mirror of
https://github.com/jxxghp/MoviePilot.git
synced 2026-05-12 10:57:16 +08:00
fix etree
This commit is contained in:
jxxghp
@@ -34,21 +34,25 @@ class NexusPhpSiteUserInfo(SiteParserBase):
|
||||
:return:
|
||||
"""
|
||||
html = etree.HTML(html_text)
|
||||
if not StringUtils.is_valid_html_element(html):
|
||||
return
|
||||
try:
|
||||
if not StringUtils.is_valid_html_element(html):
|
||||
return
|
||||
|
||||
message_labels = html.xpath('//a[@href="messages.php"]/..')
|
||||
message_labels.extend(html.xpath('//a[contains(@href, "messages.php")]/..'))
|
||||
if message_labels:
|
||||
message_text = message_labels[0].xpath("string(.)")
|
||||
message_labels = html.xpath('//a[@href="messages.php"]/..')
|
||||
message_labels.extend(html.xpath('//a[contains(@href, "messages.php")]/..'))
|
||||
if message_labels:
|
||||
message_text = message_labels[0].xpath("string(.)")
|
||||
|
||||
logger.debug(f"{self._site_name} 消息原始信息 {message_text}")
|
||||
message_unread_match = re.findall(r"[^Date](信息箱\s*|\((?![^)]*:)|你有\xa0)(\d+)", message_text)
|
||||
logger.debug(f"{self._site_name} 消息原始信息 {message_text}")
|
||||
message_unread_match = re.findall(r"[^Date](信息箱\s*|\((?![^)]*:)|你有\xa0)(\d+)", message_text)
|
||||
|
||||
if message_unread_match and len(message_unread_match[-1]) == 2:
|
||||
self.message_unread = StringUtils.str_int(message_unread_match[-1][1])
|
||||
elif message_text.isdigit():
|
||||
self.message_unread = StringUtils.str_int(message_text)
|
||||
if message_unread_match and len(message_unread_match[-1]) == 2:
|
||||
self.message_unread = StringUtils.str_int(message_unread_match[-1][1])
|
||||
elif message_text.isdigit():
|
||||
self.message_unread = StringUtils.str_int(message_text)
|
||||
finally:
|
||||
if html is not None:
|
||||
del html
|
||||
|
||||
def _parse_user_base_info(self, html_text: str):
|
||||
"""
|
||||
@@ -61,18 +65,23 @@ class NexusPhpSiteUserInfo(SiteParserBase):
|
||||
self._parse_message_unread(html_text)
|
||||
|
||||
html = etree.HTML(html_text)
|
||||
if not StringUtils.is_valid_html_element(html):
|
||||
return
|
||||
try:
|
||||
if not StringUtils.is_valid_html_element(html):
|
||||
return
|
||||
|
||||
ret = html.xpath(f'//a[contains(@href, "userdetails") and contains(@href, "{self.userid}")]//b//text()')
|
||||
if ret:
|
||||
self.username = str(ret[0])
|
||||
return
|
||||
ret = html.xpath(f'//a[contains(@href, "userdetails") and contains(@href, "{self.userid}")]//text()')
|
||||
if ret:
|
||||
self.username = str(ret[0])
|
||||
ret = html.xpath(f'//a[contains(@href, "userdetails") and contains(@href, "{self.userid}")]//b//text()')
|
||||
if ret:
|
||||
self.username = str(ret[0])
|
||||
return
|
||||
ret = html.xpath(f'//a[contains(@href, "userdetails") and contains(@href, "{self.userid}")]//text()')
|
||||
if ret:
|
||||
self.username = str(ret[0])
|
||||
|
||||
ret = html.xpath('//a[contains(@href, "userdetails")]//strong//text()')
|
||||
finally:
|
||||
if html is not None:
|
||||
del html
|
||||
|
||||
ret = html.xpath('//a[contains(@href, "userdetails")]//strong//text()')
|
||||
if ret:
|
||||
self.username = str(ret[0])
|
||||
return
|
||||
@@ -98,28 +107,32 @@ class NexusPhpSiteUserInfo(SiteParserBase):
|
||||
