三大妈网图

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
from bs4 import BeautifulSoup
import requests
'''
网址：
https://www.3dmgame.com/bagua/2192.html
https://www.3dmgame.com/bagua/2216.html

如果图片过期，更改以下列表便可以更替
'''
list_head_url = ['https://www.3dmgame.com/bagua/2216','https://www.3dmgame.com/bagua/2192']

for i in list_head_url:
        # head_url = 'https://www.3dmgame.com/bagua/1570'
        head_url = str(i)
        tail_url = '.html'

        for i in range(1,5):
                if i == 1:
                        url = head_url + tail_url
                else:
                        url = head_url + '_' + str(i) + tail_url

                head = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; W…) Gecko/20100101 Firefox/68.0'}

                re_url = requests.get(url)
                bs_url = BeautifulSoup(re_url.text, 'html.parser')
                items = bs_url.find_all('p', align='center')

                for i in items:
                        p = i.find('img')['src']
                        # print(p)
                        res = requests.get(str(p)).content
                        photo = open(str(p[-10:-4])+'.jpg', 'wb')
                        photo.write(res)
                        photo.close()



input('爬取完成，任意键退出')

彼岸图

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
from bs4 import BeautifulSoup
import requests
"""
爬取网址：http://pic.netbian.com/4kfengjing/

第9行改地址
第23行改页数
"""
list_head_url = ['http://pic.netbian.com/4kyingshi/'] 

first_head_url = 'http://pic.netbian.com' # 第二层需要用到的头部

# headers = {'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3', 'Accept-Encoding': 'gzip, deflate', 'Accept-Language': 'zh-CN,zh;q=0.9', 'Cache-Control': 'max-age=0', 'Connection': 'keep-alive', 'Host': 'pic.netbian.com', 'Referer': 'http://pic.netbian.com/4kmeinv/', 'Upgrade-Insecure-Requests': '1', 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36'}

# proxies = {
# 	"http" : "183.3.218.34" # 代理ip
# }

for i in list_head_url:
    head_url = str(i)
    tail_url = ".html"

    for i in range(1,20):
        if i == 1:
            url = head_url
        else:
            url = head_url + 'index_' + str(i) + tail_url

        print(url)
        re_url = requests.get(url)
        # re_url = requests.get(url, headers=headers, proxies = proxies)
        print(re_url.status_code)
        bs_url = BeautifulSoup( re_url.text, 'html.parser')

        items = bs_url.find_all('ul', class_='clearfix')

        '''
        提取第一个链接，然后拼接
        '''
        for i in items:
            list_a = i.find_all('a')
            for first_tail_urls in list_a:
                # print(first_tail_url['href'])

                first_tail_url = first_tail_urls['href']
                first_url = first_head_url + first_tail_url


                #    first_url
                #第一条连接提取
                re_second_url = requests.get(first_url)
                # re_second_url = requests.get(first_url, headers=headers, proxies = proxies)
                bs_second_url = BeautifulSoup(re_second_url.text, 'html.parser')
                second_items = bs_second_url.find_all('div', class_ = 'photo-pic')
                # print(second_items)

                for i in second_items:
                    second_tail_url = i.find('img')['src']
                    # 提取第二层连接
                    second_url = first_head_url + second_tail_url
                    res = requests.get(str(second_url)).content
                    # res = requests.get(str(second_url), headers=headers, proxies = proxies).content
                    photo = open(str(second_url[-10:-4] + '.jpg'), 'wb')
                    photo.write(res)
                    photo.close()
                    print('下载了一张')


print('全部下载完成')

摄影作品

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
import requests
from bs4 import BeautifulSoup
from requests.packages.urllib3.exceptions import InsecureRequestWarning
import os

class chiphell:
    def __init__(self,page):
        self.page = page

    def get_forumaddr(self):
        requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
        self.forumaddr = []
        self.cookiesdict = []
        self.proxies = {'http': '127.0.0.1:8888', 'https': '127.0.0.1:8888'}
        self.headers = \
            {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36",
             "referer":"https://www.chiphell.com/forum-62-1.html"}
        self.address = "https://www.chiphell.com/forum.php"
        self.params = {"mod":"forumdisplay",
                       "fid":"62",
                       "filter":"typeid",
                       "orderby":"lastpost",
                       "typeid":"277",
                       "page":"1"}
        for i in range(1,self.page+1):
            self.params['page'] = i
            resdata = requests.get(self.address, headers=self.headers, params=self.params,cookies = self.cookiesdict)
            self.cookiesdict = dict(self.cookiesdict, **requests.utils.dict_from_cookiejar(resdata.cookies))
            data = BeautifulSoup(resdata.text, 'html.parser').find('ul', class_='ml').find_all('li')
            for ii in data:
                self.forumaddr.append('https://www.chiphell.com/' + ii.find('h3', class_='xw0').find('a')['href'])

    def get_forum_picture(self,address):
        print(address)
        dic=address[address.find('viewthread&tid=')+15:address.find('&extra=page')]
        if os.path.exists('output') == True:
            pass
        else:
            os.makedirs('output')
        if os.path.exists('.\output\\'+dic)== True:
            pass
        else:
            os.makedirs('.\output\\'+dic)
        self.get_picture_headers = \
            {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36",
             "referer":"https://www.chiphell.com/forum.php?mod=forumdisplay&fid=62&filter=typeid&typeid=277"}
        self.get_picture_address = address
        resdata = requests.get(self.get_picture_address, headers=self.get_picture_headers, cookies=self.cookiesdict)
        data = BeautifulSoup(resdata.text, 'html.parser').find('div', class_='t_fsz').find_all('img',class_='zoom')
        for i in data:
            try:
                if i['zoomfile'] == None:
                    pass
                else:
                    print(i['zoomfile'])
                    filename = i['zoomfile'][i['zoomfile'].rfind('/') + 1:]
                    print(filename)
                    pic = requests.get(i['zoomfile'], headers=self.get_picture_headers, cookies=self.cookiesdict)
                    with open('.\output\\' + '.\\' + dic + '\\' + filename, 'wb') as file:
                        file.write(pic.content)
            except:
                pass

    def Start(self):
        self.get_forumaddr()
        for i in self.forumaddr:
            self.get_forum_picture(i)


a = chiphell(10)
a.Start()