1.京东商品页面的爬取
https://item.jd.com/14815925977.html
>>> import requests
>>> r = request.get('https://item.jd.com/14815925977.html')
>>> r.encoding
'gbk'
>>> r.text[:1000]
'<!DOCTYPE HTML>\n<html lang="zh-CN">\n<head>\n <!-- shouji -->\n <meta http-equiv="Content-Type" content="text/html; charset=gbk" />\n <title>安佳脱脂牛奶 新西兰进口轻欣脱脂250ml*24整箱装【图片 价格 品牌 报价】-京东</title>\n <meta name="keywords" content="安佳脱脂牛奶 新西兰进口轻欣脱脂250ml*24整箱装,安佳（Anchor）,,京东,网上购物"/>\n <meta name="description" content="安佳脱脂牛奶 新西兰进口轻欣脱脂250ml*24整箱装图片、价格、品牌样样齐全！【京东正品行货，全国 配送，心动不如行动，立即购买享受更多优惠哦！】" />\n <meta name="format-detection" content="telephone=no">\n <meta http-equiv="mobile-agent" content="format=xhtml; url=//item.m.jd.com/product/14815925977.html">\n <meta http-equiv="mobile-agent" content="format=html5; url=//item.m.jd.com/product/14815925977.html">\n <meta http-equiv="X-UA-Compatible" content="IE=Edge">\n <link rel="canonical" href="//item.jd.com/14815925977.html"/>\n <link rel="dns-prefetch" href="//misc.360buyimg.com"/>\n <link rel="dns-prefetch" href="//static.360buyimg.com"/>\n <link rel="dns-prefetch" href="//img10.360buyimg.com"/>\n <link rel="dns-pre'全代码
import requests
url = 'https://item.jd.com/14815925977.html'
try:
r = requests.get(url)
r.raise_for_status()
r.encoding = r.apparent_encoding
print(r.text[:1000])
except:
print('爬取失败')2.亚马逊商品页面的爬取
https://www.amazon.cn/dp/B01ION3VWI
>>> import requests
>>> r = requests.get('https://www.amazon.cn/dp/B01ION3VWI')
>>> r.stauts_code
503
>>> r.encoding
'ISO-8859-1'
>>> r.encoding = r.apparent_encoding
>>> r.text
'<!DOCTYPE html>\n<!--[if lt IE 7]> <html lang="zh-CN" class="a-no-js a-lt-ie9 a-lt-ie8 a-lt-ie7"> <![endif]-->\n<!--[if IE 7]> <html lang="zh-CN" class="a-no-js a-lt-ie9 a-lt-ie8"> <![endif]-->\n<!--[if IE 8]> <html lang="zh-CN" class="a-no-js a-lt-ie9"> <![endif]-->\n<!--[if gt IE 8]><!-->\n<html class="a-no-js" lang="zh-CN"><!--<![endif]--><head>\n<meta http-equiv="content-type" content="text/html; charset=UTF-8">\n<meta charset="utf-8">\n<meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1">\n<title dir="ltr">Amazon CAPTCHA</title>\n<meta name="viewport" content="width=device-width">\n<link rel="stylesheet" href="https://images-na.ssl-images-amazon.com/images/G/01/AUIClients/AmazonUI-3c913031596ca78a3768f4e934b1cc02ce238101.secure.min._V1_.css">\n<script>\n\nif (true === true) {\n var ue_t0 = (+ new Date()),\n ue_csm = window,\n ue = { t0: ue_t0, d: function() { return (+new Date() - ue_t0); } },\n ue_furl = "fls-cn.amazon.cn",\n ue_mid = "AAHKV2X7AFYLW",\n ue_sid = (document.cookie.match(/session-id=([0-9-]+)/) || [])[1],\n ue_sn = "opfcaptcha.amazon.cn",\n ue_id = \'WHD3D9ZKD1CAMR1ZBMA9\';\n}\n</script>\n</head>\n<body>\n\n<!--\n To discuss automated access to Amazon data please contact api-services-support@amazon.com.\n For information about migrating to our APIs refer to our Marketplace APIs at https://developer.amazonservices.com.cn/index.html/ref=rm_c_sv, or our Product Advertising API at https://associates.amazon.cn/gp/advertising/api/detail/main.html/ref=rm_c_ac for advertising use cases.\n-->\n\n<!