self.leeching = StringUtils.str_int(leeching_match.group(2)) if leeching_match and leeching_match.group(
|
||||
2).strip() else 0
|
||||
html = etree.HTML(html_text)
|
||||
has_ucoin, self.bonus = self._parse_ucoin(html)
|
||||
if has_ucoin:
|
||||
return
|
||||
tmps = html.xpath('//a[contains(@href,"mybonus")]/text()') if html else None
|
||||
if tmps:
|
||||
bonus_text = str(tmps[0]).strip()
|
||||
bonus_match = re.search(r"([\d,.]+)", bonus_text)
|
||||
if bonus_match and bonus_match.group(1).strip():
|
||||
self.bonus = StringUtils.str_float(bonus_match.group(1))
|
||||
return
|
||||
bonus_match = re.search(r"mybonus.[\[\]:：<>/a-zA-Z_\-=\"'\s#;.(使用魔力值豆]+\s*([\d,.]+)[<()&\s]", html_text)
|
||||
try:
|
||||
if bonus_match and bonus_match.group(1).strip():
|
||||
self.bonus = StringUtils.str_float(bonus_match.group(1))
|
||||
has_ucoin, self.bonus = self._parse_ucoin(html)
|
||||
if has_ucoin:
|
||||
return
|
||||
bonus_match = re.search(r"[魔力值|\]][\[\]:：<>/a-zA-Z_\-=\"'\s#;]+\s*([\d,.]+|\"[\d,.]+\")[<>()&\s]",
|
||||
html_text,
|
||||
flags=re.S)
|
||||
if bonus_match and bonus_match.group(1).strip():
|
||||
self.bonus = StringUtils.str_float(bonus_match.group(1).strip('"'))
|
||||
except Exception as err:
|
||||
logger.error(f"{self._site_name} 解析魔力值出错, 错误信息: {str(err)}")
|
||||
tmps = html.xpath('//a[contains(@href,"mybonus")]/text()') if html else None
|
||||
if tmps:
|
||||
bonus_text = str(tmps[0]).strip()
|
||||
bonus_match = re.search(r"([\d,.]+)", bonus_text)
|
||||
if bonus_match and bonus_match.group(1).strip():
|
||||
self.bonus = StringUtils.str_float(bonus_match.group(1))
|
||||
return
|
||||
bonus_match = re.search(r"mybonus.[\[\]:：<>/a-zA-Z_\-=\"'\s#;.(使用魔力值豆]+\s*([\d,.]+)[<()&\s]", html_text)
|
||||
try:
|
||||
if bonus_match and bonus_match.group(1).strip():
|
||||
self.bonus = StringUtils.str_float(bonus_match.group(1))
|
||||
return
|
||||
bonus_match = re.search(r"[魔力值|\]][\[\]:：<>/a-zA-Z_\-=\"'\s#;]+\s*([\d,.]+|\"[\d,.]+\")[<>()&\s]",
|
||||
html_text,
|
||||
flags=re.S)
|
||||
if bonus_match and bonus_match.group(1).strip():
|
||||
self.bonus = StringUtils.str_float(bonus_match.group(1).strip('"'))
|
||||
except Exception as err:
|
||||
logger.error(f"{self._site_name} 解析魔力值出错, 错误信息: {str(err)}")
|
||||
finally:
|
||||
if html is not None:
|
||||
del html
|
||||
|
||||
@staticmethod
|
||||
def _parse_ucoin(html):
|
||||
@@ -155,72 +168,76 @@ class NexusPhpSiteUserInfo(SiteParserBase):
|
||||
:return: 下页地址
|
||||
"""
|
||||
html = etree.HTML(str(html_text).replace(r'\/', '/'))
|
||||
if not StringUtils.is_valid_html_element(html):
|
||||
return None
|
||||
try:
|
||||
if not StringUtils.is_valid_html_element(html):
|
||||
return None
|
||||
|
||||
# 首页存在扩展链接，使用扩展链接
|
||||
seeding_url_text = html.xpath('//a[contains(@href,"torrents.php") '
|
||||
'and contains(@href,"seeding")]/@href')
|
||||
if multi_page is False and seeding_url_text and seeding_url_text[0].strip():
|
||||
self._torrent_seeding_page = seeding_url_text[0].strip()
|
||||
return self._torrent_seeding_page
|
||||
# 首页存在扩展链接，使用扩展链接
|
||||
seeding_url_text = html.xpath('//a[contains(@href,"torrents.php") '
|
||||
'and contains(@href,"seeding")]/@href')
|
||||
