实现搜索功能

This commit is contained in:
liyp 2023-06-21 15:44:42 +08:00
parent 9d75014e58
commit fd3bd8656e
6 changed files with 368 additions and 235 deletions

4
.gitignore vendored
View file

@ -161,6 +161,4 @@ cython_debug/
.pdm-python
/test_get_txt.py
/test_tmp.py
/深空彼岸/
/深空彼岸.epub
/斗破苍穹.epub
test_search.py

View file

@ -1,14 +1,14 @@
import io
import json
import os
import random
import re
import shutil
import threading
import time
import requests
from bs4 import BeautifulSoup
import re
import requests
from ebooklib import epub
@ -37,268 +37,375 @@ def get_user_agent():
return {'User-Agent': user_agent}
# 定义请求间隔时间(秒)
interval = 2
class Download_Novel:
# 设置请求头,模拟浏览器访问
def search_novel(self):
hm_url = f'https://user.bqgso.cc/hm.html?&q={self.name}'
result = requests.get(hm_url, headers=get_user_agent()).text
# print(result)
hm = result[2:-2]
# print(hm)
# 发起请求并获取响应
url = f'https://user.bqgso.cc/search.html?&q={self.name}&hm={hm}'
# 要爬取的小说主页链接
url = 'https://www.bqg221.com/xs/17931/'
response = json.loads(requests.get(url, headers=get_user_agent()).text[1:-1])
# print(type(response))
for i, book in enumerate(response):
# i['url_list'][:9] = 'https://www'
trans_url = book['url_list'].replace('https://m', 'https://www')
response[i]['url_list'] = trans_url
# 发起请求并获取响应
response = requests.get(url, headers=get_user_agent())
# 返回一个json对象
return response
# 将响应转换为BeautifulSoup对象
soup = BeautifulSoup(response.text, 'html.parser')
def get_novel_info(self, response):
# 获取小说名字
title = soup.select_one('.book h1').get_text(strip=True)
print(title)
# 定义请求间隔时间(秒)
interval = 2
# 获取小说简介
# print(soup.select('.small')[0])
div_tag = soup.find('div', {'class': 'small'})
# print(div_tag)
all_span_tags = div_tag.find_all('span')
# print(all_span_tags)
author = all_span_tags[0].text.strip()[3:]
status = all_span_tags[1].text.strip()
update_time = all_span_tags[2].text.strip()
latest_update = all_span_tags[3].text.strip()
# for i in all_span_tags:
# print(i.text.strip())
intro = soup.select_one('.intro').get_text(strip=True)[:-6]
print(intro)
# 设置请求头,模拟浏览器访问
cover = soup.select_one('.cover img')['src']
# print(cover)
# 获取小说所有章节链接
chapter_urls = [url + i.get('href').split('/')[-1] for i in soup.select('.listmain a') if
i.get('href').split('/')[-1] != 'javascript:dd_show()']
# print(chapter_urls)
# 要爬取的小说主页链接
url = response['url_list']
print('开始下载。。。')
# 停顿两秒
time.sleep(interval)
# 发起请求并获取响应
url_response = requests.get(url, headers=get_user_agent())
# 将响应转换为BeautifulSoup对象
soup = BeautifulSoup(url_response.text, 'html.parser')
# 多线程下载txt
def download_url(chapter_url, file_name):
# 限制下载线程数
with semaphore:
file_path = './' + title
file_name = file_path + '/' + file_name
# 获取小说名字
# title = soup.select_one('.book h1').get_text(strip=True)
self.title = response['articlename']
print(self.title)
if not os.path.exists(file_path):
os.makedirs(file_path)
print('文件夹不存在,创建文件夹')
# 获取小说简介
# print(soup.select('.small')[0])
div_tag = soup.find('div', {'class': 'small'})
# print(div_tag)
all_span_tags = div_tag.find_all('span')
# print(all_span_tags)
# author = all_span_tags[0].text.strip()[3:]
self.author = response['author']
self.status = all_span_tags[1].text.strip()
self.update_time = all_span_tags[2].text.strip()
self.latest_update = all_span_tags[3].text.strip()
# for i in all_span_tags:
# print(i.text.strip())
self.intro = soup.select_one('.intro').get_text(strip=True)[:-6]
print(self.intro)
# cover = soup.select_one('.cover img')['src']
self.cover = response['url_img']
