python网络爬虫一

正则表达式详细介绍

import urllib2
import random
#浏览器信息
USER_AGENTS = ["Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1","Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6","Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6","Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1","Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5","Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3","Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3","Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3","Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3","Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3","Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3","Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3","Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24","Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24","Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/531.21.8 (KHTML, like Gecko) Version/4.0.4 Safari/531.21.10","Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/533.17.8 (KHTML, like Gecko) Version/5.0.1 Safari/533.17.8","Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/533.19.4 (KHTML, like Gecko) Version/5.0.2 Safari/533.18.5","Mozilla/5.0 (Windows; U; Windows NT 6.1; en-GB; rv:1.9.1.17) Gecko/20110123 (like Firefox/3.x) SeaMonkey/2.0.12","Mozilla/5.0 (Windows NT 5.2; rv:10.0.1) Gecko/20100101 Firefox/10.0.1 SeaMonkey/2.7.1","Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.8 (KHTML, like Gecko) Chrome/4.0.302.2 Safari/532.8","Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.464.0 Safari/534.3","Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_5; en-US) AppleWebKit/534.13 (KHTML, like Gecko) Chrome/9.0.597.15 Safari/534.13","Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.186 Safari/535.1","Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.54 Safari/535.2","Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7","Mozilla/5.0 (Macintosh; U; Mac OS X Mach-O; en-US; rv:2.0a) Gecko/20040614 Firefox/3.0.0 ","Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.5; en-US; rv:1.9.0.3) Gecko/2008092414 Firefox/3.0.3","Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.5; en-US; rv:1.9.1) Gecko/20090624 Firefox/3.5","Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.6; en-US; rv:1.9.2.14) Gecko/20110218 AlexaToolbar/alxf-2.0 Firefox/3.6.14","Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.5; en-US; rv:1.9.2.15) Gecko/20110303 Firefox/3.6.15","Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1"]
#代理IP
proxies = ['116.213.98.6:8080','122.114.31.177:808','121.31.195.145:8123','125.118.147.0:808']
#设置请求对象
req = urllib2.Request('http://www.baidu.com/')# 设置请求头部信息
req.add_header('User-Agent',random.choice(USER_AGENTS))#  设置代理IP地址
proxy_support = urllib2.ProxyHandler({"http":random.choice(proxies)})
opener = urllib2.build_opener(proxy_support)
urllib2.install_opener(opener)
# 2.获取访问网站后，网站返回的对象
res = urllib2.urlopen(req)
# 3.处理浏览器返回的对象
# 3.1如读取
print(res.read())
#查看dir,打印url地址，访问信息msg,状态码code
# print(dir(res))
# print(res.url)    #http://www.baidu.com/
# print(res.msg)    #OK
# print(res.code)  #200

#设置一个函数，只用来获取网页内容
import urllib2
import random
import json
import re
count = 0
def getHtml(url):USER_AGENTS = ["Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1","Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6","Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6","Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1","Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5","Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3","Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3","Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3","Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3","Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3","Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3","Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3","Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24","Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24","Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/531.21.8 (KHTML, like Gecko) Version/4.0.4 Safari/531.21.10","Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/533.17.8 (KHTML, like Gecko) Version/5.0.1 Safari/533.17.8","Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/533.19.4 (KHTML, like Gecko) Version/5.0.2 Safari/533.18.5","Mozilla/5.0 (Windows; U; Windows NT 6.1; en-GB; rv:1.9.1.17) Gecko/20110123 (like Firefox/3.x) SeaMonkey/2.0.12","Mozilla/5.0 (Windows NT 5.2; rv:10.0.1) Gecko/20100101 Firefox/10.0.1 SeaMonkey/2.7.1","Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.8 (KHTML, like Gecko) Chrome/4.0.302.2 Safari/532.8","Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.464.0 Safari/534.3","Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_5; en-US) AppleWebKit/534.13 (KHTML, like Gecko) Chrome/9.0.597.15 Safari/534.13","Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.186 Safari/535.1","Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.54 Safari/535.2","Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7","Mozilla/5.0 (Macintosh; U; Mac OS X Mach-O; en-US; rv:2.0a) Gecko/20040614 Firefox/3.0.0 ","Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.5; en-US; rv:1.9.0.3) Gecko/2008092414 Firefox/3.0.3","Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.5; en-US; rv:1.9.1) Gecko/20090624 Firefox/3.5","Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.6; en-US; rv:1.9.2.14) Gecko/20110218 AlexaToolbar/alxf-2.0 Firefox/3.6.14","Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.5; en-US; rv:1.9.2.15) Gecko/20110303 Firefox/3.6.15","Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1"]# 代理IPproxies = ['116.213.98.6:8080','122.114.31.177:808','121.31.195.145:8123','125.118.147.0:808']# 设置请求对象req = urllib2.Request(url)# 设置请求头部信息req.add_header('User-Agent', random.choice(USER_AGENTS))#  设置代理IP地址proxy_support = urllib2.ProxyHandler({"http": random.choice(proxies)})opener = urllib2.build_opener(proxy_support)urllib2.install_opener(opener)# 访问并获取服务端返回的对象try:res = urllib2.urlopen(req)html = res.read()return htmlexcept:global countcount+=1if(count>20):print count,json.dumps('请检查网络设置',ensure_ascii=False)returngetHtml(url)   #自己执行自己douban = getHtml('https://www.douban.com')
print str(douban)
reg = re.compile('href=".*"')    #查找网页所有带href字段的内容
print re.search(reg,douban)
print re.findall(reg,douban)

