修改一些更新
This commit is contained in:
rm
parent
c8f21183f6
commit
ca4e344913
|
|
@ -111,7 +111,7 @@
|
|||
</table>
|
||||
</td>
|
||||
<td class="rowfollow">
|
||||
<a href="comment.php?action=add&pid=130681&type=torrent" title="添加评论">0</a>
|
||||
<a href="" title="添加评论">0</a>
|
||||
</td>
|
||||
<td class="rowfollow nowrap">
|
||||
<span title="2024-01-13 22:24:08">
|
||||
|
|
@ -125,7 +125,7 @@
|
|||
</td>
|
||||
<td class="rowfollow" align="center">
|
||||
<b>
|
||||
<a href="details.php?id=130681&hit=1&dllist=1#seeders">186</a>
|
||||
<a href="details.php?id=130681&hit=1&dllist=1#seeders">123</a>
|
||||
</b>
|
||||
</td>
|
||||
<td class="rowfollow">
|
||||
|
|
|
|||
74
PT/test.py
74
PT/test.py
|
|
@ -4,6 +4,17 @@ import requests
|
|||
import toml
|
||||
from lxml import html as lhtml
|
||||
|
||||
|
||||
def contains_alpha_or_chinese(input_str):
|
||||
s = input_str.strip()
|
||||
# 判断是否包含字母
|
||||
has_alpha = any(char.isalpha() for char in s)
|
||||
# 判断是否包含汉字
|
||||
has_chinese = any('\u4e00' <= char <= '\u9fff' for char in s)
|
||||
# 返回结果
|
||||
return s if has_alpha or has_chinese else None
|
||||
|
||||
|
||||
# headers = {
|
||||
# 'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
|
||||
# 'accept-language': 'zh,zh-CN;q=0.9',
|
||||
|
|
@ -43,24 +54,74 @@ from lxml import html as lhtml
|
|||
# print(f"{section_name} , 5次出现错误，无法访问！！！")
|
||||
# if len(html) == 0:
|
||||
# break
|
||||
with open('/Users/renmeng/Downloads/test.html', 'r', encoding='utf-8') as file:
|
||||
with open('test.html', 'r', encoding='utf-8') as file:
|
||||
html_code = file.read()
|
||||
try:
|
||||
# 使用lxml解析HTML
|
||||
doc = lhtml.fromstring(html_code)
|
||||
# 使用XPath获取目标元素
|
||||
title_elements = doc.xpath('//table[@class="torrents"]//table[@class="torrentname"]//a[@title]/@title')
|
||||
print(title_elements[0])
|
||||
print(f"标题：{title_elements[0]}")
|
||||
second_title_s = doc.xpath(
|
||||
'//table[@class="torrents"]//table[@class="torrentname"]//td[@class="embedded"]/text()[normalize-space()]')
|
||||
|
||||
second_title = ""
|
||||
for text in second_title_s:
|
||||
second_title = contains_alpha_or_chinese(text) if contains_alpha_or_chinese(text) is not None else None
|
||||
print(f"二级标题：{second_title}")
|
||||
|
||||
seed_status = doc.xpath('//table[@class="torrents"]//table[@class="torrentname"]//td[1]//img[@alt]/@alt')
|
||||
if len(seed_status) > 0:
|
||||
print(f"种子状态：{seed_status[1]}")
|
||||
else:
|
||||
print(f"种子状态：{seed_status[0]}")
|
||||
|
||||
seeding_status = doc.xpath(
|
||||
'//table[@class="torrents"]//table[@class="torrentname"]//div[@class="progressarea"]/@title')
|
||||
print(f"做种状态：{seeding_status[0]}")
|
||||
|
||||
comment_count = doc.xpath('//td[@class="rowfollow"][2]//a/text()[normalize-space()]')
