Python爬取大量數據時防止被封IP
阿新 • • 發佈:2018-02-08
ble tree user range ask ron 都沒有 進一步 pri 繼續老套路,這兩天我爬取了豬八戒上的一些數據 網址是:
http://task.zbj.com/t-ppsj/p1s5.html
,可能是由於爬取的數據量有點多吧,結果我的IP被封了,需要自己手動來驗證解封ip,但這顯然阻止了我爬取更多的數據了。
下面是我寫的爬取豬八戒的被封IP的代碼
# coding=utf-8 import requests from lxml import etree def getUrl(): for i in range(33): url = ‘http://task.zbj.com/t-ppsj/p{}s5.html‘.format(i+1) spiderPage(url) def spiderPage(url): if url is None: return None htmlText = requests.get(url).text selector = etree.HTML(htmlText) tds = selector.xpath(‘//*[@class="tab-switch tab-progress"]/table/tr‘) try: for td in tds: price = td.xpath(‘./td/p/em/text()‘) href = td.xpath(‘./td/p/a/@href‘) title = td.xpath(‘./td/p/a/text()‘) subTitle = td.xpath(‘./td/p/text()‘) deadline = td.xpath(‘./td/span/text()‘) price = price[0] if len(price)>0 else ‘‘ # python的三目運算 :為真時的結果 if 判定條件 else 為假時的結果 title = title[0] if len(title)>0 else ‘‘ href = href[0] if len(href)>0 else ‘‘ subTitle = subTitle[0] if len(subTitle)>0 else ‘‘ deadline = deadline[0] if len(deadline)>0 else ‘‘ print price,title,href,subTitle,deadline print ‘---------------------------------------------------------------------------------------‘ spiderDetail(href) except: print ‘出錯‘ def spiderDetail(url): if url is None: return None try: htmlText = requests.get(url).text selector = etree.HTML(htmlText) aboutHref = selector.xpath(‘//*[@id="utopia_widget_10"]/div[1]/div/div/div/p[1]/a/@href‘) price = selector.xpath(‘//*[@id="utopia_widget_10"]/div[1]/div/div/div/p[1]/text()‘) title = selector.xpath(‘//*[@id="utopia_widget_10"]/div[1]/div/div/h2/text()‘) contentDetail = selector.xpath(‘//*[@id="utopia_widget_10"]/div[2]/div/div[1]/div[1]/text()‘) publishDate = selector.xpath(‘//*[@id="utopia_widget_10"]/div[2]/div/div[1]/p/text()‘) aboutHref = aboutHref[0] if len(aboutHref) > 0 else ‘‘ # python的三目運算 :為真時的結果 if 判定條件 else 為假時的結果 price = price[0] if len(price) > 0 else ‘‘ title = title[0] if len(title) > 0 else ‘‘ contentDetail = contentDetail[0] if len(contentDetail) > 0 else ‘‘ publishDate = publishDate[0] if len(publishDate) > 0 else ‘‘ print aboutHref,price,title,contentDetail,publishDate except: print ‘出錯‘ if ‘_main_‘: getUrl()
我發現代碼運行完後,後面有幾頁數據沒有被爬取,我再也沒有辦法去訪問豬八戒網站了,等過了一段時間才能去訪問他們的網站,這就很尷尬了,我得防止被封IP
如何防止爬取數據的時候被網站封IP這裏有一些套路.查了一些套路
1.修改請求頭
之前的爬蟲代碼沒有添加頭部,這裏我添加了頭部,模擬成瀏覽器去訪問網站
user_agent = ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.104 Safari/537.36 Core/1.53.4295.400‘ headers = {‘User-Agent‘: user_agent} htmlText = requests.get(url, headers=headers, proxies=proxies).text
2.采用代理IP
當自己的ip被網站封了之後,只能采用代理ip的方式進行爬取,所以每次爬取的時候盡量用代理ip來爬取,封了代理還有代理。
這裏我引用了這個博客的一段代碼來生成ip地址:http://blog.csdn.net/lammonpeter/article/details/52917264
生成代理ip,大家可以直接把這個代碼拿去用
# coding=utf-8 # IP地址取自國內髙匿代理IP網站:http://www.xicidaili.com/nn/ # 僅僅爬取首頁IP地址就足夠一般使用 from bs4 import BeautifulSoup import requests import random def get_ip_list(url, headers): web_data = requests.get(url, headers=headers) soup = BeautifulSoup(web_data.text, ‘lxml‘) ips = soup.find_all(‘tr‘) ip_list = [] for i in range(1, len(ips)): ip_info = ips[i] tds = ip_info.find_all(‘td‘) ip_list.append(tds[1].text + ‘:‘ + tds[2].text) return ip_list def get_random_ip(ip_list): proxy_list = [] for ip in ip_list: proxy_list.append(‘http://‘ + ip) proxy_ip = random.choice(proxy_list) proxies = {‘http‘: proxy_ip} return proxies if __name__ == ‘__main__‘: url = ‘http://www.xicidaili.com/nn/‘ headers = { ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36‘ } ip_list = get_ip_list(url, headers=headers) proxies = get_random_ip(ip_list) print(proxies)
好了我用上面的代碼給我生成了一批ip地址(有些ip地址可能無效,但只要不封我自己的ip就可以了,哈哈),然後我就可以在我的請求頭部添加ip地址
