import requests

import os, sys, stat

from lxml import etree

import time

class HuangMan():

def __init__(self):

#設(shè)置請(qǐng)求頭

self.headers = {'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'}

self.url_list = []

self.Hman_url_list = []

self.Hman_name_list = []

def get_url_list(self):

#這里是設(shè)置爬取到第3頁(yè)，想要更多的話(huà)請(qǐng)自行更改

url = "http://www.93qoqo.com/artlist/27-%d.html"

for i in range(2,4):

#獲取第2到3頁(yè)的url

self.url_list.append(url % i)

#由于第一頁(yè)網(wǎng)址不同，所以單獨(dú)寫(xiě)一個(gè)獲取函數(shù)

def start_1(self):

url_1 = "http://www.93qoqo.com/artlist/27.html"

response = requests.get(url_1, headers = self.headers).content.decode('utf-8')

html = etree.HTML(response)

result = html.xpath('//ul/li[@class="name"]/a')

for i in range(len(result)):

#獲取result的屬性

shuxing = result[i].attrib

#獲取url

self.Hman_url_list.append("http://www.93qoqo.com" + shuxing.get('href'))

#獲取名字

self.Hman_name_list.append(shuxing.get('title'))

print("正在爬取第1頁(yè)的網(wǎng)站信息")

time.sleep(2)

#從第二頁(yè)開(kāi)始爬取信息

def start(self):

self.start_1()

self.get_url_list()

for url in self.url_list:

response = requests.get(url, headers = self.headers).content.decode('utf-8')

html = etree.HTML(response)

result = html.xpath('//ul/li[@class="name"]/a')

for i in range(len(result)):

#獲取result的屬性

shuxing = result[i].attrib

#獲取url

self.Hman_url_list.append("http://www.93qoqo.com" + shuxing.get('href'))

#獲取名字

self.Hman_name_list.append(result[i].text)

print("正在爬取第%d頁(yè)的網(wǎng)站信息" % (self.url_list.index(url) + 2))

time.sleep(2)

self.wenjian()

self.main()

def wenjian(self):

#創(chuàng)建文件夾

if os.path.exists("photo") == False:

os.makedirs("photo")

os.chmod("photo", stat.S_IWRITE)

os.chdir("photo")

else:

print("文件已經(jīng)存在")

def main(self):

for url in self.Hman_url_list:

response = requests.get(url, headers = self.headers).content.decode('utf-8')

html = etree.HTML(response)

result = html.xpath('//center/div[@class="t_msgfont"]/img')

print(self.Hman_name_list[self.Hman_url_list.index(url)])

for i in range(len(self.Hman_name_list)):

#創(chuàng)建次級(jí)文件夾用于存放圖片

f = os.makedirs(self.Hman_name_list[i])

os.chmod(self.Hman_name_list[i], stat.S_IWRITE)

print("正在創(chuàng)建文件夾")

for e in range(len(result)):

print("下載圖片中。。。請(qǐng)稍等片刻")

name ="%d.jpg" % e

#請(qǐng)求圖片

respomse=requests.get(url,headers=self.headers)

#下載

with open(os.path.join(self.Hman_name_list[i],name),mode='wb') as f:

f.write(respomse.content)

if __name__ == "__main__":

h = HuangMan()

h.start()

總結(jié)

以上是生活随笔為你收集整理的python 下载图片损坏_爬虫爬取出的图片下载出错，图片文件直接损坏的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。