|
||||
print(f"评论数：{comment_count[0]}")
|
||||
|
||||
upload_time = doc.xpath('//td[contains(@class, "rowfollow")][4]//span/@title')
|
||||
# for td_element in upload_time:
|
||||
# html_content = lhtml.tostring(td_element, encoding='unicode')
|
||||
# print(html_content)
|
||||
print(f"资源上传时间：{upload_time[0]}")
|
||||
|
||||
size = doc.xpath('//td[@class="rowfollow"][3]/text()[normalize-space()]')
|
||||
print(f"资源大小：{size[0].strip() + '' + size[1].strip()}")
|
||||
|
||||
seed_count = doc.xpath('//td[@class="rowfollow"][4]')[0]
|
||||
print(f"做种数：{seed_count.text_content().strip()}")
|
||||
|
||||
download_count = doc.xpath('//td[@class="rowfollow"][5]')[0]
|
||||
print(f"下载数：{download_count.text_content().strip()}")
|
||||
|
||||
completion_count = doc.xpath('//td[@class="rowfollow"][6]')[0]
|
||||
print(f"完成数：{completion_count.text_content().strip()}")
|
||||
|
||||
publisher = doc.xpath('//td[@class="rowfollow"][7]')[0]
|
||||
print(f"发布者：{publisher.text_content().strip()}")
|
||||
download_link = doc.xpath('//table[@class="torrents"]//table[@class="torrentname"]//img[@class="download"]/parent::a/@href')
|
||||
print(f"下载链接：/{download_link[0]}")
|
||||
# 详情链接地址
|
||||
details_link = doc.xpath('//table[@class="torrents"]//table[@class="torrentname"]//a[@href]/@href')
|
||||
print(f"/{details_link[0]}")
|
||||
print(f"详情链接：/{details_link[0]}")
|
||||
|
||||
douban_rating = doc.xpath('')
|
||||
print(f"豆瓣评分：/{douban_rating[0]}")
|
||||
|
||||
imdb_rating = doc.xpath('')
|
||||
print(f"imdb_rating：/{imdb_rating[0]}")
|
||||
|
||||
|
||||
except Exception as e:
|
||||
print(e)
|
||||
print(f"页面无法解析，请知晓！！！")
|
||||
|
||||
"""
|
||||
主键id,来源名称,一级标题,二级标题,种子状态,状态剩余时间,做种状态,评论数,做种数,下载数,完成数，发布者，豆瓣评分，IMDB评分，下载链接，详情链接,资源大小
|
||||
主键id,来源名称,一级标题,二级标题,种子状态,状态剩余时间,做种状态,评论数,资源上传时间,资源大小，做种数,下载数,完成数，发布者，豆瓣评分，IMDB评分，下载链接，详情链接
|
||||
CREATE TABLE IF NOT EXISTS pt_website_data (
|
||||
id INTEGER PRIMARY KEY,
|
||||
source_name TEXT NOT NULL,
|
||||
|
|
@ -70,6 +131,8 @@ CREATE TABLE IF NOT EXISTS pt_website_data (
|
|||
status_remaining_time TEXT,
|
||||
seeding_status TEXT,
|
||||
comment_count INTEGER,
|
||||
upload_time TEXT,
|
||||
size TEXT,
|
||||
seed_count INTEGER,
|
||||
download_count INTEGER,
|
||||
completion_count INTEGER,
|
||||
|
|
@ -78,7 +141,6 @@ CREATE TABLE IF NOT EXISTS pt_website_data (
|
|||
imdb_rating REAL,
|
||||
download_link TEXT,
|
||||
details_link TEXT,
|
||||
size TEXT,
|
||||
UNIQUE(source_name, first_title, second_title)
|
||||
);
|
||||
|
||||
|
|
@ -88,4 +150,4 @@ CREATE TABLE IF NOT EXISTS pt_website_type (
|
|||
type_name TEXT NOT NULL,
|
||||
type_url TEXT NOT NULL
|
||||
);
|
||||
"""
|
||||
"""
|
||||
|
|
|
|||
Loading…
Reference in New Issue