# print(cover)
# 获取小说所有章节链接
self.chapter_urls = [url + i.get('href').split('/')[-1] for i in soup.select('.listmain a') if
i.get('href').split('/')[-1] != 'javascript:dd_show()']
# print(chapter_urls)
print('开始下载。。。')
# 获取当前文件所在目录路径
dir_path = os.path.dirname(os.path.abspath(__file__))
self.download_path = dir_path + '/downloads/'
self.file_path = self.download_path + self.title + '/'
if not os.path.exists(self.file_path):
os.makedirs(self.file_path)
# 停顿两秒
time.sleep(self.interval)
def get_multi_txt_file_status(self, file_name):
file_name = self.file_path + file_name
if os.path.exists(file_name) and os.path.getsize(file_name) > 0:
print(file_name + ' 已存在,跳过...\n')
# success_account =+ 1
return file_name, True
else:
print('开始下载:' + file_name)
with open(file_name, 'w', encoding='utf-8') as f:
retry = 8
while retry > 0:
try:
response = requests.get(chapter_url, headers=get_user_agent(), timeout=5)
soup = BeautifulSoup(response.text, 'html.parser')
return file_name, False
chapter_title = soup.select_one('.content h1').get_text()
print(chapter_title)
chapter_content = soup.select_one('div#chaptercontent').get_text().strip()
# print('before: '+chapter_content)
# # 将所有的<br>标签替换成换行符\n
chapter_content = chapter_content.replace('  ', '\n ')
# chapter_content = chapter_content.replace('<br>', '\n')
content = re.sub(r'(第\d+章|请收藏本站|『点此报错).*$', '', chapter_content, flags=re.MULTILINE)
# print(content)
# 将处理后的结果写入到test.txt文件中
f.write(chapter_title + '\n' + content + '\n\n')
# success_account = success_account + 1
break
# return True
except Exception as e:
print(e, '\n retry...')
time.sleep(interval)
retry -= 1
# return False
def download_url(self, chapter_url, file_name):
# 限制下载线程数
with self.semaphore:
# 获取当前文件所在目录路径
# dir_path = os.path.dirname(os.path.abspath(__file__))
#
# file_path = dir_path + '/downloads/' + self.title
# file_name = file_path + '/' + file_name
#
# if not os.path.exists(file_path):
# os.makedirs(file_path)
# # print('文件夹不存在,创建文件夹')
file_name, status = self.get_multi_txt_file_status(file_name=file_name)
if status:
print(file_name + ' 已存在,跳过...\n')
# success_account =+ 1
else:
print('开始下载:' + file_name)
with open(file_name, 'w', encoding='utf-8') as f:
retry = 8
while retry > 0:
try:
response = requests.get(chapter_url, headers=get_user_agent(), timeout=5)
soup = BeautifulSoup(response.text, 'html.parser')
chapter_title = soup.select_one('.content h1').get_text()
print(chapter_title)
chapter_content = soup.select_one('div#chaptercontent').get_text().strip()
# print('before: '+chapter_content)
# # 将所有的<br>标签替换成换行符\n
chapter_content = chapter_content.replace('  ', '\n ')
# chapter_content = chapter_content.replace('<br>', '\n')
content = re.sub(r'(第\d+章|请收藏本站|『点此报错).*$', '', chapter_content,
flags=re.MULTILINE)
# print(content)
# 将处理后的结果写入到test.txt文件中
f.write(chapter_title + '\n' + content + '\n\n')
# success_account = success_account + 1
break
# return True
except Exception as e:
print(e, '\n retry...')
time.sleep(self.interval)
retry -= 1
# return False
def multi_thread_download(self):
self.threads = []
for file_name, chapter_url in enumerate(self.chapter_urls):
args = (chapter_url, str(file_name) + '.txt')
thread = threading.Thread(target=self.download_url, args=args)
self.threads.append(thread)
thread.start()
for thread in self.threads:
thread.join()
def download_process(self):
# 限制同时4线程建议使用4线程过多线程会导致错误增多
max_concurrent_threads = 4
# 创建Semaphore对象并将其初始值设置为max_concurrent_threads
self.semaphore = threading.Semaphore(max_concurrent_threads)
