爬取mzitu.com/zipai的妹子图
本帖最后由 沉好人 于 2020-2-12 14:35 编辑爬取妹子图，
根据小甲鱼OOXX改
**** Hidden Message ***** 最近试了一下，原来的版本里正则式匹配不了图片链接了，重新改了一下
import requests
import re
import os
import easygui as g
def get_url(url):
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3314.0 Safari/537.36 SE 2.X MetaSr 1.0'}
req = requests.get(url, headers=headers)
return req
def get_img_url(url1, url2): #图片地址
headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3314.0 Safari/537.36 SE 2.X MetaSr 1.0',
'referer':url2
}
req = requests.get(url1, headers=headers)
return req
def get_page(url):#共有多少页
html = get_url(url).text
p = r"page-numbers.+[\d]+/'"
page_match = re.findall(p, html)
for each in page_match:
page = re.sub(r'\D','', each)
return page
def find_picurl(url): #每一页中的项目url
html = get_url(url).text
p = r'<li><a href="(https://www.mzitu.com/[\d]+)" target'
picurl = re.findall(p, html)
return picurl
def pro_name(url): #每一页的项目名称
html = get_url(url).text
p = r"alt='(.+)' width='236'"
targets = re.findall(p, html)
return targets
def get_p_page(url): #每一个项目的页数即图片数
html = get_url(url).text
p = r'<span>([\d]+)</span>'
p_page = re.findall(p, html)
for each in p_page:
page = each
return int(page)
def find_imgs(url):
html = get_url(url).text
p = re.search(r'img class="blur" src="(https.+\.jpg)', html)
return p.group(1)
def save_img(url, ref_url):
filename = url.split('/')[-1]
with open(filename, 'wb') as f:
img = get_img_url(url, ref_url).content
f.write(img)
def main():
folder = g.diropenbox("请选择存放照片的文件夹")
os.listdir(folder)
os.chdir(folder)
url = "https://www.mzitu.com/xinggan/"
page = get_page(url) #总共几页
print("总共有{}页".format(page))
f = True
while f == True:
Page = input("请输入下载第几页：")
url1 = 'https://www.mzitu.com/xinggan/page/{}/'.format(Page)
pic_url = find_picurl(url1)
pic_pro = pro_name(url1)
num = len(pic_url) #每一页的项目个数
print("第%s页共有%d个项目" % (Page, num))
for each in range(1, num+1):
print("第%d个项目是：" % each)
print(pic_pro)
Num = int(input("请输入需要下载第几个项目："))
p_page = get_p_page(pic_url)
print("共有%d页：" % p_page)
for i in range(1,p_page+1):
url2 = pic_url + '/' + str(i)
img_addr = find_imgs(url2)
print(img_addr)
save_img(img_addr, url2)
print("下载完毕")
ans = input("是否继续下载：输入Y/N")
if ans == 'N':
f = False
if __name__ == '__main__':
main()
哈哈
{:5_92:} haha 111 更OOXX过不去了…… 学习学习 1 想学一下 22222222222222222222 1
111111111 学习学习 学习学习 ？？？
666666666
. 学习学习 看看看
9999