GithubBackup/MoviePilot
1
0
Fork 0
mirror of https://github.com/jxxghp/MoviePilot.git synced 2026-09-05 15:38:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix etree

Browse Source
This commit is contained in:
jxxghp
2025-07-08 11:00:38 +08:00
parent a8aedba6ff
commit d336bcbf1f
17 changed files with 897 additions and 749 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/modules/indexer/parser/gazelle.py
+92 -81
View File
@@ -14,46 +14,49 @@ class GazelleSiteUserInfo(SiteParserBase):
def _parse_user_base_info(self, html_text: str):
html_text = self._prepare_html_text(html_text)
html = etree.HTML(html_text)
try:
tmps = html.xpath('//a[contains(@href, "user.php?id=")]')
if tmps:
user_id_match = re.search(r"user.php\?id=(\d+)", tmps[0].attrib['href'])
if user_id_match and user_id_match.group().strip():
self.userid = user_id_match.group(1)
self._torrent_seeding_page = f"torrents.php?type=seeding&userid={self.userid}"
self._user_detail_page = f"user.php?id={self.userid}"
self.username = tmps[0].text.strip()
tmps = html.xpath('//a[contains(@href, "user.php?id=")]')
if tmps:
user_id_match = re.search(r"user.php\?id=(\d+)", tmps[0].attrib['href'])
if user_id_match and user_id_match.group().strip():
self.userid = user_id_match.group(1)
self._torrent_seeding_page = f"torrents.php?type=seeding&userid={self.userid}"
self._user_detail_page = f"user.php?id={self.userid}"
self.username = tmps[0].text.strip()
tmps = html.xpath('//*[@id="header-uploaded-value"]/@data-value')
if tmps:
self.upload = StringUtils.num_filesize(tmps[0])
else:
tmps = html.xpath('//li[@id="stats_seeding"]/span/text()')
tmps = html.xpath('//*[@id="header-uploaded-value"]/@data-value')
if tmps:
self.upload = StringUtils.num_filesize(tmps[0])
else:
tmps = html.xpath('//li[@id="stats_seeding"]/span/text()')
if tmps:
self.upload = StringUtils.num_filesize(tmps[0])
tmps = html.xpath('//*[@id="header-downloaded-value"]/@data-value')
if tmps:
self.download = StringUtils.num_filesize(tmps[0])
else:
tmps = html.xpath('//li[@id="stats_leeching"]/span/text()')
tmps = html.xpath('//*[@id="header-downloaded-value"]/@data-value')
if tmps:
self.download = StringUtils.num_filesize(tmps[0])
else:
tmps = html.xpath('//li[@id="stats_leeching"]/span/text()')
if tmps:
self.download = StringUtils.num_filesize(tmps[0])
self.ratio = 0.0 if self.download <= 0.0 else round(self.upload / self.download, 3)
self.ratio = 0.0 if self.download <= 0.0 else round(self.upload / self.download, 3)
tmps = html.xpath('//a[contains(@href, "bonus.php")]/@data-tooltip')
if tmps:
bonus_match = re.search(r"([\d,.]+)", tmps[0])
if bonus_match and bonus_match.group(1).strip():
self.bonus = StringUtils.str_float(bonus_match.group(1))
else:
tmps = html.xpath('//a[contains(@href, "bonus.php")]')
tmps = html.xpath('//a[contains(@href, "bonus.php")]/@data-tooltip')
if tmps:
bonus_text = tmps[0].xpath("string(.)")
bonus_match = re.search(r"([\d,.]+)", bonus_text)
bonus_match = re.search(r"([\d,.]+)", tmps[0])
if bonus_match and bonus_match.group(1).strip():
self.bonus = StringUtils.str_float(bonus_match.group(1))
else:
tmps = html.xpath('//a[contains(@href, "bonus.php")]')
if tmps:
bonus_text = tmps[0].xpath("string(.)")
