最基本的抓取网页内容的代码实现:
#!/usr/bin/env python from urllib import urlretrieve def firstNonBlank(lines): for eachLine in lines: if not eachLine.strip(): continue else: return eachLine def firstLast(webpage): f = open(webpage) lines = f.readlines() f.close() print firstNonBlank(lines), lines.reverse() print firstNonBlank(lines), def download(url='http://www',process=firstLast): try: retval = urlretrieve(url)[0] except IOError: retval = None if retval: process(retval) if __name__ == '__main__': download()
利用urllib模块,来实现一个网页中针对图片的抓取功能:
import urllib.request import socket import re import sys import os targetDir = r"C:\Users\elqstux\Desktop\pic" def destFile(path): if not os.path.isdir(targetDir): os.mkdir(targetDir) pos = path.rindex('/') t = os.path.join(targetDir, path[pos+1:]) return t if __name__ == "__main__": hostname = "http://www.douban.com" req = urllib.request.Request(hostname) webpage = urllib.request.urlopen(req) contentBytes = webpage.read() for link, t in set(re.findall(r'(http:[^\s]*?(jpg|png|gif))', str(contentBytes))): print(link) urllib.request.urlretrieve(link, destFile(link))
import urllib.request import socket import re import sys import os targetDir = r"H:\pic" def destFile(path): if not os.path.isdir(targetDir): os.mkdir(targetDir) pos = path.rindex('/') t = os.path.join(targetDir, path[pos+1:]) #会以/作为分隔 return t if __name__ == "__main__": hostname = "http://www.douban.com/" req = urllib.request.Request(hostname) webpage = urllib.request.urlopen(req) contentBytes = webpage.read() match = re.findall(r'(http:[^\s]*?(jpg|png|gif))', str(contentBytes) )#r'(http:[^\s]*?(jpg|png|gif))'中包含两层圆括号,故有两个分组, #上面会返回列表,括号中匹配的内容才会出现在列表中 for picname, picType in match: print(picname) print(picType) ''''' 输出: http://img3.douban.com/pics/blank.gif gif http://img3.douban.com/icon/g111328-1.jpg jpg http://img3.douban.com/pics/blank.gif gif http://img3.douban.com/icon/g197523-19.jpg jpg http://img3.douban.com/pics/blank.gif gif ... '''