if multi_page is False and seeding_url_text and seeding_url_text[0].strip():
|
||||
self._torrent_seeding_page = seeding_url_text[0].strip()
|
||||
return self._torrent_seeding_page
|
||||
|
||||
size_col = 3
|
||||
seeders_col = 4
|
||||
# 搜索size列
|
||||
size_col_xpath = '//tr[position()=1]/' \
|
||||
'td[(img[@class="size"] and img[@alt="size"])' \
|
||||
' or (text() = "大小")' \
|
||||
' or (a/img[@class="size" and @alt="size"])]'
|
||||
if html.xpath(size_col_xpath):
|
||||
size_col = len(html.xpath(f'{size_col_xpath}/preceding-sibling::td')) + 1
|
||||
# 搜索seeders列
|
||||
seeders_col_xpath = '//tr[position()=1]/' \
|
||||
'td[(img[@class="seeders"] and img[@alt="seeders"])' \
|
||||
' or (text() = "在做种")' \
|
||||
' or (a/img[@class="seeders" and @alt="seeders"])]'
|
||||
if html.xpath(seeders_col_xpath):
|
||||
seeders_col = len(html.xpath(f'{seeders_col_xpath}/preceding-sibling::td')) + 1
|
||||
size_col = 3
|
||||
seeders_col = 4
|
||||
# 搜索size列
|
||||
size_col_xpath = '//tr[position()=1]/' \
|
||||
'td[(img[@class="size"] and img[@alt="size"])' \
|
||||
' or (text() = "大小")' \
|
||||
' or (a/img[@class="size" and @alt="size"])]'
|
||||
if html.xpath(size_col_xpath):
|
||||
size_col = len(html.xpath(f'{size_col_xpath}/preceding-sibling::td')) + 1
|
||||
# 搜索seeders列
|
||||
seeders_col_xpath = '//tr[position()=1]/' \
|
||||
'td[(img[@class="seeders"] and img[@alt="seeders"])' \
|
||||
' or (text() = "在做种")' \
|
||||
' or (a/img[@class="seeders" and @alt="seeders"])]'
|
||||
if html.xpath(seeders_col_xpath):
|
||||
seeders_col = len(html.xpath(f'{seeders_col_xpath}/preceding-sibling::td')) + 1
|
||||
|
||||
page_seeding = 0
|
||||
page_seeding_size = 0
|
||||
page_seeding_info = []
|
||||
# 如果 table class="torrents"，则增加table[@class="torrents"]
|
||||
table_class = '//table[@class="torrents"]' if html.xpath('//table[@class="torrents"]') else ''
|
||||
seeding_sizes = html.xpath(f'{table_class}//tr[position()>1]/td[{size_col}]')
|
||||
seeding_seeders = html.xpath(f'{table_class}//tr[position()>1]/td[{seeders_col}]/b/a/text()')
|
||||
if not seeding_seeders:
|
||||
seeding_seeders = html.xpath(f'{table_class}//tr[position()>1]/td[{seeders_col}]//text()')
|
||||
if seeding_sizes and seeding_seeders:
|
||||
page_seeding = len(seeding_sizes)
|
||||
page_seeding = 0
|
||||
page_seeding_size = 0
|
||||
page_seeding_info = []
|
||||
# 如果 table class="torrents"，则增加table[@class="torrents"]
|
||||
table_class = '//table[@class="torrents"]' if html.xpath('//table[@class="torrents"]') else ''
|
||||
seeding_sizes = html.xpath(f'{table_class}//tr[position()>1]/td[{size_col}]')
|
||||
seeding_seeders = html.xpath(f'{table_class}//tr[position()>1]/td[{seeders_col}]/b/a/text()')
|
||||
if not seeding_seeders:
|
||||
seeding_seeders = html.xpath(f'{table_class}//tr[position()>1]/td[{seeders_col}]//text()')
|
||||
if seeding_sizes and seeding_seeders:
|
||||
page_seeding = len(seeding_sizes)
|
||||
|
||||
for i in range(0, len(seeding_sizes)):
|
||||
size = StringUtils.num_filesize(seeding_sizes[i].xpath("string(.)").strip())
|
||||
seeders = StringUtils.str_int(seeding_seeders[i])
|
||||
for i in range(0, len(seeding_sizes)):
|
||||
size = StringUtils.num_filesize(seeding_sizes[i].xpath("string(.)").strip())