--\nCorreios.DoNotSend\n-->\n\n<div class="a-container a-padding-double-large" style="min-width:350px;padding:44px 0 !important">\n\n <div class="a-row a-spacing-double-large" style="width: 350px; margin: 0 auto">\n\n <div class="a-row a-spacing-medium a-text-center"><i class="a-icon a-logo"></i></div>\n\n <div class="a-box a-alert a-alert-info a-spacing-base">\n <div class="a-box-inner">\n <i class="a-icon a-icon-alert"></i>\n <h4>请输入您在下方看到的字符</h4>\n <p class="a-last">抱歉，我们只是想确认一下当前访问者并非自动程序。为了达到最佳效果，请确保您浏览器上的 Cookie 已启用。</p>\n </div>\n </div>\n\n <div class="a-section">\n\n <div class="a-box a-color-offset-background">\n <div class="a-box-inner a-padding-extra-large">\n\n <form method="get" action="/errors/validateCaptcha" name="">\n <input type=hidden name="amzn" value="Ds6Fb8xSEP8SX63xhhDPcw==" /><input type=hidden name="amzn-r" value="/dp/B01ION3VWI" />\n <div class="a-row a-spacing-large">\n <div class="a-box">\n <div class="a-box-inner">\n <h4>请输入您在这个图片中看到 的字符：</h4>\n <div class="a-row a-text-center">\n <img src="https://images-na.ssl-images-amazon.com/captcha/qujzzelu/Captcha_jtbnpmutnr.jpg">\n </div>\n <div class="a-row a-spacing-base">\n <div class="a-row">\n <div class="a-column a-span6">\n <label for="captchacharacters">输入字符</label>\n </div>\n <div class="a-column a-span6 a-span-last a-text-right">\n <a onclick="window.location.reload()">换一张图</a>\n </div>\n </div>\n <input autocomplete="off" spellcheck="false" id="captchacharacters" name="field-keywords" class="a-span12" autocapitalize="off" autocorrect="off" type="text">\n </div>\n </div>\n </div>\n </div>\n\n <div class="a-section a-spacing-extra-large">\n\n <div class="a-row">\n <span class="a-button a-button-primary a-span12">\n <span class="a-button-inner">\n <button type="submit" class="a-button-text">继续购物</button>\n </span>\n </span>\n </div>\n\n </div>\n </form>\n\n </div>\n </div>\n\n </div>\n\n </div>\n\n <div class="a-divider a-divider-section"><div class="a-divider-inner"></div></div>\n\n <div class="a-text-center a-spacing-small a-size-mini">\n <a href="https://www.amazon.cn/gp/help/customer/display.html/ref=footer_claim?ie=UTF8&nodeId=200347160">使用条件</a>\n <span class="a-letter-space"></span>\n <span class="a-letter-space"></span>\n <span class="a-letter-space"></span>\n <span class="a-letter-space"></span>\n <a href="https://www.amazon.cn/gp/help/customer/display.html/ref=footer_privacy?ie=UTF8&nodeId=200347130">隐私声明</a>\n </div>\n\n <div class="a-text-center a-size-mini a-color-secondary">\n © 1996-2015, Amazon.com, Inc. or its affiliates\n <script>\n if (true === true) {\n document.write(\'<img src="https://fls-cn.amaz\'+\'on.cn/\'+\'1/oc-csi/1/OP/requestId=WHD3D9ZKD1CAMR1ZBMA9&js=1" />\');\n };\n </script>\n <noscript>\n <img src="https://fls-cn.amazon.cn/1/oc-csi/1/OP/requestId=WHD3D9ZKD1CAMR1ZBMA9&js=0" />\n </noscript>\n </div>\n </div>\n <script>\n if (true === true) {\n var elem = document.createElement("script");\n elem.src = "https://images-cn.ssl-images-amazon.com/images/G/01/csminstrumentation/csm-captcha-instrumentation.min._V" + (+ new Date()) + "_.js";\n document.getElementsByTagName(\'head\')[0].appendChild(elem);\n }\n </script>\n</body></html>\n'HTTP状态码是503，有可能是服务器拒绝我们的python爬虫访问，因为python爬虫进行访问服务器端资源的时候提交的HTTP头是python的，不是我们平常上网用的，很多网站的反爬虫机制也是这样，检测来源是否为爬虫，就看HTTP头，我使用chrome浏览器访问一下这个网站，看HTTP头是什么样的
