Python爬虫，图片下载完后是损坏的，怎么解决？

图片描述

图片描述

coding:utf-8

import requests
from bs4 import BeautifulSoup
import os
import sys
reload(sys)
sys.setdefaultencoding('utf8')

爬取目标

url = 'http://www.mzitu.com/page/'
parser = 'html.parser'
cur_path = os.getcwd() + '/'

设置报头，Http协议

header = {

 'User-Agent' : 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Mobile Safari/537.36',
 'Accept' : 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8' , 
 'Accept-Encoding' : 'gzip, deflate' , 
 'Accept-Language' : 'zh-CN,zh;q=0.8,en;q=0.6' ,
 'Connection' : 'keep-alive' ,
 'Host':'www.mzitu.com' ,
 'Upgrade-Insecure-Requests': '1',
 'Referer': 'http:://http://www.mzitu.com/'

}

爬取的预览页面数量

preview_page_cnt = 2
for cur_page in range(1, int(preview_page_cnt) + 1):

cur_url = url + str(cur_page)
cur_page = requests.get(cur_url, headers=header)
# 解析网页
soup = BeautifulSoup(cur_page.text, parser)
# 图片入口和文字入口取一个即可
preview_link_list = soup.find(id='pins').find_all('a', target='_blank')[1::2]
for link in preview_link_list:
    dir_name = link.get_text().strip().replace('?', '')
    link = link['href']
    soup = BeautifulSoup(requests.get(link).text, parser)
    # 获取图片数量
    pic_cnt = soup.find('div', class_='pagenavi').find_all('a')[4].get_text()
    # 创建目录
    pic_path = cur_path + dir_name
    if os.path.exists(pic_path):
        print('directory exist!')
    else:
        os.mkdir(pic_path)
    os.chdir(pic_path)  # 进入目录，开始下载
    print('下载' + dir_name + '...')
    # 遍历获取每页图片的地址
    for pic_index in range(1, int(pic_cnt) + 1):
        pic_link = link + '/' + str(pic_index)
        cur_page = requests.get(pic_link, headers=header)
        soup = BeautifulSoup(cur_page.text, parser)
        pic_src = soup.find('div', 'main-image').find('img')['src']
        pic_name = pic_src.split('/')[-1]
        f = open(pic_name, 'wb')
        f.write(requests.get(pic_src, headers=header).content)
        f.close()
    os.chdir(cur_path)  # 完成下载，退出目录

print('下载完成')

回答：

不喜欢看截图

回答：

用urlretrieve试试

回答：

   ret = requests.get(pic_src, headers=header)
   open(pic_name, 'wb').write(ret.content)

这样试试呢

回答：

    for pic_index in range(1, int(pic_cnt) + 1):
        pic_link = link + '/' + str(pic_index)
        cur_page = requests.get(pic_link, headers=header)
        soup = BeautifulSoup(cur_page.text, parser)
        pic_src = soup.find('div', 'main-image').find('img')['src']
        pic_name = pic_src.split('/')[-1]
        f = open(pic_name, 'wb')
        f.write(requests.get(pic_src, headers=header).content) # header有问题
        f.close()

header有问题，自己改一下吧

以上是 Python爬虫，图片下载完后是损坏的，怎么解决？ 的全部内容， 来源链接： utcz.com/a/162531.html

回到顶部