python 爬虫图片打不开_python爬虫抓取图片 终端报错 <urlopen error no hsot given> 是什么原因？...

python利用urllib爬虫，图片获取二十几张后就报错

python版本3.6 windows系统下运行

urllib.error.URLError:

代码如下：

#!/usr/bin/python

# -*- coding:utf-8 -*-

import urllib

import requests

import re

from bs4 import BeautifulSoup

import csv

import socket

socket.setdefaulttimeout(300)

headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36"}

#url池

url1 = ('http://jandan.net/ooxx/page-')

urls = []

src_list = []

for i in range(2000,2020):

urls.append(url1+str(i))

print (urls)

for url in urls:#从url池中获取url

r = requests.get(url,headers = headers)#获取页面

html = BeautifulSoup(r.text,'html.parser')#利用tag结构划分#获取名称

for link in html.find_all('img'):

src_list.append('http:'+link.get('src'))

src_list.pop()

print (src_list)

tmp = 1

for src in src_list:

urllib.request.urlretrieve(src,r'C:\Users\姜梦天\Desktop\spider\img\%s.jpg' % tmp)

tmp += 1

print ('下载完毕')

.....尝试解决未果...

求各位大大DEBUG....

#coding=utf-8

import os

import requests

from pyquery import PyQuery as Q

def download_image(image_url):

if not image_url.startswith('http:'):

image_url = 'http:{}'.format(image_url)

image_dir = './image'

if not os.path.exists(image_dir):

os.mkdir(image_dir)

_, image_name = os.path.split(image_url)

image_path = os.path.join(image_dir, image_name)

print 'download:', image_url,

try:

r = requests.get(image_url)

with open(image_path, 'wb') as f:

f.write(r.content)

print 'success'

except:

print 'error'

if __name__ == '__main__':

for i in range(2000, 2020):

url = 'http://jandan.net/ooxx/page-{0}'.format(i)

print 'get:', url

r = requests.get(url)

for _ in Q(r.text).find('img'):

image_url = Q(_).attr('src')

download_image(image_url)

......改进了代码.写入了try.虽然还是会报错......但是不妨碍继续下载图片........

代码如下：#!/usr/bin/python

# -*- coding:utf-8 -*-

import urllib

import requests

import re

from bs4 import BeautifulSoup

import csv

import socket

socket.setdefaulttimeout(300)

headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36"}

#url池

url1 = ('http://jandan.net/ooxx/page-')

urls = []

src_list = []

for i in range(1500,2380):

urls.append(url1+str(i))

print (urls)

for url in urls:#从url池中获取url

r = requests.get(url,headers = headers)#获取页面

html = BeautifulSoup(r.text,'html.parser')

for link in html.find_all('img'):

try:

src_list.append('http:'+link.get('src'))

except:

print ('url获取错误')

src_list.pop()

print (src_list)

tmp = 0

for src in src_list:

try:

urllib.request.urlretrieve(src,r'C:\Users\姜梦天\Desktop\spider\img\%s.jpg' % tmp)

tmp = tmp+1

except:

print ('失败')

print ('下载完毕')

可以下载众多妹子的图片了

玩蛇网文章，转载请注明出处和文章网址：https://www.iplaypy.com/wenda/wd13779.html

相关文章 Recommend