用Python爬虫抓取网络图片，很酸爽啊，嘿嘿

Python3.6版本，代码如下：

import re
import urllib.request
import ssl
ssl._create_default_https_context=ssl._create_unverified_context


def getimgtwo(url,page):
    req=urllib.request.Request(url)
    allcont=urllib.request.urlopen(req).read()
#    print(allcont)
    pattern=re.compile('&lt;div class="MeinvTuPianBox".*?&lt;/ul&gt;')
    getimgstr=re.search(pattern,str(allcont)).group(0)
#    print(getimgstr)
    patternimg=re.compile('&lt;img src="http://.*?.jpg')
    guolv=re.findall(patternimg,getimgstr)
    x=1
    for item in guolv:
        patternimgurl=re.compile('http://.*?.jpg')
        imgurl=re.search(patternimgurl,item).group(0)
        print(str(x)+"-&gt;"+imgurl)
        imagename="/Users/adongblog/Desktop/MyGame/Python/Img/meinv"+str(page)+"_"+str(x)+".jpg"
        try:
            urllib.request.urlretrieve(imgurl,filename=imagename)
        except urllib.error.URLError as e:
            if hasattr(e,"code"):
                print("add")
            if hasattr(e,"reson"):
                print("add2")
        x+=1

for i in range(1,10):
    url="http://www.27270.com/ent/meinvtupian/list_11_"+str(i)+".html"
    getimgtwo(url,i)

import re

import urllib.request

import ssl

ssl._create_default_https_context=ssl._create_unverified_context

def getimgtwo(url,page):

req=urllib.request.Request(url)

allcont=urllib.request.urlopen(req).read()

# print(allcont)

pattern=re.compile('<div class="MeinvTuPianBox".*?</ul>')

getimgstr=re.search(pattern,str(allcont)).group(0)

# print(getimgstr)

patternimg=re.compile('<img src="http://.*?.jpg')

guolv=re.findall(patternimg,getimgstr)

x=1

for item in guolv:

patternimgurl=re.compile('http://.*?.jpg')

imgurl=re.search(patternimgurl,item).group(0)

print(str(x)+"->"+imgurl)

imagename="/Users/adongblog/Desktop/MyGame/Python/Img/meinv"+str(page)+"_"+str(x)+".jpg"

try:

urllib.request.urlretrieve(imgurl,filename=imagename)

except urllib.error.URLError as e:

if hasattr(e,"code"):

print("add")

if hasattr(e,"reson"):

print("add2")

x+=1

for i in range(1,10):

url="http://www.27270.com/ent/meinvtupian/list_11_"+str(i)+".html"

getimgtwo(url,i)

一下子爬取了几百张图片，嘿嘿！

接下来爬取大图

import re
import urllib.request
import ssl
ssl._create_default_https_context=ssl._create_unverified_context


def getimgtwo(url,page,name):
    req=urllib.request.Request(url)
    allcont=urllib.request.urlopen(req).read()
#    print(allcont)
    pattern=re.compile('&lt;div class="articleV4Body".*?&lt;/a&gt;')
    getimgstr=re.search(pattern,str(allcont)).group(0)
#    print(getimgstr)
    patternimg=re.compile('&lt;img.*?src="http://.*?.jpg')
    guolv=re.findall(patternimg,getimgstr)
    x=1
    for item in guolv:
        patternimgurl=re.compile('http://.*?.jpg')
        imgurl=re.search(patternimgurl,item).group(0)
        print(str(page)+"-&gt;"+imgurl)
        imagename="/Users/adongblog/Desktop/MyGame/Python/ImgBig/"+name+"_"+str(page)+".jpg"
        try:
            urllib.request.urlretrieve(imgurl,filename=imagename)
        except urllib.error.URLError as e:
            if hasattr(e,"code"):
                print("add")
            if hasattr(e,"reson"):
                print("add2")
        x+=1

listid=258932
for i in range(1,8):
    url="http://www.27270.com/ent/meinvtupian/2018/"+str(listid)+"_"+str(i)+".html"
    getimgtwo(url,i,str(listid))

import re

import urllib.request

import ssl

ssl._create_default_https_context=ssl._create_unverified_context

def getimgtwo(url,page,name):

req=urllib.request.Request(url)

allcont=urllib.request.urlopen(req).read()

# print(allcont)

pattern=re.compile('<div class="articleV4Body".*?</a>')

getimgstr=re.search(pattern,str(allcont)).group(0)

# print(getimgstr)

patternimg=re.compile('<img.*?src="http://.*?.jpg')

guolv=re.findall(patternimg,getimgstr)

x=1

for item in guolv:

patternimgurl=re.compile('http://.*?.jpg')

imgurl=re.search(patternimgurl,item).group(0)

print(str(page)+"->"+imgurl)

imagename="/Users/adongblog/Desktop/MyGame/Python/ImgBig/"+name+"_"+str(page)+".jpg"

try:

urllib.request.urlretrieve(imgurl,filename=imagename)

except urllib.error.URLError as e:

if hasattr(e,"code"):

print("add")

if hasattr(e,"reson"):

print("add2")

x+=1

listid=258932

for i in range(1,8):

url="http://www.27270.com/ent/meinvtupian/2018/"+str(listid)+"_"+str(i)+".html"

getimgtwo(url,i,str(listid))