self.multi_thread_download()
time.sleep(self.interval)
file = 0
# 判断是否全部下载成功
for i in range(0, len(self.chapter_urls)):
status = self.get_multi_txt_file_status(str(i) + '.txt')[1]
if not status:
file += 1
break
if not file:
convert_type = int(input('下载成功!\n请输入要合并的格式:\n0 TxT文件\n1 Epub文件\n'))
convert_status = True
if convert_type == 0:
print(self.file_path, self.download_path + self.title + '.txt')
convert_status = self.merge_txt_file(self.download_path + self.title + '.txt')
elif convert_type == 1:
txt_files = []
for n in range(0, len(self.chapter_urls)):
txt_files.append(self.file_path + str(n) + '.txt')
# print('txt_files:',txt_files)
convert_status = self.merge_txt_to_epub(txt_files, self.download_path + self.title + '.epub')
if convert_status:
print('合并成功!')
else:
print('合并失败请删除downloads下面目录后重新运行程序')
exit(1)
else:
print('部分文件下载失败,限制线程数可以提高下载成功率,是否重新下载个别文件?')
download = input('0 退出\n1 重试\n')
if download == 0:
exit(0)
else:
self.download_process()
# 合并为txt文件
def merge_txt_file(self, merged_file_name=''):
"""
:param merged_file_name: 合并后文件保存位置
:returns bool: 返回合并成功或者失败状态
"""
# os.chdir(file_path)
if os.path.exists(merged_file_name):
os.remove(merged_file_name)
print('merge file : ', sorted(os.listdir(self.file_path), key=lambda x: int(x.split('.')[0])))
time.sleep(self.interval)
with open(merged_file_name, 'wb') as outfile:
try:
for filename in sorted(os.listdir(self.file_path), key=lambda x: int(x.split('.')[0])):
print(filename)
if filename.endswith('.txt'):
# 判断文件是否为空
if os.path.exists(self.file_path + '/' + filename) and os.path.getsize(
self.file_path + '/' + filename) > 0:
# print(filename + ' 已存在,跳过...\n')
with open(self.file_path + '/' + filename, 'rb') as infile:
shutil.copyfileobj(infile, outfile)
else:
return False
except Exception as e:
os.remove(merged_file_name)
print(e)
return False
return True
# txt转换为epub
def merge_txt_to_epub(self, txt_files, epub_file):
"""
将txt转换为epub
txt_files (list) : 是一个列表
epub_file (str) 实际为转换成功的epub文件路径及名称
# txt转换为epub
def merge_txt_to_epub(txt_files=[], epub_file='', author='', cover='', direction=''):
"""
将txt转换为epub
"""
# 创建EPUB书籍对象
book = epub.EpubBook()
txt_files (list) : 是一个列表
if os.path.exists(epub_file):
os.remove(epub_file)
epub_file (str) 实际为转换成功的epub文件路径及名称
# 设置元数据(可根据需要进行调整)
book.set_title(self.title)
book.set_language('zh')
book.add_author(self.author)
book.set_direction(self.intro)
# 添加封面
# 获取图片并将其转换为字节流
response = requests.get(self.cover)
stream = io.BytesIO(response.content)
author (str) 作者
book.set_cover('cover.jpg', stream.getvalue(), 'image/jpeg')
cover (str) 封面图片链接
print('合并中。。。。。。')
# print(txt_files)
direction (str) 书籍简介
# 书籍目录
book_spine = []
# 遍历所有txt文件
# os.chdir(title)
for i, txt_file in enumerate(txt_files):
# 读取txt文件内容
with open(txt_file, 'r', encoding='utf-8') as file:
content = file.readlines()
try:
# 将所有换行符替换为<br>
content = [s.replace('\n', '') for s in content if len(s.strip()) > 0]
"""
# 获取章节标题
chapter_title = content[0]
# print(chapter_title)
# 创建EPUB书籍对象
book = epub.EpubBook()
# content = ['&nbsp;&nbsp;' + line + '<br>' for line in content]
# 处理html文档
content[0] = f""" <div class="calibre2" id="calibre_pb_0"></div><h1 class="kindle-cn-heading" id="calibre_pb_1">
{content[0]} </h1> """
for j, line in enumerate(content[1:]):
content[j + 1] = '<p class="calibre3">' + line + '</p>\n'
# content.append('</body></html>')
except IndexError as e:
print(e)
return False
# 创建一个章节对象
if os.path.exists(epub_file):
os.remove(epub_file)