我们再看一下python提交request的headers
>>> r.reuqest.headers
{'User-Agent': 'python-requests/2.20.0', 'Accept-Encoding': 'gzip, deflate', 'Accept': '*/*', 'Connection': 'keep-alive'}这就很明显了，User-Agent这个字段就暴露了我们的身份，所以我们要自己构造请求头，然后再去访问
全代码
import requests
url = 'https://www.amazon.cn/dp/B01ION3VWI'
try:
kv = {}
kv['user-agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36' #http头大小写不敏感
kv['accept'] = 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8'
kv['Connection'] = 'keep-alive'
kv['Upgrade-Insecure-Requests'] = '1'
r = requests.get(url,headers = kv)
r.raise_for_status()
r.encoding = r.apparent_encoding
print(r.text[850000:851000])
except:
print('爬取失败')3.百度/360搜索
搜索引擎关键词提交的接口：
百度的关键词接口：
- http://www.baidu.com/s?wd=keyword
360的关键词接口：
- http://www.so.com/s?q=keyword
>>> import requests
>>> kv = {'wd':'Python'}
>>> r = requests.get('http://www.baidu.com/s',params = kv)
>>> r.status_code
200
>>> r.request.url
'http://www,baidu.com/s?wd=Python'
>>> len(r.text)
417452百度搜索全代码
import requests
keyword = 'Python'
try:
kv = {'wd':keyword}
url = 'http://www.baidu.com/s'
r = requests.get(url,params = kv)
r.raise_for_status()
r.encoding = r.apparent_encoding
print(r.text[300000:301000])
except:
print('爬取失败')360搜索全代码
import requests
keyword = 'Python'
try:
kv = {'q':keyword}
url = 'http://www.so.com/s'
r = requests.get(url,params = kv)
r.raise_for_status()
#r.encoding = r.apparent_encoding
print(len(r.text))
except:
print('爬取失败')4.网络图片的爬取和存储
网络图片链接的格式：
http://www.example.com/picture.jpg
国家地理：http://www.ngchina.com.cn/
选择一个图片Web页面：
http://www.ngchina.com.cn/photography/picture_story/4836.html
图片地址：http://image.nationalgeographic.com.cn/2017/1121/20171121023827440.jpg
>>> import requests
>>> path = "D://test.jpg"
>>> url = "http://image.nationalgeographic.com.cn/2017/1121/20171121023827440.jpg"
>>> r = requests.get(url)
>>> r.status_code
200
>>> f = open(path,'wb')
>>> f.write(r.content)
237661
>>> f.close()图片爬取全代码
import requests
import os
url = "http://image.nationalgeographic.com.cn/2017/1121/20171121023827440.jpg"
root = "D://pics//"
path = root + url.split('/')[-1]
try:
if not os.path.exists(root):
os.mkdir(root)
if not os.path.exists(path):
r = requests.get(url)
with open(path,'wb') as f:
f.write(r.content)
f.close()
print("文件保存成功")
else:
print("文件已经存在")
except:
print("爬取失败")5.IP地址归属地自动查询
>>> import requests
>>> url = "http://m.ip138.com/ip.asp?ip="
>>> r = requests.get(url + "202.204.80.112")
>>> r.status_code
200
>>> r.text[-500:]
'value="查询" class="form-btn" />\r\n\t\t\t\t\t</form>\r\n\t\t\t\t</div>\r\n\t\t\t\t<div class="query-hd">ip138.com IP查询(搜索IP地址的地理位置)</div>\r\n\t\t\t\t<h1 class="query">您查询的IP：202.204.80.112</h1><p class="result">本站主数据：北京市海淀 区 北京理工大学 教育网</p><p class="result">参考数据一：北京市 北京理工大学</p>\r\n\r\n\t\t\t</div>\r\n\t\t</div>\r\n\r\n\t\t<div class="footer">\r\n\t\t\t<a href="http://www.miitbeian.gov.cn/" rel="nofollow" target="_blank">沪ICP备10013467号-1</a>\r\n\t\t</div>\r\n\t</div>\r\n\r\n\t<script type="text/javascript" src="/script/common.js"></script></body>\r\n</html>\r\n'IP地址查询全代码
import requests
url = "http://m.ip138.com/ip.asp?ip="
try:
r = requests.get(url + "202.204.80.112")
r.raise_for_status()
r.encoding = r.apparent_encoding
print(r.text[-500:])
except:
print("爬取失败")
