python 爬取网页图片2

最新推荐文章于 2022-05-24 20:47:39 发布

转载最新推荐文章于 2022-05-24 20:47:39 发布 · 500 阅读

1 ·

CC 4.0 BY-SA版权

原文链接：https://blog.youkuaiyun.com/toyijiu/article/details/79335240

本文详细介绍使用Python爬虫从不同网站抓取图片的方法，包括贴吧、新闻网站及壁纸站点等，涵盖基本爬虫框架搭建、图片链接解析、图片下载保存及图片元数据提取等内容。

（2）Python爬虫入门——爬取贴吧图片
https://blog.youkuaiyun.com/toyijiu/article/details/79335240

[START]

import re
import urllib
import sys  
reload(sys) 
sys.setdefaultencoding('utf8')
def getHtml(url):
    page = urllib.urlopen(url)
    html = page.read()
    return html

def getImg(html, x):
    reg = r'src="(http://img.*?\.jpg)"'
    imgre = re.compile(reg)
    imList = re.findall(reg, html)
    print(imList)
    for i in imList:
        print(i)
        print x
        urllib.urlretrieve(i, '%s.jpg' % x)
        x += 1
    return x

x = 1
url = "http://tieba.baidu.com/p/3466236659?pn="
for k in range(1, 28):
    ul = url+str(k)
    print ul
    html = getHtml(ul)
    # print html
    x = getImg(html, x)

[END]

（3）python批量抓取网页图片
https://blog.youkuaiyun.com/qq_38344751/article/details/99448271

[START]

#!/usr/bin/python3
# -*- encoding:utf-8 *-*
from urllib import request
import re   
import sys
def getResponse(url):
    url_request = request.Request(url)
    url_response = request.urlopen(url_request)
    return url_response   
 
def getJpg(data):
    jpglist = re.findall(r'src="http.+?.jpg"',data)
    return  jpglist
 
def downLoad(jpgUrl,n):
    try:
        request.urlretrieve(jpgUrl,'pic\\%s.jpg'  %n)   
    except Exception as e:
        print(e)
    finally:
        print('picture %s downloding success' % n)
 
http_response = getResponse("http://dzh.mop.com/") 
data = http_response.read().decode('utf-8')
n = 1
jpglist = getJpg(data)
for info in jpglist:
    print(info)
    s = re.findall(r'http.+?.jpg',info)
    downLoad(s[0],n)
    n= n +1
    
# from urllib import request
# url='http://dzh.mop.com/'
# url_request=request.Request(url)
# url_response=request.urlopen(url_request)
# data=url_response.read().decode('utf-8')
# jpglist=re.findall('http.+?.jpg',data)
 
# n=1
# for each in jpglist:
#     print(each)
#     try:
#         request.urlretrieve(each,'pic\\%s.jpg',n)
#     except Exception as e:
#         print(e)
#     finally:
#         print('success downloding %s',n)
#     n+=1

[END]

（4）Python爬虫之爬取网站图片
https://blog.youkuaiyun.com/qq_38412868/article/details/82080260

[START]

from bs4 import BeautifulSoup
import requests
 
 
if __name__=='__main__':
    url='http://www.27270.com/tag/649.html'
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36"}
    req = requests.get(url=url, headers=headers)
    req=requests.get(url=url,headers=headers)
    req.encoding = 'gb2312'
    html=req.text
    bf=BeautifulSoup(html,'lxml')
    targets_url=bf.find('div',class_='w1200 oh').find_all('a',target='_blank')
    for each in targets_url:
        img_req=requests.get(url=each.get('href'),headers=headers)
        img_req.encoding = 'gb2312'
        html = img_req.text
        bf = BeautifulSoup(html, 'lxml')
        img_url = bf.find('div', class_='articleV4Body').find('img')['src']
        name=each.img.get('alt')+'.jpg'
        path=r'C:\Users\asus\Desktop\新建文件夹'
        file_name = path + '\\' + name
        try:
            req1=requests.get(img_url,headers=headers)
            f=open(file_name,'wb')
            f.write(req1.content)
            f.close()
        except:
            print("some error")

from bs4 import BeautifulSoup
import requests
 
def download(img_url,headers,n):
    req = requests.get(img_url, headers=headers)
    name = '%s'%n+'='+img_url[-15:]
    path = r'C:\Users\asus\Desktop\火影壁纸1'
    file_name = path + '\\' + name
    f = open(file_name, 'wb')
    f.write(req.content)
    f.close
 
def parses_picture(url,headers,n):
    url = r'http://desk.zol.com.cn/' + url
    img_req = requests.get(url, headers=headers)
    img_req.encoding = 'gb2312'
    html = img_req.text
    bf = BeautifulSoup(html, 'lxml')
    try:
        img_url = bf.find('div', class_='photo').find('img').get('src')
        download(img_url,headers,n)
        url1 = bf.find('div',id='photo-next').a.get('href')
        parses_picture(url1,headers,n)
    except:
        print(u'第%s图片集到头了'%n)
 
if __name__=='__main__':
    url='http://desk.zol.com.cn/dongman/huoyingrenzhe/'
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36"}
    req = requests.get(url=url, headers=headers)
    req=requests.get(url=url,headers=headers)
    req.encoding = 'gb2312'
    html=req.text
    bf=BeautifulSoup(html,'lxml')
    targets_url=bf.find_all('li',class_='photo-list-padding')
    n=1
    for each in targets_url:
        url = each.a.get('href')
        parses_picture(url,headers,n)
        n=n+1

[END]

（5）python 获取网站上所有图片的元数据信息
https://cloud.tencent.com/developer/article/1477335

[START]

!/usr/bin/python
# -*- encoding:utf-8 *-*
import optparse
 from PIL import Image
 from PIL.ExifTags import TAGS
 import urllib2
 from bs4 import BeautifulSoup as BS
 from os.path import basename
 from urlparse import urlsplit

#通过BeautifulSoup查找URL中所有的img标签
def findImages(url):
 print '[+] Finding images on ' + url
 urlContent = urllib2.urlopen(url).read()
 soup = BS(urlContent, 'lxml')
 imgTags = soup.findAll('img')
 return imgTags

#通过img标签的src属性的值来获取图片URL下载图片
def downloadImage(imgTag):
 try:
 print '[+] Dowloading image...'
 imgSrc = imgTag['src']
 imgContent = urllib2.urlopen(imgSrc).read()
 imgFileName = basename(urlsplit(imgSrc)[2])
 imgFile = open(imgFileName, 'wb')
 imgFile.write(imgContent)
 imgFile.close()
 return imgFileName
 except:
 return ' '

#获取图像文件的元数据，并寻找是否存在Exif标签“GPSInfo”
def testForExif(imgFileName):
 try:
 exifData = {}
 imgFile = Image.open(imgFileName)
 info = imgFile._getexif()
 if info:
 for (tag, value) in info.items():
 decoded = TAGS.get(tag, tag)
 exifData[decoded] = value
 exifGPS = exifData['GPSInfo']
 if exifGPS:
 print '[*] ' + imgFileName + ' contains GPS MetaData'
 except:
 pass

def main():
 parser = optparse.OptionParser('[*]Usage: python Exif.py -u <target url>')
 parser.add_option('-u', dest='url', type='string', help='specify url address')
 (options, args) = parser.parse_args()
 url = options.url
 if url == None:
 print parser.usage
 exit(0)
 else:
 imgTags = findImages(url)
 for imgTag in imgTags:
 imgFileName = downloadImage(imgTag)
 testForExif(imgFileName)

if name == 'main':
 main()

[END]