chapter = epub.EpubHtml(title=chapter_title, file_name='text/' + str(i) + '.xhtml')
chapter.content = ''.join(content) # 将整个文件内容作为章节内容
# 下面的是将css文件引用到单个章节里面
page_style = open('./css/page_styles.css', 'r', encoding='utf-8').read()
page_style1 = open('./css/page_styles1.css', 'r', encoding='utf-8').read()
style = open('./css/stylesheet.css', 'r', encoding='utf-8').read()
chapter.add_item(
epub.EpubItem(uid="page_style", file_name="../style/page_styles.css", media_type="text/css",
content=page_style))
chapter.add_item(
epub.EpubItem(uid="page_style1", file_name="../style/page_styles1.css", media_type="text/css",
content=page_style1))
chapter.add_item(
epub.EpubItem(uid="style_default", file_name="../style/stylesheet.css", media_type="text/css",
content=style))
# 设置元数据(可根据需要进行调整)
book.set_title(title)
book.set_language('zh')
book.add_author(author)
book.set_direction(direction)
# 添加封面
# 获取图片并将其转换为字节流
response = requests.get(cover)
stream = io.BytesIO(response.content)
# 将章节添加到书籍中
book.add_item(chapter)
book.set_cover('cover.jpg', stream.getvalue(), 'image/jpeg')
book_spine.append(chapter)
print('合并中。。。。。。')
# 将目录添加到书籍中
book.add_item(epub.EpubNcx())
book.add_item(epub.EpubNav())
book.spine = book_spine
book.toc = book_spine
# 书籍目录
book_spine = []
# 遍历所有txt文件
os.chdir(title)
for i, txt_file in enumerate(txt_files):
# 读取txt文件内容
with open(txt_file, 'r', encoding='utf-8') as file:
content = file.readlines()
try:
# 将所有换行符替换为<br>
content = [s.replace('\n', '') for s in content if len(s.strip()) > 0]
# 设置书籍的样式文件
page_style = open('./css/page_styles.css', 'r', encoding='utf-8').read()
page_style1 = open('./css/page_styles1.css', 'r', encoding='utf-8').read()
# 获取章节标题
chapter_title = content[0]
# print(chapter_title)
# content = ['&nbsp;&nbsp;' + line + '<br>' for line in content]
# 处理html文档
content[0] = f""" <div class="calibre2" id="calibre_pb_0"></div><h1 class="kindle-cn-heading" id="calibre_pb_1">
{content[0]} </h1> """
for j, line in enumerate(content[1:]):
content[j + 1] = '<p class="calibre3">' + line + '</p>'
# content.append('</body></html>')
except IndexError as e:
print(e)
return False
# 创建一个章节对象
chapter = epub.EpubHtml(title=chapter_title, file_name='text/' + str(i) + '.xhtml')
chapter.content = ''.join(content) # 将整个文件内容作为章节内容
# 下面的是将css文件引用到单个章节里面
page_style = open('../css/page_styles.css', 'r', encoding='utf-8').read()
page_style1 = open('../css/page_styles1.css', 'r', encoding='utf-8').read()
style = open('../css/stylesheet.css', 'r', encoding='utf-8').read()
chapter.add_item(
epub.EpubItem(uid="page_style", file_name="../style/page_styles.css", media_type="text/css",
style = open('./css/stylesheet.css', 'r', encoding='utf-8').read()
book.add_item(
epub.EpubItem(uid="page_style", file_name="style/page_styles.css", media_type="text/css",
content=page_style))
chapter.add_item(
epub.EpubItem(uid="page_style1", file_name="../style/page_styles1.css", media_type="text/css",
book.add_item(
epub.EpubItem(uid="page_style1", file_name="style/page_styles1.css", media_type="text/css",
content=page_style1))
chapter.add_item(
epub.EpubItem(uid="style_default", file_name="../style/stylesheet.css", media_type="text/css",
content=style))
book.add_item(
epub.EpubItem(uid="style_default", file_name="style/stylesheet.css", media_type="text/css", content=style))
# 将章节添加到书籍中
book.add_item(chapter)
# 打包EPUB文件
epub.write_epub(epub_file, book, {})
return True
book_spine.append(chapter)
def __init__(self, name):
self.file_path = None
self.chapter_urls = None