import urllib2
req = urllib2.Request('http://blog.csdn.net/cecrel')
try:res = urllib2.urlopen(req)except urllib2.HTTPError,e:   #HTTPError是URLError的子类print dir(e)print e.code    #403print e.msg     #Forbiddenprint e.reason   #Forbidden
except urllib2.URLError, e:   #URLError包含HTTPErrorprint e.reason
print 'over'

python网络爬虫一相关推荐

爬虫书籍-Python网络爬虫权威指南OCR库 NLTK 数据清洗 BeautifulSoup Lambda表达式 Scrapy 马尔可夫模型
Python网络爬虫权威指南编辑推荐适读人群 :需要抓取Web 数据的相关软件开发人员和研究人员作为一种采集和理解网络上海量信息的方式,网页抓取技术变得越来越重要.而编写简单的自动化程序(网络爬 ...
python网络爬虫_Python网络爬虫——爬取视频网站源视频！
原标题:Python网络爬虫--爬取视频网站源视频! 学习前提 1.了解python基础语法 2.了解re.selenium.BeautifulSoup.os.requests等python第三方库 ...
《精通Python网络爬虫：核心技术、框架与项目实战》——1.3　网络爬虫的组成...
本节书摘来自华章出版社<精通Python网络爬虫:核心技术.框架与项目实战>一书中的第1章,第1.3节,作者韦玮,更多章节内容可以访问云栖社区"华章计算机"公众号查 ...
python商业爬虫教程_廖雪峰老师的Python商业爬虫课程 Python网络爬虫实战教程体会不一样的Python爬虫课程...
廖雪峰老师的Python商业爬虫课程 Python网络爬虫实战教程体会不一样的Python爬虫课程 1.JPG (53.51 KB, 下载次数: 1) 2019-8-9 08:15 上传 2.JPG ...
python爬虫教程视频下载-利用Python网络爬虫获取电影天堂视频下载链接【详细教程】...
相信大家都有一种头疼的体验,要下载电影特别费劲,对吧?要一部一部的下载,而且不能直观的知道最近电影更新的状态. 今天以电影天堂为例,带大家更直观的去看自己喜欢的电影,并且下载下来. [二.项目准备] ...
python网络爬虫权威指南百度云-分析《Python网络爬虫权威指南第2版》PDF及代码...
对那些没有学过编程的人来说,计算机编程看着就像变魔术.如果编程是魔术(magic),那么网页抓取(Web scraping)就是巫术(wizardry),也就是运用"魔术"来实现精 ...
python爬虫文件代码大全-Python网络爬虫实战项目代码大全（长期更新，欢迎补充）...
WechatSogou[1]- 微信公众号爬虫.基于搜狗微信搜索的微信公众号爬虫接口,可以扩展成基于搜狗搜索的爬虫,返回结果是列表,每一项均是公众号具体信息字典.[1]: https://github ...
精通python网络爬虫-精通python网络爬虫
广告关闭腾讯云11.11云上盛惠 ,精选热门产品助力上云,云服务器首年88元起,买的越多返的越多,最高返5000元! 作者:韦玮转载请注明出处随着大数据时代的到来,人们对数据资源的需求越来越多, ...
python爬虫程序-Python网络爬虫实战(一)快速入门
本系列从零开始阐述如何编写Python网络爬虫,以及网络爬虫中容易遇到的问题,比如具有反爬,加密的网站,还有爬虫拿不到数据,以及登录验证等问题,会伴随大量网站的爬虫实战来进行. 我们编写网络爬虫最主要 ...
精通python网络爬虫-精通Python网络爬虫 PDF 高清版
给大家带来的一篇关于Python爬虫相关的电子书资源,介绍了关于Python.网络爬虫.核心技术.框架.项目实战方面的内容,本书是由机械工业出版社出版,格式为PDF,资源大小108.6 MB,韦玮编写 ...

python网络爬虫一

python网络爬虫一相关推荐

最新文章

热门文章