有序队列：queue

有序队列：queue

在大佬博客发现的这个有序队列，挺有意思的

Python queue模块的FIFO队列先进先出。 queue.Queue(maxsize)

LIFO类似于堆，即先进后出。 queue.LifoQueue(maxsize)

还有一种是优先级队列级别越低越先出来。 queue.PriorityQueue(maxsize)

queue.PriorityQueue(maxsize)

1
2
3
4
5
6
7
8
9
10
11
12
13
import queue

q = queue.PriorityQueue(5)
q.put((5, 5454))
q.put((2, 532566))
q.put((3, 555))
q.put((7, 344))
print(q.get())
print(q.get())

-----------
(2, 532566)
(3, 555)

我的py

按小说章节ID排序（1, ‘…’）

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
import time
import requests
from lxml import etree
from multiprocessing.dummy import Pool as ThreadPool
from urllib.parse import urljoin
from queue import PriorityQueue

# 有序队列，可以全局使用, 用来储存章节内容
queue = PriorityQueue()
# 目录页url
start_url = 'http://www.ybiquge.com/95_95524/'
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=0.9',
    'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
    'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36'
}


# getURL
def get_url(url):
    print("访问url：{}".format(url))
    try:
        res = requests.get(url, headers)
        # tree = etree.HTML(res)
        return res.text
    except:
        return False


# 获取小说章节链接
def get_page():
    # get
    page_html = get_url(start_url)
    if page_html:
        # lxml解析
        page_tree = etree.HTML(page_html)
        # 书名
        book_name = page_tree.xpath('//div[@id="info"]/h1/text()')[0]
        print(book_name)
        # 章节链接
        page_url_lists = page_tree.xpath('//div[@id="list"]/dl/dd/a/@href')
        return book_name, page_url_lists
    else:
        return False


# 获取小说内容
def get_text(url):
    # 先拼接URL
    url = urljoin(start_url, url)
    # get
    zj_html = get_url(url)
    if zj_html:
        # lxml解析
        page_tree = etree.HTML(zj_html)
        # 章节名
        zj_name = page_tree.xpath('//div[@class="bookname"]/h1/text()')[0]
        print(zj_name)
        # 内容
        zj_text_list = page_tree.xpath('//div[@id="content"]/text()')
        # 遍历合并内容
        zj_text = ''
        for text in zj_text_list:
            zj_text = zj_text + text + '\n'
        print('内容:', zj_text[0:15], '...')
        # 有序列队提交
        # 匹配章节id
        zj_id = url.split('/')[-1].replace('.html', '')
        # 开始提交, 序号+内容
        queue.put((int(zj_id), zj_name+'\n'+zj_text+'\n'))
        # 设置延迟（理性一点）
        time.sleep(1)


# 下载
def down_text(name, texts):
    path = name + '.txt'
    with open(path, 'a', encoding='utf-8') as a:
        a.writelines(texts)


if __name__ == '__main__':
    start_time = time.time()
    # 获取小说名字，章节链接list
    xs_book_name, zj_lists = get_page()
    # 实例化 Pool 对象,设置线程4
    pool = ThreadPool(4)
    # 设置任务
    pool.map(get_text, zj_lists)
    # 关闭线程
    pool.close()
    pool.join()
    # 有序获取章节内容
    print("正在保存小说，请稍后...")
    content = ""
    # queue.empty() 如果队列为空，返回True
    while not queue.empty():
        # get有序获取
        next_obj = queue.get()
        # print(next_obj[0])
        content += next_obj[1]
    # 保存
    down_text(xs_book_name, content)
    print(xs_book_name, "下载完成！")
    print("共用时：", time.time()-start_time)

写在后面

不知不觉写了好多下载小说的py了

爱好看小说，没别的意思！

python3 queue

本博客所有文章除特别声明外，均采用 CC BY-SA 4.0 协议 ，转载请注明出处！