|
||||
seeders = StringUtils.str_int(seeding_seeders[i])
|
||||
|
||||
page_seeding_size += size
|
||||
page_seeding_info.append([seeders, size])
|
||||
page_seeding_size += size
|
||||
page_seeding_info.append([seeders, size])
|
||||
|
||||
self.seeding += page_seeding
|
||||
self.seeding_size += page_seeding_size
|
||||
self.seeding_info.extend(page_seeding_info)
|
||||
self.seeding += page_seeding
|
||||
self.seeding_size += page_seeding_size
|
||||
self.seeding_info.extend(page_seeding_info)
|
||||
|
||||
# 是否存在下页数据
|
||||
next_page = None
|
||||
next_page_text = html.xpath(
|
||||
'//a[contains(.//text(), "下一页") or contains(.//text(), "下一頁") or contains(.//text(), ">")]/@href')
|
||||
|
||||
# 防止识别到详情页
|
||||
while next_page_text:
|
||||
next_page = next_page_text.pop().strip()
|
||||
if not next_page.startswith('details.php'):
|
||||
break
|
||||
# 是否存在下页数据
|
||||
next_page = None
|
||||
next_page_text = html.xpath(
|
||||
'//a[contains(.//text(), "下一页") or contains(.//text(), "下一頁") or contains(.//text(), ">")]/@href')
|
||||
|
||||
# fix up page url
|
||||
if next_page:
|
||||
if self.userid not in next_page:
|
||||
next_page = f'{next_page}&userid={self.userid}&type=seeding'
|
||||
# 防止识别到详情页
|
||||
while next_page_text:
|
||||
next_page = next_page_text.pop().strip()
|
||||
if not next_page.startswith('details.php'):
|
||||
break
|
||||
next_page = None
|
||||
|
||||
# fix up page url
|
||||
if next_page:
|
||||
if self.userid not in next_page:
|
||||
next_page = f'{next_page}&userid={self.userid}&type=seeding'
|
||||
finally:
|
||||
if html is not None:
|
||||
del html
|
||||
|
||||
return next_page
|
||||
|
||||
@@ -231,57 +248,61 @@ class NexusPhpSiteUserInfo(SiteParserBase):
|
||||
:return:
|
||||
"""
|
||||
html = etree.HTML(html_text)
|
||||
if not StringUtils.is_valid_html_element(html):
|
||||
return
|
||||
try:
|
||||
if not StringUtils.is_valid_html_element(html):
|
||||
return
|
||||
|
||||
self._get_user_level(html)
|
||||
self._get_user_level(html)
|
||||
|
||||
self._fixup_traffic_info(html)
|
||||
self._fixup_traffic_info(html)
|
||||
|
||||
# 加入日期
|
||||
join_at_text = html.xpath(
|
||||
'//tr/td[text()="加入日期" or text()="注册日期" or *[text()="加入日期"]]/following-sibling::td[1]//text()'
|
||||
'|//div/b[text()="加入日期"]/../text()')
|
||||
if join_at_text:
|
||||
self.join_at = StringUtils.unify_datetime_str(join_at_text[0].split(' (')[0].strip())
|
||||
# 加入日期
|
||||
join_at_text = html.xpath(
|
||||
'//tr/td[text()="加入日期" or text()="注册日期" or *[text()="加入日期"]]/following-sibling::td[1]//text()'
|
||||
'|//div/b[text()="加入日期"]/../text()')
|
||||
if join_at_text:
|
||||
self.join_at = StringUtils.unify_datetime_str(join_at_text[0].split(' (')[0].strip())
|
||||
|
||||
# 做种体积 & 做种数
|
||||
# seeding 页面获取不到的话，此处再获取一次
|
||||
seeding_sizes = html.xpath('//tr/td[text()="当前上传"]/following-sibling::td[1]//'
|
||||
'table[tr[1][td[4 and text()="尺寸"]]]//tr[position()>1]/td[4]')
|
||||
seeding_seeders = html.xpath('//tr/td[text()="当前上传"]/following-sibling::td[1]//'
|
||||
'table[tr[1][td[5 and text()="做种者"]]]//tr[position()>1]/td[5]//text()')
|
||||
tmp_seeding = len(seeding_sizes)
|
||||
tmp_seeding_size = 0
|
||||
tmp_seeding_info = []
|
||||
for i in range(0, len(seeding_sizes)):
