmlcode = get_html(result_url)
try:
number = getNum(htmlcode)
dic = {
'title':
getTitle(htmlcode).replace(number, '').strip().replace(' ', '-'),
'studio':
getStudio(htmlcode),
'publisher':
'',
'year':
getYear(getRelease(htmlcode)),
'outline':
'',
'runtime':
getRuntime(htmlcode).replace('分鐘', '').strip(),
'director':
getDirector(htmlcode),
'actor':
getActor(htmlcode),
'release':
getRelease(htmlcode),
'number':
getNum(htmlcode),
'cover':
getCover(htmlcode),
'tag':
getTag(htmlcode),
'series':
getSeries(htmlcode),
'imagecut':
3,
'cover_small':
getCover_small(number),
'actor_photo':
getActorPhoto(htmlcode),
'website':
result_url,
'source':
'javbus.py',
}
if dic['cover_small'] == '':
dic['imagecut'] = 0
except Exception as error_info:
print('Error in javbus.main_uncensored :' + str(error_info))
if htmlcode == 'ProxyError':
dic = {
'title': '',
'website': 'timeout',
}
else:
dic = {
'title': '',
'website': '',
}
js = json.dumps(
dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':'),
) # .encode('UTF-8')
return js
def main(number, javlibrary_url):
try:
htmlcode = get_html('http://' + javlibrary_url +
'/ja/vl_searchbyid.php?keyword=' + number).replace(
u'\xa0', u' ')
title = getTitle(htmlcode)
movie_found = 1
if title == '': # 页面为搜索结果页，而不是视频信息页，遍历搜索结果
movie_found = 0
html = etree.fromstring(
htmlcode, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
count_all = len(
html.xpath(
"//div[@class='videothumblist']/div[@class='videos']/div[@class='video']"
))
for count in range(1, count_all + 1):
number_get = str(
html.xpath(
"//div[@class='videothumblist']/div[@class='videos']/div["
+ str(count) + "]/a/div[1]/text()")).strip(" ['']")
if number_get == number.upper():
url_get = str(
html.xpath(
"//div[@class='videothumblist']/div[@class='videos']/div["
+ str(count) + "]/a/@href")).strip(" ['.']")
htmlcode = get_html('http://' + javlibrary_url + '/ja' +
url_get).replace(u'\xa0', u' ')
movie_found = 1
break
if movie_found == 1:
try: # 从dmm获取简介
dww_htmlcode = get_html(
"https://www.dmm.co.jp/digital/videoa/-/detail/=/cid=" +
number.replace("-", '00'))
except:
dww_htmlcode = ''
actor = getActor(htmlcode)
number = getNum(htmlcode)
release = getRelease(htmlcode)
dic = {
'actor':
str(actor).strip(" [',']").replace('\'', ''),
'title':
getTitle(htmlcode).replace(
'中文字幕', '').replace("\\n", '').replace('_', '-').replace(
number, '').strip().replace(' ',
'-').replace('--', '-'),
'studio':
getStudio(htmlcode),
'publisher':
getPublisher(htmlcode),
'outline':
getOutline(dww_htmlcode).replace('\n', '').replace(
'\\n', '').replace('\'', '').replace(',',
'').replace(' ', ''),
'runtime':
getRuntime(htmlcode),
'director':
str(getDirector(htmlcode)).replace('----', ''),
'release':
release,
'number':
number,
'cover':
getCover(htmlcode),
'imagecut':
1,
'tag':
getTag(htmlcode),
'series':
'',
'year':
getYear(release),
'actor_photo':
getActorPhoto(actor),
'website':
getWebsite(htmlcode),
'source':
'javlibrary.py',
}
else:
dic = {
'title': '',
'website': '',
}
except:
if htmlcode == 'ProxyError':
dic = {
'title': '',
'website': 'timeout',
}
else:
dic = {
'title': '',
'website': '',
}
js = json.dumps(
dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':'),
) # .encode('UTF-8')
return js
def main(number):
result_url = find_number(number)
if result_url == 'not found':
dic = {
'title': '',
'actor': '',
'website': '',
}
js = json.dumps(
dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':'),
) # .encode('UTF-8')
return js
htmlcode = get_html(result_url)
try:
dww_htmlcode = get_html(
"https://www.dmm.co.jp/digital/videoa/-/detail/=/cid=" +
number.replace("-", '00'))
except:
dww_htmlcode = ''
try:
number = getNum(htmlcode)
dic = {
'title':
str(getTitle(htmlcode)).replace(number,
'').strip().replace(' ', '-'),
'studio':
getStudio(htmlcode),
'publisher':
getPublisher(htmlcode),
'year':
getYear(getRelease(htmlcode)),
'outline':
getOutline(dww_htmlcode).replace('\n', '').replace(
'\\n', '').replace('\'', '').replace(',', '').replace(' ', ''),
'runtime':
getRuntime(htmlcode).replace('分鐘', '').strip(),
'director':
getDirector(htmlcode),
'actor':
getActor(htmlcode),
'release':
getRelease(htmlcode),
'number':
number,
'cover':
getCover(htmlcode),
'imagecut':
1,
'tag':
getTag(htmlcode),
'series':
getSeries(htmlcode),
'actor_photo':
getActorPhoto(htmlcode),
'website':
result_url,
'source':
'javbus.py',
}
except Exception as error_info:
print('Error in javbus.main :' + str(error_info))
if htmlcode == 'ProxyError':
dic = {
'title': '',
'website': 'timeout',
}
else:
dic = {
'title': '',
'website': '',
}
js = json.dumps(
dic,
ensure_ascii=False,
sort_keys=True,
indent=4,
separators=(',', ':'),
) # .encode('UTF-8')
return js