import requests
from bs4 import BeautifulSoup
import os
import sys
#http://blog.csdn.net/baidu_35085676/article/details/68958267
#安卓端需要此语句
reload(sys)
sys.setdefaultencoding('utf-8')
if(os.name == 'nt'):
print(u'你正在使用win平台')
else:
print(u'你正在使用linux平台')
header = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 UBrowser/6.1.2107.204 Safari/537.36',
'Referer':'http://www.mzitu.com/'
}
#http请求头
all_url = 'http://www.mzitu.com'
start_html = requests.get(all_url,headers = header)
character=['"','/','?','<','>','*','|','\\',':']#文件名不能含有这些字符
#保存地址
#path = 'D:/mzitu/'
path=os.getcwd()+'/pic/'
#找寻最大页数
soup = BeautifulSoup(start_html.text,"html.parser")
page = soup.find_all('a',class_='page-numbers')
max_page = page[-2].text
same_url = 'http://www.mzitu.com/page/'
for n in range(1,int(max_page)+1):
ul = same_url+str(n)
start_html = requests.get(ul, headers=header)
soup = BeautifulSoup(start_html.text,"html.parser")
all_a = soup.find('div',class_='postlist').find_all('a',target='_blank')
for a in all_a:
title = a.get_text() #提取文本
old_title=title
for i in character:
if i in title:
title=title.replace(i,'')
#print(title)
#print(old_title)
if(title != ''):
print("准备扒取:"+title)
#win不能创建带?的目录
if(os.path.exists(path+title.strip())):
#print('目录已存在')
flag=1
else:
os.makedirs(path+title.strip())
flag=0
os.chdir(path + title.strip())
href = a['href']
html = requests.get(href,headers = header)
mess = BeautifulSoup(html.text,"html.parser")
pic_max = mess.find_all('span')
pic_max = pic_max[10].text #最大页数
if(flag == 1 and len(os.listdir(path+title.strip())) >= int(pic_max)):
print('已经保存完毕,跳过')
continue
for num in range(1,int(pic_max)+1):
pic = href+'/'+str(num)
html = requests.get(pic,headers = header)
mess = BeautifulSoup(html.text,"html.parser")
pic_url = mess.find('img',alt = old_title)
#print(pic_url)
html = requests.get(pic_url['src'],headers = header)
file_name = pic_url['src'].split(r'/')[-1]
f = open(file_name,'wb')
f.write(html.content)
f.close()
print('完成')
print('第',n,'页完成')
爬取图片分类保存
最新推荐文章于 2021-06-02 18:09:06 发布