給我們的請求添加代理ip
proxies = {
‘http‘: ‘http://124.72.109.183:8118‘,
‘http‘: ‘http://49.85.1.79:31666‘
}
user_agent = ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.104 Safari/537.36 Core/1.53.4295.400‘
headers = {‘User-Agent‘: user_agent}
htmlText = requests.get(url, headers=headers, timeout=3, proxies=proxies).text
目前知道的就
最後完整代碼如下:
# coding=utf-8
import requests
import time
from lxml import etree
def getUrl():
for i in range(33):
url = ‘http://task.zbj.com/t-ppsj/p{}s5.html‘.format(i+1)
spiderPage(url)
def spiderPage(url):
if url is None:
return None
try:
proxies = {
‘http‘: ‘http://221.202.248.52:80‘,
}
user_agent = ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.104 Safari/537.36 Core/1.53.4295.400‘
headers = {‘User-Agent‘: user_agent}
htmlText = requests.get(url, headers=headers,proxies=proxies).text
selector = etree.HTML(htmlText)
tds = selector.xpath(‘//*[@class="tab-switch tab-progress"]/table/tr‘)
for td in tds:
price = td.xpath(‘./td/p/em/text()‘)
href = td.xpath(‘./td/p/a/@href‘)
title = td.xpath(‘./td/p/a/text()‘)
subTitle = td.xpath(‘./td/p/text()‘)
deadline = td.xpath(‘./td/span/text()‘)
price = price[0] if len(price)>0 else ‘‘ # python的三目運算 :為真時的結果 if 判定條件 else 為假時的結果
title = title[0] if len(title)>0 else ‘‘
href = href[0] if len(href)>0 else ‘‘
subTitle = subTitle[0] if len(subTitle)>0 else ‘‘
deadline = deadline[0] if len(deadline)>0 else ‘‘
print price,title,href,subTitle,deadline
print ‘---------------------------------------------------------------------------------------‘
spiderDetail(href)
except Exception,e:
print ‘出錯‘,e.message
def spiderDetail(url):
if url is None:
return None
try:
htmlText = requests.get(url).text
selector = etree.HTML(htmlText)
aboutHref = selector.xpath(‘//*[@id="utopia_widget_10"]/div[1]/div/div/div/p[1]/a/@href‘)
price = selector.xpath(‘//*[@id="utopia_widget_10"]/div[1]/div/div/div/p[1]/text()‘)
title = selector.xpath(‘//*[@id="utopia_widget_10"]/div[1]/div/div/h2/text()‘)
contentDetail = selector.xpath(‘//*[@id="utopia_widget_10"]/div[2]/div/div[1]/div[1]/text()‘)
publishDate = selector.xpath(‘//*[@id="utopia_widget_10"]/div[2]/div/div[1]/p/text()‘)
aboutHref = aboutHref[0] if len(aboutHref) > 0 else ‘‘ # python的三目運算 :為真時的結果 if 判定條件 else 為假時的結果
price = price[0] if len(price) > 0 else ‘‘
title = title[0] if len(title) > 0 else ‘‘
contentDetail = contentDetail[0] if len(contentDetail) > 0 else ‘‘
publishDate = publishDate[0] if len(publishDate) > 0 else ‘‘
print aboutHref,price,title,contentDetail,publishDate
except:
print ‘出錯‘
if ‘_main_‘:
getUrl()
最後程序完美運行,再也沒有出現被封IP的情況。當然防止被封IP肯定不止這些了,這還需要進一步探索!
最後
當然數據我是已經抓取過來了,但是我的數據都沒有完美呈現出來,我應該寫入execl文件,或者數據庫中啊,這樣才能方便采用.所以接下來我準備了使用
Python操作execl,mysql,mongoDB
Python爬取大量數據時防止被封IP