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))
finally:
if html is not None:
del html
def _parse_site_page(self, html_text: str):
pass
@@ -65,27 +68,31 @@ class GazelleSiteUserInfo(SiteParserBase):
:return:
"""
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
# 用户等级
user_levels_text = html.xpath('//*[@id="class-value"]/@data-value')
if user_levels_text:
self.user_level = user_levels_text[0].strip()
else:
user_levels_text = html.xpath('//li[contains(text(), "用户等级")]/text()')
# 用户等级
user_levels_text = html.xpath('//*[@id="class-value"]/@data-value')
if user_levels_text:
self.user_level = user_levels_text[0].split(':')[1].strip()
self.user_level = user_levels_text[0].strip()
else:
user_levels_text = html.xpath('//li[contains(text(), "用户等级")]/text()')
if user_levels_text:
self.user_level = user_levels_text[0].split(':')[1].strip()
# 加入日期
join_at_text = html.xpath('//*[@id="join-date-value"]/@data-value')
if join_at_text:
self.join_at = StringUtils.unify_datetime_str(join_at_text[0].strip())
else:
join_at_text = html.xpath(
'//div[contains(@class, "box_userinfo_stats")]//li[contains(text(), "加入时间")]/span/text()')
# 加入日期
join_at_text = html.xpath('//*[@id="join-date-value"]/@data-value')
if join_at_text:
self.join_at = StringUtils.unify_datetime_str(join_at_text[0].strip())
else:
join_at_text = html.xpath(
'//div[contains(@class, "box_userinfo_stats")]//li[contains(text(), "加入时间")]/span/text()')
if join_at_text:
self.join_at = StringUtils.unify_datetime_str(join_at_text[0].strip())
finally:
if html is not None:
del html
def _parse_user_torrent_seeding_info(self, html_text: str, multi_page: Optional[bool] = False) -> Optional[str]:
"""
@@ -95,48 +102,52 @@ class GazelleSiteUserInfo(SiteParserBase):
:return: 下页地址
"""
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
size_col = 3
# 搜索size列
if html.xpath('//table[contains(@id, "torrent")]//tr[1]/td'):
size_col = len(html.xpath('//table[contains(@id, "torrent")]//tr[1]/td')) - 3
# 搜索seeders列
seeders_col = size_col + 2
size_col = 3
# 搜索size列
if html.xpath('//table[contains(@id, "torrent")]//tr[1]/td'):
size_col = len(html.xpath('//table[contains(@id, "torrent")]//tr[1]/td')) - 3
# 搜索seeders列
seeders_col = size_col + 2
page_seeding = 0
page_seeding_size = 0
page_seeding_info = []
seeding_sizes = html.xpath(f'//table[contains(@id, "torrent")]//tr[position()>1]/td[{size_col}]')
seeding_seeders = html.xpath(f'//table[contains(@id, "torrent")]//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 = []
seeding_sizes = html.xpath(f'//table[contains(@id, "torrent")]//tr[position()>1]/td[{size_col}]')
seeding_seeders = html.xpath(f'//table[contains(@id, "torrent")]//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 = int(seeding_seeders[i])
for i in range(0, len(seeding_sizes)):
size = StringUtils.num_filesize(seeding_sizes[i].xpath("string(.)").strip())
seeders = int(seeding_seeders[i])
page_seeding_size += size
page_seeding_info.append([seeders, size])
page_seeding_size += size
page_seeding_info.append([seeders, size])
if multi_page:
self.seeding += page_seeding
self.seeding_size += page_seeding_size
self.seeding_info.extend(page_seeding_info)
else:
if not self.seeding:
self.seeding = page_seeding
if not self.seeding_size:
self.seeding_size = page_seeding_size
if not self.seeding_info:
self.seeding_info = page_seeding_info
if multi_page:
self.seeding += page_seeding
self.seeding_size += page_seeding_size
self.seeding_info.extend(page_seeding_info)
else:
if not self.seeding:
self.seeding = page_seeding
if not self.seeding_size:
self.seeding_size = page_seeding_size
if not self.seeding_info:
self.seeding_info = page_seeding_info
# 是否存在下页数据
next_page = None
next_page_text = html.xpath('//a[contains(.//text(), "Next") or contains(.//text(), "下一页")]/@href')
if next_page_text:
next_page = next_page_text[-1].strip()
# 是否存在下页数据
next_page = None
next_page_text = html.xpath('//a[contains(.//text(), "Next") or contains(.//text(), "下一页")]/@href')
if next_page_text:
next_page = next_page_text[-1].strip()
finally:
if html is not None:
del html
return next_page