代码片段三

再来补全一下，通过输入列表，抓取列表中所有的大图，再做个小的窗口界面更直观一些如下图。

贴出代码如下：

import re
import urllib.request
import ssl
import time
import tkinter as tk
from tkinter import messagebox
ssl._create_default_https_context=ssl._create_unverified_context

window=tk.Tk()
window.title("抓美女，嘿嘿！")
window.geometry('500x100')

e=tk.Entry(window,show=None,width=60)
e.pack()

timename=time.strftime('%Y%m%d',time.localtime(time.time()))
def getimgtwo(url,listid,page):
    req=urllib.request.Request(url)
    allcont=urllib.request.urlopen(req).read()
    pattern=re.compile('&lt;div class="articleV4Body".*?.jpg')
    getimgstr=re.search(pattern,str(allcont)).group(0)
    patternimg=re.compile('&lt;img.*?src="http://.*?.jpg')
    guolv=re.findall(patternimg,getimgstr)
    x=1
    for item in guolv:
        patternimgurl=re.compile('http://.*?.jpg')
        imgurl=re.search(patternimgurl,item).group(0)
        print(imgurl)
        imagename="D:/python/ImgBigList2/"+timename+"_"+str(page)+"_"+str(listid)+".jpg"
        x+=1
        try:
            urllib.request.urlretrieve(imgurl,filename=imagename)
        except urllib.error.URLError as e:
            if hasattr(e,"code"):
                print("add")
            if hasattr(e,"reson"):
                print("add2")


# 获取列表
def getimglist(url):
    req=urllib.request.Request(url)
    allcont=urllib.request.urlopen(req).read()
    pattern=re.compile('&lt;div class="MeinvTuPianBox".*?&lt;/ul&gt;')
    getimgstr=re.search(pattern,str(allcont)).group(0)
    patternimg=re.compile('&lt;a href="http:.*?.html.*?"MMPic"')
    guolv=re.findall(patternimg,getimgstr)
    y=1
    for item in guolv:
        patternimgurl=re.compile('http://.*?.html')
        imgurl=re.search(patternimgurl,item).group(0)
        print(str(y)+imgurl)
        try:
            for j in range(1,8):
                pattimgurl=imgurl.replace('.html','')
                newimgurl=pattimgurl+"_"+str(j)+".html"
                getimgtwo(newimgurl,y,j)
        except urllib.error.URLError as e:
            if hasattr(e,"code"):
                print("add")
            if hasattr(e,"reson"):
                print("add2")
        y+=1

def getimgbtn():
    varurl=e.get()
    if varurl=='':
        tk.messagebox.showerror(title='错误',message='输入网址为空')
    else:
        getimglist(varurl)

btn=tk.Button(window,text='开始',width=15,height=2,command=getimgbtn).pack()

window.mainloop()

import re

import urllib.request

import ssl

import time

import tkinter as tk

from tkinter import messagebox

ssl._create_default_https_context=ssl._create_unverified_context

window=tk.Tk()

window.title("抓美女，嘿嘿！")

window.geometry('500x100')

e=tk.Entry(window,show=None,width=60)

e.pack()

timename=time.strftime('%Y%m%d',time.localtime(time.time()))

def getimgtwo(url,listid,page):

req=urllib.request.Request(url)

allcont=urllib.request.urlopen(req).read()

pattern=re.compile('<div class="articleV4Body".*?.jpg')

getimgstr=re.search(pattern,str(allcont)).group(0)

patternimg=re.compile('<img.*?src="http://.*?.jpg')

guolv=re.findall(patternimg,getimgstr)

x=1

for item in guolv:

patternimgurl=re.compile('http://.*?.jpg')

imgurl=re.search(patternimgurl,item).group(0)

print(imgurl)

imagename="D:/python/ImgBigList2/"+timename+"_"+str(page)+"_"+str(listid)+".jpg"

x+=1

try:

urllib.request.urlretrieve(imgurl,filename=imagename)

except urllib.error.URLError as e:

if hasattr(e,"code"):

print("add")

if hasattr(e,"reson"):

print("add2")

# 获取列表

def getimglist(url):

req=urllib.request.Request(url)

allcont=urllib.request.urlopen(req).read()

pattern=re.compile('<div class="MeinvTuPianBox".*?</ul>')

getimgstr=re.search(pattern,str(allcont)).group(0)

patternimg=re.compile('<a href="http:.*?.html.*?"MMPic"')

guolv=re.findall(patternimg,getimgstr)

y=1

for item in guolv:

patternimgurl=re.compile('http://.*?.html')

imgurl=re.search(patternimgurl,item).group(0)

print(str(y)+imgurl)

try:

for j in range(1,8):

pattimgurl=imgurl.replace('.html','')

newimgurl=pattimgurl+"_"+str(j)+".html"

getimgtwo(newimgurl,y,j)

except urllib.error.URLError as e:

if hasattr(e,"code"):

print("add")

if hasattr(e,"reson"):

print("add2")

y+=1

def getimgbtn():

varurl=e.get()

if varurl=='':

tk.messagebox.showerror(title='错误',message='输入网址为空')

else:

getimglist(varurl)

btn=tk.Button(window,text='开始',width=15,height=2,command=getimgbtn).pack()

window.mainloop()

输入列表网址，点击开始后，自动工作了，大约一个列表200张图尽收文件夹，嘿嘿！

接下来爬取大图

代码片段三

发表评论 取消回复

发表评论取消回复