爬取網址:www.mzitu.com
源代碼:
```python
import os
import requests
import bs4
from bs4 import BeautifulSoup
import random
import time
lots_headers = [
"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:30.0) Gecko/20100101 Firefox/30.0",
"Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Win64; x64; Trident/6.0)",
'Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11',
'Opera/9.25 (Windows NT 5.1; U; en)',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)',
'Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Kubuntu)',
'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12',
'Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9',
"Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:10.0) Gecko/20100101 Firefox/10.0",
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36'
]
global headers
headers = {'User-Agent': random.choice(lots_headers)}
global savepath
savepath = "G:\ysltest2"
global mziTu
mziTu = "http://www.mzitu.com"
# 創建文件
def creatFile(filepath):
if os.path.exists(filepath) is False:
os.mkdir(filepath)
os.chdir(filepath)
# 下載文件
def downLoad(file):
global headers
res_sub = requests.get(mziTu, headers=headers)
soup_sub = BeautifulSoup(res_sub.text, 'html.parser')
# 找到欄目
all_a = soup_sub.find('div', class_='postlist').find_all('a', target='_blank')
# 使用count防止重複下載
count = 0
for a in all_a:
count = count + 1
if count % 2 == 0:
headers = {'User-Agent':random.choice(lots_headers)}
# 提取href
href = a.attrs['href']
# print("套圖地址:"+href)
res_sub_1 = requests.get(href, headers=headers)
soup_sub_1 = BeautifulSoup(res_sub_1.text, 'html.parser')
try:
# 獲取最大套圖數量
img_max = soup_sub_1.find('div', class_='pagenavi').find_all('span')[6].text
# print("套圖數量:"+img_max)
for j in range(1, int(img_max)+1):
time.sleep(random.randint(1, 3))
headers = {'User-Agent': random.choice(lots_headers)}
href_sub = href + "/" + str(j)
print("圖片地址:"+href_sub)
res_sub_2 = requests.get(href_sub, headers=headers)
soup_sub_2 = BeautifulSoup(res_sub_2.text, 'html.parser')
img = soup_sub_2.find('div', class_='main-image').find('img')
if isinstance(img, bs4.element.Tag):
# 提取src
src = img.attrs['src']
array = src.split('/')
file_name = array[len(array)-1]
# 防盜鏈加入Referer
headers = {'User-Agent': random.choice(lots_headers), 'Referer': src}
img = requests.get(src, headers=headers)
# print("開始下載圖片", img)
f = open(file_name, 'ab')
f.write(img.content)
print("圖片"+file_name+"保存成功,保存地址:"+file)
f.close()
except Exception as e:
print(e)
def main():
res = requests.get(mziTu, headers=headers)
soup = BeautifulSoup(res.text, 'html.parser')
# 創建總文件夾
creatFile(savepath)
# 獲取首頁總頁數
img_max = soup.find('div', class_='nav-links').find_all('a')[3].text
print("總頁數爲"+img_max)
for i in range(1, int(img_max)+1):
# 獲取每頁的URL地址
if i == 1:
page = mziTu
else:
page = mziTu+'page/'+str(i)
# 創建子文件夾
file = savepath + "\\" + str(i)
creatFile(file)
# 下載圖片
# print("套圖頁碼:"+page)
downLoad(file)
if __name__ == '__main__':
main()
``