|
||||
size = StringUtils.num_filesize(seeding_sizes[i].xpath("string(.)").strip())
|
||||
seeders = StringUtils.str_int(seeding_seeders[i])
|
||||
# 做种体积 & 做种数
|
||||
# seeding 页面获取不到的话，此处再获取一次
|
||||
seeding_sizes = html.xpath('//tr/td[text()="当前上传"]/following-sibling::td[1]//'
|
||||
'table[tr[1][td[4 and text()="尺寸"]]]//tr[position()>1]/td[4]')
|
||||
seeding_seeders = html.xpath('//tr/td[text()="当前上传"]/following-sibling::td[1]//'
|
||||
'table[tr[1][td[5 and text()="做种者"]]]//tr[position()>1]/td[5]//text()')
|
||||
tmp_seeding = len(seeding_sizes)
|
||||
tmp_seeding_size = 0
|
||||
tmp_seeding_info = []
|
||||
for i in range(0, len(seeding_sizes)):
|
||||
size = StringUtils.num_filesize(seeding_sizes[i].xpath("string(.)").strip())
|
||||
seeders = StringUtils.str_int(seeding_seeders[i])
|
||||
|
||||
tmp_seeding_size += size
|
||||
tmp_seeding_info.append([seeders, size])
|
||||
tmp_seeding_size += size
|
||||
tmp_seeding_info.append([seeders, size])
|
||||
|
||||
if not self.seeding_size:
|
||||
self.seeding_size = tmp_seeding_size
|
||||
if not self.seeding:
|
||||
self.seeding = tmp_seeding
|
||||
if not self.seeding_info:
|
||||
self.seeding_info = tmp_seeding_info
|
||||
if not self.seeding_size:
|
||||
self.seeding_size = tmp_seeding_size
|
||||
if not self.seeding:
|
||||
self.seeding = tmp_seeding
|
||||
if not self.seeding_info:
|
||||
self.seeding_info = tmp_seeding_info
|
||||
|
||||
seeding_sizes = html.xpath('//tr/td[text()="做种统计"]/following-sibling::td[1]//text()')
|
||||
if seeding_sizes:
|
||||
seeding_match = re.search(r"总做种数:\s+(\d+)", seeding_sizes[0], re.IGNORECASE)
|
||||
seeding_size_match = re.search(r"总做种体积:\s+([\d,.\s]+[KMGTPI]*B)", seeding_sizes[0], re.IGNORECASE)
|
||||
tmp_seeding = StringUtils.str_int(seeding_match.group(1)) if (
|
||||
seeding_match and seeding_match.group(1)) else 0
|
||||
tmp_seeding_size = StringUtils.num_filesize(
|
||||
seeding_size_match.group(1).strip()) if seeding_size_match else 0
|
||||
if not self.seeding_size:
|
||||
self.seeding_size = tmp_seeding_size
|
||||
if not self.seeding:
|
||||
self.seeding = tmp_seeding
|
||||
seeding_sizes = html.xpath('//tr/td[text()="做种统计"]/following-sibling::td[1]//text()')
|
||||
if seeding_sizes:
|
||||
seeding_match = re.search(r"总做种数:\s+(\d+)", seeding_sizes[0], re.IGNORECASE)
|
||||
seeding_size_match = re.search(r"总做种体积:\s+([\d,.\s]+[KMGTPI]*B)", seeding_sizes[0], re.IGNORECASE)
|
||||
tmp_seeding = StringUtils.str_int(seeding_match.group(1)) if (
|
||||
seeding_match and seeding_match.group(1)) else 0
|
||||
tmp_seeding_size = StringUtils.num_filesize(
|
||||
seeding_size_match.group(1).strip()) if seeding_size_match else 0
|
||||
if not self.seeding_size:
|
||||
self.seeding_size = tmp_seeding_size
|
||||
if not self.seeding:
|
||||
self.seeding = tmp_seeding
|
||||
|
||||
self._fixup_torrent_seeding_page(html)
|
||||
self._fixup_torrent_seeding_page(html)
|
||||
finally:
|
||||
if html is not None:
|
||||
del html
|
||||
|
||||
def _fixup_torrent_seeding_page(self, html):
|
||||
"""
|
||||
@@ -348,43 +369,51 @@ class NexusPhpSiteUserInfo(SiteParserBase):
|
||||
|
||||
def _parse_message_unread_links(self, html_text: str, msg_links: list) -> Optional[str]:
