Python 爬虫 七夕福利

Posted 2020-12-30 暗香丶

祝大家七夕愉快

妹子图

 1 import requests
 2 from lxml import etree
 3 import os
 4 def headers(referer):#图片的下载可能和头部的referer有关,所以将referer设为变换值,以躲避反扒
 5     headers = {
 6         ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36‘,
 7         ‘Referer‘: ‘{}‘.format(referer)}
 8     return headers
 9 def Tuji(pag):#找图集
10     fullurl = ‘http://www.mzitu.com/page/{}/‘.format(pag)
11     shouye_html = requests.get(fullurl)
12     shouye_html_text = shouye_html.text
13     shouye_ele = etree.HTML(shouye_html_text)
14     tj_list = shouye_ele.xpath(‘//*[@id="pins"]/li/a/@href‘)#找每页的图集url
15     Tuji_url_list = []
16     for tj_url in tj_list:
17         Tuji_url_list.append(tj_url)
18     return Tuji_url_list
19 def gettuji_info(tj_url_list):#图集的url列表 收集图集的相关信息
20     for tj_url_1 in tj_url_list: #tj_url_1 --- > http://www.mzitu.com/146823
21         tj_html = requests.get(tj_url_1, headers=headers(tj_url_1))
22         tj_html_text = tj_html.text
23         tj_ele = etree.HTML(tj_html_text)
24         img_title = tj_ele.xpath(‘//h2[@class="main-title"]/text()‘)[0]  # 图集名称
25         max_pag_list = int(tj_ele.xpath(‘/html/body/div[2]/div[1]/div[4]/a[5]/span/text()‘)[0])  # 找最大页数
26         if os.path.exists(img_title) == True:
27             print(‘!‘)
28         else:
29             os.mkdir(img_title)
30             for i in range(1, int(max_pag_list + 1)):
31                 tj_url_2 = tj_url_1 + ‘/‘+str(i)  #tj_url_2 ---> http://www.mzitu.com/146823 + pag
32                 tj_html = requests.get(tj_url_2, headers=headers(tj_url_1))
33                 tj_html_text = tj_html.text
34                 tj_ele = etree.HTML(tj_html_text)
35                 img_url = tj_ele.xpath(‘//div[@class="main-image"]/p/a/img/@src‘)[0] # 从不同的tj_url_2中找图片的url
36                 print(‘正在下载‘+img_title+‘第‘+str(i)+‘张‘)
37                 with open(img_title+‘/‘+str(i)+‘.jpg‘, "wb+") as jpg:
38                     jpg.write(requests.get(img_url, headers=headers(tj_url_2)).content)
39 
40 if __name__ == ‘__main__‘:
41     pags = int(input(‘你想搞几页的嘿嘿?‘))
42     for pag in range(1,pags+1):
43         gettuji_info(Tuji(pag))