[宅男福利]用Python下载页面中所有的图片

思路分析

首先利用Python的Requests库去获取参数中页面的内容 , 然后进行使用BeautifulSoup库进行解析 , 解析到图片以后开启多线程进行下载保存

截图展示 :

Paste_Image.png

代码实现 :

#!/usr/bin/env python
#encoding:utf8

import requests
import threading
from bs4 import BeautifulSoup
import sys
import os

# config-start
url = sys.argv[1]
threadNumber = 20 # 设置线程数
# config-end

def getContent(url):
    response = requests.get(url)
    response.encoding = 'utf-8' # 设置相应体的字符集
    return response.text

def getTitle(soup):
    return soup.title.string.encode("GBK")

def getImageLinks(soup):
    imgs = soup.findAll("img")
    result = []
    for img in imgs:
        result.append(img)
    return result

def makeDirectory(dicName):
    if not os.path.exists(dicName):
        os.mkdir(dicName)

def downloadImage(imgUrl,savePath): 
    local_filename = imgUrl.split('/')[-1] 
    local_filename = formatFileName(local_filename)
    r = requests.get(imgUrl, stream=True) 
    counter = 0
    if not savePath.endswith("\\"):
        savePath += "\\"
    f = open(savePath + local_filename, 'wb')
    for chunk in r.iter_content(chunk_size=1024): 
        if chunk: 
            f.write(chunk) 
            f.flush()
            counter += 1
    f.close()

def formatFileName(fileName):
    fileName = fileName.replace("/","_")
    fileName = fileName.replace("\\","_")
    fileName = fileName.replace(":","_")
    fileName = fileName.replace("*","_")
    fileName = fileName.replace("?","_")
    fileName = fileName.replace("\"","_")
    fileName = fileName.replace(">","_")
    fileName = fileName.replace("<","_")
    fileName = fileName.replace("|","_")
    fileName = fileName.replace(" ","_")
    return fileName

def threadFunction(imgSrc,directoryName):
    downloadImage(imgSrc,directoryName)

class myThread (threading.Thread):
    def __init__(self, imgSrc, directoryName):
        threading.Thread.__init__(self)
        self.imgSrc = imgSrc
        self.directoryName = directoryName

    def run(self):
        threadFunction(self.imgSrc, self.directoryName)


content = getContent(url)
soup = BeautifulSoup(content, "html.parser")
images = getImageLinks(soup)
title = getTitle(soup)
title = formatFileName(title)
print u"页面标题 : " , title
print u"本页图片数量 :",len(images)
print u"正在创建文件夹以用来保存所有图片"
makeDirectory(title)
threads = []

for image in images:
    src = image['src']
    print u"图片地址 : " + src
    threads.append(myThread(str(src), str(title)))

for t in threads:
    t.start()
    while True:
        if(len(threading.enumerate()) < threadNumber):
            break

print u"所有图片下载完成 ! "

后记 :

之前的脚本在处理某些网站的时候容错性还不是很强 , 这里将脚本简单修改了一下
新版本代码如下

#!/usr/bin/env python
#encoding:utf8

import requests
import threading
from bs4 import BeautifulSoup
import sys
import os

if len(sys.argv) != 2:
    print("Usage : ")
    print("        python main.py [URL]")
    exit(1)

# config-start
url = sys.argv[1]
threadNumber = 20 # 设置线程数
# config-end

def getContent(url):
    try:
        response = requests.get(url)
        response.raise_for_status()
        response.encoding = response.apparent_encoding
        return response.text
    except Exception as e:
        print(e)
        return str(e)

def getTitle(soup):
    try:
        return soup.title.string
    except:
        return "UnTitled"

def getImageLinks(soup):
    imgs = soup.findAll("img")
    result = []
    for img in imgs:
        try:
            src = img['src']
            if src.startswith("http"):
                result.append(img['src'])
            else:
                result.append(domain + img['src'])
        except:
            continue
    return result

def makeDirectory(dicName):
    if not os.path.exists(dicName):
        os.mkdir(dicName)

def downloadImage(imgUrl,savePath):
    local_filename = imgUrl.split('/')[-1]
    local_filename = formatFileName(local_filename)
    r = requests.get(imgUrl, stream=True)
    counter = 0
    if not savePath.endswith("/"):
        savePath += "/"
    f = open(savePath + local_filename + ".png", 'wb')
    for chunk in r.iter_content(chunk_size=1024):
        if chunk:
            f.write(chunk)
            f.flush()
            counter += 1
    f.close()

def formatFileName(fileName):
    fileName = fileName.replace("/","_")
    fileName = fileName.replace("\\","_")
    fileName = fileName.replace(":","_")
    fileName = fileName.replace("*","_")
    fileName = fileName.replace("?","_")
    fileName = fileName.replace("\"","_")
    fileName = fileName.replace(">","_")
    fileName = fileName.replace("<","_")
    fileName = fileName.replace("|","_")
    fileName = fileName.replace(" ","_")
    return fileName

def threadFunction(imgSrc,directoryName):
    downloadImage(imgSrc,directoryName)

class myThread (threading.Thread):
    def __init__(self, imgSrc, directoryName):
        threading.Thread.__init__(self)
        self.imgSrc = imgSrc
        self.directoryName = directoryName

    def run(self):
        threadFunction(self.imgSrc, self.directoryName)


def getPrefix(url):
    # http://doamin/xxx.jpg
    return ''.join(i+"/" for i in url.split("/")[0:4])

def getDomain(url):
    return ''.join(i+"/" for i in url.split("/")[0:3])



content = getContent(url)
prefix = getPrefix(url)
domain = getDomain(url)
soup = BeautifulSoup(content, "html.parser")
images = getImageLinks(soup)
title = getTitle(soup)
title = formatFileName(title)
print(u"页面标题 : " , title)
print(u"本页图片数量 :",len(images))
print(u"正在创建文件夹以用来保存所有图片")
makeDirectory(title)
threads = []

for image in images:
    print(u"图片地址 : " + image)
    threads.append(myThread(image, title))

for t in threads:
    t.start()
    while True:
        if(len(threading.enumerate()) < threadNumber):
            break

print(u"所有图片已加入下载队列 ! 正在下载...")

测试结果 :

image.png

[宅男福利]用Python下载页面中所有的图片

推荐阅读更多精彩内容