|
||||
html = etree.HTML(html_text)
|
||||
if not StringUtils.is_valid_html_element(html):
|
||||
return None
|
||||
try:
|
||||
if not StringUtils.is_valid_html_element(html):
|
||||
return None
|
||||
|
||||
message_links = html.xpath('//tr[not(./td/img[@alt="Read"])]/td/a[contains(@href, "viewmessage")]/@href')
|
||||
msg_links.extend(message_links)
|
||||
# 是否存在下页数据
|
||||
next_page = None
|
||||
next_page_text = html.xpath('//a[contains(.//text(), "下一页") or contains(.//text(), "下一頁")]/@href')
|
||||
if next_page_text:
|
||||
next_page = next_page_text[-1].strip()
|
||||
message_links = html.xpath('//tr[not(./td/img[@alt="Read"])]/td/a[contains(@href, "viewmessage")]/@href')
|
||||
msg_links.extend(message_links)
|
||||
# 是否存在下页数据
|
||||
next_page = None
|
||||
next_page_text = html.xpath('//a[contains(.//text(), "下一页") or contains(.//text(), "下一頁")]/@href')
|
||||
if next_page_text:
|
||||
next_page = next_page_text[-1].strip()
|
||||
finally:
|
||||
if html is not None:
|
||||
del html
|
||||
|
||||
return next_page
|
||||
|
||||
def _parse_message_content(self, html_text):
|
||||
html = etree.HTML(html_text)
|
||||
if not StringUtils.is_valid_html_element(html):
|
||||
return None, None, None
|
||||
# 标题
|
||||
message_head_text = None
|
||||
message_head = html.xpath('//h1/text()'
|
||||
'|//div[@class="layui-card-header"]/span[1]/text()')
|
||||
if message_head:
|
||||
message_head_text = message_head[-1].strip()
|
||||
try:
|
||||
if not StringUtils.is_valid_html_element(html):
|
||||
return None, None, None
|
||||
# 标题
|
||||
message_head_text = None
|
||||
message_head = html.xpath('//h1/text()'
|
||||
'|//div[@class="layui-card-header"]/span[1]/text()')
|
||||
if message_head:
|
||||
message_head_text = message_head[-1].strip()
|
||||
|
||||
# 消息时间
|
||||
message_date_text = None
|
||||
message_date = html.xpath('//h1/following-sibling::table[.//tr/td[@class="colhead"]]//tr[2]/td[2]'
|
||||
'|//div[@class="layui-card-header"]/span[2]/span[2]')
|
||||
if message_date:
|
||||
message_date_text = message_date[0].xpath("string(.)").strip()
|
||||
# 消息时间
|
||||
message_date_text = None
|
||||
message_date = html.xpath('//h1/following-sibling::table[.//tr/td[@class="colhead"]]//tr[2]/td[2]'
|
||||
'|//div[@class="layui-card-header"]/span[2]/span[2]')
|
||||
if message_date:
|
||||
message_date_text = message_date[0].xpath("string(.)").strip()
|
||||
|
||||
# 消息内容
|
||||
message_content_text = None
|
||||
message_content = html.xpath('//h1/following-sibling::table[.//tr/td[@class="colhead"]]//tr[3]/td'
|
||||
'|//div[contains(@class,"layui-card-body")]')
|
||||
if message_content:
|
||||
message_content_text = message_content[0].xpath("string(.)").strip()
|
||||
# 消息内容
|
||||
message_content_text = None
|
||||
message_content = html.xpath('//h1/following-sibling::table[.//tr/td[@class="colhead"]]//tr[3]/td'
|
||||
'|//div[contains(@class,"layui-card-body")]')
|
||||
if message_content:
|
||||
message_content_text = message_content[0].xpath("string(.)").strip()
|
||||
finally:
|
||||
if html is not None:
|
||||
del html
|
||||
|
||||
return message_head_text, message_date_text, message_content_text
|
||||
|
||||
|
||||
Reference in New Issue
Block a user