import requests
import re#根據url獲取網頁html內容
def getHtmlContent(url):page = requests.get(url)return page.texthtml = getHtmlContent('https://tieba.baidu.com/p/4840106397')#以html中使用re模塊解析出所有jpg圖片的url
#百度貼吧html中jpg圖片的url格式：<img...src="xxx.jpg" width=....>
def getJPGs(html):#解析jpg圖片url的正則jpgReg = re.compile(r'<img.*?src="(.*?\.jpg)"')#解析出jpg的url列表jpgs = re.findall(jpgReg,html)return jpgsjpgs = getJPGs(html) 
print(jpgs)html = 'https://tieba.baidu.com/f?ie=utf-8&kw=%E5%9B%BE%E7%89%87&fr=search'#用圖片url下載圖片并保存成制定文件名
def downloadJPG(imgUrl,fileName):#可自動關閉請求和相應的模塊from contextlib import closingwith closing(requests.get(imgUrl,stream=True)) as resp:with open(fileName,'wb') as f:for chunk in resp.iter_content(128):f.write(chunk)#批量下載圖片，默認保存在當前目錄下
def batchDownloadJPGs(imgUrls,path='./'):#用于給圖片命名count =1for url in imgUrls:downloadJPG(url,''.join([path,'{0}.jpg'.format(count)]))print('下載完成第{0}張圖片'.format(count))count =count+1#封裝，從百度貼吧網頁下載圖片
def download(url):html = getHtmlContent(url)jpgs = getJPGs(html)batchDownloadJPGs(jpgs)def main():url = 'http://tieba.baidu.com'download(url)if __name__ =='__main__' :main()

進入爬蟲學習：

首先導包

import requests
import re

?獲取網頁源碼，確定可以獲取，獲得了之后可以操作的整體對象

#根據url獲取網頁html內容
def getHtmlContent(url):page = requests.get(url)return page.texthtml = getHtmlContent('https://tieba.baidu.com/p/4840106397')

?獲取圖片，用到的就是很神奇的正則表達式，本人起初覺得很一般，沒什么不得了，但是用的時候，卻發現大道至簡。

#以html中使用re模塊解析出所有jpg圖片的url
#百度貼吧html中jpg圖片的url格式：<img...src="xxx.jpg" width=....>
def getJPGs(html):#解析jpg圖片url的正則jpgReg = re.compile(r'<img.*?src="(.*?\.jpg)"')#解析出jpg的url列表jpgs = re.findall(jpgReg,html)return jpgsjpgs = getJPGs(html) 
print(jpgs)html = 'https://tieba.baidu.com/f?ie=utf-8&kw=%E5%9B%BE%E7%89%87&fr=search'

?接下來就是獲取圖片，照著跑就行。

#用圖片url下載圖片并保存成制定文件名
def downloadJPG(imgUrl,fileName):#可自動關閉請求和相應的模塊from contextlib import closingwith closing(requests.get(imgUrl,stream=True)) as resp:with open(fileName,'wb') as f:for chunk in resp.iter_content(128):f.write(chunk)#批量下載圖片，默認保存在當前目錄下
def batchDownloadJPGs(imgUrls,path='./'):#用于給圖片命名count =1for url in imgUrls:downloadJPG(url,''.join([path,'{0}.jpg'.format(count)]))print('下載完成第{0}張圖片'.format(count))count =count+1#封裝，從百度貼吧網頁下載圖片
def download(url):html = getHtmlContent(url)jpgs = getJPGs(html)batchDownloadJPGs(jpgs)def main():url = 'http://tieba.baidu.com'download(url)if __name__ =='__main__' :main()

?