python爬取猫猫图

1
猫猫图http://p.ik123.com/zt/maomi/68_1.html

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
import requests
import re
from bs4 import BeautifulSoup

HEADERS = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
                         "Chrome/99.0.4844.51 Safari/537.36 Edg/99.0.1150.30"}


# 获取末页的页码
def get_pagesize(html):
    print("正在获取页码")
    findend_page = re.findall(r"<a href='68_(d+).html'>末页</a>", html)
    if findend_page is not None:
        return findend_page[0]
    else:
        print("获取页码异常")


# 获取网页代码

def analyzedata(url, key):
    if key is None:
        print("正在分析网页")
        res = requests.get(url=url, headers=HEADERS, timeout=2)
        res.encoding = "gb2312"
        html = res.text
        return html
    elif key == "img":
        res = requests.get(url=url, headers=HEADERS)
        res.encoding = "gb2312"
        content = res.content
        return content


# 获取待爬网页分页链接

def get_href(baseurl):
    url_list = []
    print("正在获取分页链接")
    html = analyzedata(baseurl, key=None)
    # print(html)
    pagesize = int(get_pagesize(html))
    # print(pagesize)
    for i in range(1, pagesize + 1):
        if pagesize > 0:
            url_list.append(f"http://p.ik123.com/zt/maomi/68_{i}.html")
        else:
            print("页码异常")
    return url_list


# 获取详情页链接

def get_content_url(url_list):
    hrefs = []
    print("正在获取详情页数据")
    for href in url_list:
        html = analyzedata(href, key=None)
        soup = BeautifulSoup(html, "html.parser")
        for img in soup.find_all("li", class_="img"):
            href = re.findall(r'class="preview" href="(.*?)"', str(img))
            hrefs.append(href)
    return hrefs


# 获取图片
def getimg(hrefs):
    print("正在获取图片")
    num = 0
    s = 0
    for href in hrefs:
        num += 1
        html = analyzedata(href[0], key=None)
        soup = BeautifulSoup(html, "html.parser")
        for img in soup.find_all("img"):
            s += 1
            src = re.findall(r'img alt=".*" src="(.*?)"', str(img))[0]
            title = re.findall(r'img alt="(.*?)" src=".*"', str(img))[0]
            save_img(src, title, num, s)
            # print(src)


# 保存图片
def save_img(src, title, num, s):
    # content = analyzedata(src, text="img")

    content = analyzedata(src, "img")
    with open(fr".img{title}{s}.jpg", "wb") as f:
        f.write(content)
        print(f"正在保存第{num}页的照片")
        print(f"已保存{s}张照片")


def main():
    getimg(get_content_url(get_href("http://p.ik123.com/zt/maomi/68_1.html")))


if __name__ == '__main__':
    main()
# getimg('http://www.ik123.com/q/tuku/keai/62324.html')