self.cover = None
self.intro = None
self.status = None
self.author = None
self.title = None
self.name = name
# 将目录添加到书籍中
book.add_item(epub.EpubNcx())
book.add_item(epub.EpubNav())
book.spine = book_spine
book.toc = book_spine
# 定义请求间隔时间(秒)
self.interval = 2
# 设置书籍的样式文件
os.chdir('../')
page_style = open('./css/page_styles.css', 'r', encoding='utf-8').read()
page_style1 = open('./css/page_styles1.css', 'r', encoding='utf-8').read()
style = open('./css/stylesheet.css', 'r', encoding='utf-8').read()
book.add_item(
epub.EpubItem(uid="page_style", file_name="style/page_styles.css", media_type="text/css", content=page_style))
book.add_item(
epub.EpubItem(uid="page_style1", file_name="style/page_styles1.css", media_type="text/css",
content=page_style1))
book.add_item(
epub.EpubItem(uid="style_default", file_name="style/stylesheet.css", media_type="text/css", content=style))
# 打包EPUB文件
epub.write_epub('./' + epub_file, book, {})
return True
# 要爬取的小说主页链接
# self.novel_url = 'https://www.bqg221.com/xs/'
# 合并为txt文件
def merge_txt_file(file_path='', merged_file_name=''):
"""
:param file_path: txt文件的保存位置
:param merged_file_name: 合并后文件保存位置
:returns bool: 返回合并成功或者失败状态
"""
os.chdir(file_path)
if os.path.exists(merged_file_name):
os.rmdir(merged_file_name)
print('merge file : ', sorted(os.listdir('.'), key=lambda x: int(x.split('.')[0])))
with open(merged_file_name, 'wb') as outfile:
for filename in sorted(os.listdir('.'), key=lambda x: int(x.split('.')[0])):
print(filename)
if filename.endswith('.txt'):
# 判断文件是否为空
if os.path.exists(filename) and os.path.getsize(filename) > 0:
# print(filename + ' 已存在,跳过...\n')
with open(filename, 'rb') as infile:
shutil.copyfileobj(infile, outfile)
else:
return False
return True
def multi_thread_download():
threads = []
for file_name, chapter_url in enumerate(chapter_urls):
args = (chapter_url, str(file_name) + '.txt')
thread = threading.Thread(target=download_url, args=args)
threads.append(thread)
thread.start()
for thread in threads:
thread.join()
# 限制同时4线程建议使用4线程过多线程会导致错误增多
max_concurrent_threads = 4
# 创建Semaphore对象并将其初始值设置为max_concurrent_threads
semaphore = threading.Semaphore(max_concurrent_threads)
multi_thread_download()
time.sleep(interval)
while True:
# merge_txt_file('./' + title, '../' + title + '.txt')
# 调用函数进行合并
txt_files = sorted(os.listdir(title), key=lambda x: int(x.split('.')[0]))
epub_file_path = title + '.epub'
result = merge_txt_to_epub(txt_files, epub_file_path, author, cover, intro)
if not result:
print('下载失败:', result, '\t是否重试?')
num = int(input('0 重试\n1 退出\n'))
if num == 0:
multi_thread_download()
merge_txt_to_epub(txt_files, epub_file_path, author, cover, intro)
if __name__ == '__main__':
search_name = input('请输入要搜索的书籍名称: ')
if search_name:
download_novel = Download_Novel(search_name)
response = download_novel.search_novel()
print(response)
print('搜索到 ' + str(len(response)) + ' 个结果\n')
print('---------------------------------------\n')
for i, book in enumerate(response):
print(str(i) + ' 书籍名称:' + book['articlename'] + '\n作者:' + book['author'] + '\n简介:' + book[
'intro'] + '...\n')
print('---------------------------------------')
print('---------------------------------------\n')
select_book = int(input(f'选择要下载的书籍序号(从0-{str(len(response) - 1)}中选择)'))
# 判断输入合法
if isinstance(select_book, int) and 0 <= select_book <= len(response):
download_novel.get_novel_info(response[select_book])
download_novel.download_process()
else:
break
print('输入内容不合法!')
else:
print('合并成功!')
break
exit(0)

9
README.md Normal file
View file

@ -0,0 +1,9 @@
## Novel_Download
`https://www.bqg221.com` 获取小说内容将爬取的内容合并为txt或者epub格式。
- 现已实现的功能
- [x] 实现下载txt文档
- [x] 实现合并txt
- [x] 实现合并为epub
- [x] 实现搜索功能
- [ ] 实现多个书源替换

View file

@ -2,7 +2,15 @@
margin-bottom: 5pt;
margin-top: 5pt
}
@font-face {
font-family: yinbiao;
src: url(styles/XXXXXXXXXXXXXXXX)
}
html {
overflow: hidden;
}
body {
height: 100%;
overflow: auto;
-webkit-column-width: 100%;
-moz-column-width: 100%;
column-width: 100%;
page-break-inside: avoid;
}

View file

@ -46,6 +46,12 @@ dependencies = [
"urllib3<3,>=1.21.1",
]
[[package]]
name = "setuptools"
version = "68.0.0"
requires_python = ">=3.7"
summary = "Easily download, build, install, upgrade, and uninstall Python packages"
[[package]]
name = "six"
version = "1.16.0"
@ -62,7 +68,7 @@ summary = "HTTP library with thread-safe connection pooling, file post, and more
lock_version = "4.2"
cross_platform = true
groups = ["default"]
content_hash = "sha256:2fff54024aa639561573351b1841dd1f0084ca345b52d35859bfae33744350e8"
content_hash = "sha256:095da8eef1987e0630ebddf4a4513ad826ad8630af33554248065ff297544cb6"
[metadata.files]
"certifi 2023.5.7" = [
@ -236,6 +242,10 @@ content_hash = "sha256:2fff54024aa639561573351b1841dd1f0084ca345b52d35859bfae337
{url = "https://files.pythonhosted.org/packages/70/8e/0e2d847013cb52cd35b38c009bb167a1a26b2ce6cd6965bf26b47bc0bf44/requests-2.31.0-py3-none-any.whl", hash = "sha256:58cd2187c01e70e6e26505bca751777aa9f2ee0b7f4300988b709f44e013003f"},
{url = "https://files.pythonhosted.org/packages/9d/be/10918a2eac4ae9f02f6cfe6414b7a155ccd8f7f9d4380d62fd5b955065c3/requests-2.31.0.tar.gz", hash = "sha256:942c5a758f98d790eaed1a29cb6eefc7ffb0d1cf7af05c3d2791656dbd6ad1e1"},
]
"setuptools 68.0.0" = [
{url = "https://files.pythonhosted.org/packages/c7/42/be1c7bbdd83e1bfb160c94b9cafd8e25efc7400346cf7ccdbdb452c467fa/setuptools-68.0.0-py3-none-any.whl", hash = "sha256:11e52c67415a381d10d6b462ced9cfb97066179f0e871399e006c4ab101fc85f"},
{url = "https://files.pythonhosted.org/packages/dc/98/5f896af066c128669229ff1aa81553ac14cfb3e5e74b6b44594132b8540e/setuptools-68.0.0.tar.gz", hash = "sha256:baf1fdb41c6da4cd2eae722e135500da913332ab3f2f5c7d33af9b492acb5235"},
]
"six 1.16.0" = [
{url = "https://files.pythonhosted.org/packages/71/39/171f1c67cd00715f190ba0b100d606d440a28c93c7714febeca8b79af85e/six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
{url = "https://files.pythonhosted.org/packages/d9/5a/e7c31adbe875f2abbb91bd84cf2dc52d792b5a01506781dbcf25c91daf11/six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254"},

View file

@ -9,6 +9,7 @@ authors = [
dependencies = [
"requests>=2.31.0",
"ebooklib>=0.18",
"setuptools>=68.0.0",
]
requires-python = ">=3.11"
license = {text = "MIT"}