update code in python_spider

master
xianhu 2016-10-16 20:26:43 +08:00
parent 54a152483b
commit 8be49fcbfd
2 changed files with 58 additions and 45 deletions

View File

@ -1,8 +1,12 @@
# LearnPython # LearnPython
以撸代码的形式学习Python 以撸代码的形式学习Python
============================================================
### python_base.py: 千行代码入门Python ### python_base.py: 千行代码入门Python
### python_visual.py: 15张图入门Matplotlib ### python_visual.py: 15张图入门Matplotlib
### python_spider.py: 一个很“水”的Python爬虫入门代码文件 ### python_spider.py: 一个很“水”的Python爬虫入门代码文件
============================================================
### 您可以fork该项目,并在修改后提交Pull request

View File

@ -9,79 +9,88 @@ import urllib.parse
import urllib.request import urllib.request
import http.cookiejar import http.cookiejar
# 首先定义下边可能需要的变量
url = "https://www.baidu.com"
headers = {"User-Agent": "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)"}
# 最简单的方式 # 最简单的网页抓取方式
response = urllib.request.urlopen("http://www.baidu.com", timeout=10) response = urllib.request.urlopen(url, timeout=10)
html = response.read().decode("utf-8") html = response.read().decode("utf-8")
# 使用Request # 使用Request实例代替url
request = urllib.request.Request("http://www.baidu.com/") request = urllib.request.Request(url, data=None, headers={})
response = urllib.request.urlopen(request, timeout=10) response = urllib.request.urlopen(request, timeout=10)
# 发送数据即在urlopen()或者Request()中添加data参数 # 发送数据即在Request()中添加data参数
url = "http://localhost/login.php"
data = urllib.parse.urlencode({"act": "login", "email": "xianhu@qq.com", "password": "123456"}) data = urllib.parse.urlencode({"act": "login", "email": "xianhu@qq.com", "password": "123456"})
request1 = urllib.request.Request(url, data) # POST方法 request1 = urllib.request.Request(url, data=data) # POST方法
request2 = urllib.request.Request(url + "?%s" % data) # GET方法 request2 = urllib.request.Request(url+"?%s" % data) # GET方法
response = urllib.request.urlopen(request, timeout=10) response = urllib.request.urlopen(request, timeout=10)
# 发送Header即在urlopen()或者Request()中添加headers参数 # 发送Header即在Request()中添加headers参数
headers = {"User-Agent": "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)"}
request = urllib.request.Request(url, data=data, headers=headers) # 参数中添加header参数 request = urllib.request.Request(url, data=data, headers=headers) # 参数中添加header参数
request.add_header("Referer", "http://www.baidu.com") # add_header函数另一种添加header的方法 request.add_header("Referer", "http://www.baidu.com") # 另一种添加header的方式,添加Referer是为了应对"反盗链"
response = urllib.request.urlopen(request, timeout=10) response = urllib.request.urlopen(request, timeout=10)
# 对付"反盗链"所谓的反盗链设置就是检查header里的referer站点是不是他自己。所以只需要像把headers的referer改成某个网站自己即可 # 网页抓取引发异常urllib.error.HTTPError, urllib.error.URLError, 两者存在继承关系
headers = {"Referer": "http://www.baidu.com/"}
# 引发异常urllib.error.HTTPError, urllib.error.URLError, 两者存在继承关系
try: try:
urllib.request.urlopen(request, timeout=10) urllib.request.urlopen(request, timeout=10)
except urllib.error.HTTPError as e: except urllib.error.HTTPError as e:
print(e.code, e.reason) print(e.code, e.reason)
except urllib.error.URLError as e:
print(e.errno, e.reason)
# 使用代理以防止IP被封或IP次数受限 # 使用代理以防止IP被封或IP次数受限
proxy = urllib.request.ProxyHandler({"http": "111.123.76.12:8080"}) proxy_handler = urllib.request.ProxyHandler(proxies={"http": "111.123.76.12:8080"})
opener = urllib.request.build_opener(proxy) # 利用代理创建opener实例OpenerDirector实例 opener = urllib.request.build_opener(proxy_handler) # 利用代理创建opener实例
response = opener.open("https://www.baidu.com/") # 直接利用opener实例打开url response = opener.open(url) # 直接利用opener实例打开url
urllib.request.install_opener(opener) # 安装、设置全局的opener然后利用urlopen打开url urllib.request.install_opener(opener) # 安装全局opener然后利用urlopen打开url
response = urllib.request.urlopen("https://www.baidu.com/") response = urllib.request.urlopen(url)
# 使用cookie和cookiejar,应对服务器检查
cookie_jar = http.cookiejar.CookieJar()
cookie_jar_handler = urllib.request.HTTPCookieProcessor(cookiejar=cookie_jar)
opener = urllib.request.build_opener(cookie_jar_handler)
response = opener.open(url)
# 发送在浏览器中获取的cookie,两种方式:
# (1)直接放到headers里
headers = {
"User-Agent": "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)",
"Cookie": "PHPSESSID=btqkg9amjrtoeev8coq0m78396; USERINFO=n6nxTHTY%2BJA39z6CpNB4eKN8f0KsYLjAQTwPe%2BhLHLruEbjaeh4ulhWAS5RysUM%2B; "
}
request = urllib.request.Request(url, headers=headers)
# (2)构建cookie,添加到cookiejar中
cookie = http.cookiejar.Cookie(name="xx", value="xx", domain="xx", ...)
cookie_jar.set_cookie(cookie)
response = opener.open(url)
# 同时使用代理和cookiejar
opener = urllib.request.build_opener(cookie_jar_handler)
opener.add_handler(proxy_handler)
response = opener.open("https://www.baidu.com/")
# 抓取网页中的图片:同样适用于抓取网络上的文件。右击鼠标,找到图片属性中的地址,然后进行保存。 # 抓取网页中的图片:同样适用于抓取网络上的文件。右击鼠标,找到图片属性中的地址,然后进行保存。
url = "http://ww3.sinaimg.cn/large/7d742c99tw1ee7dac2766j204q04qmxq.jpg" response = urllib.request.urlopen("http://ww3.sinaimg.cn/large/7d742c99tw1ee7dac2766j204q04qmxq.jpg", timeout=120)
response = urllib.request.urlopen(url, timeout=120)
with open("test.jpg", "wb") as file_img: with open("test.jpg", "wb") as file_img:
file_img.write(response.read()) file_img.write(response.read())
# 使用cookie和cookiejar # HTTP认证即HTTP身份验证
cookie_jar = http.cookiejar.CookieJar() password_mgr = urllib.request.HTTPPasswordMgrWithDefaultRealm() # 创建一个PasswordMgr
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cookiejar=cookie_jar)) password_mgr.add_password(realm=None, uri=url, user='username', passwd='password') # 添加用户名和密码
response = opener.open("https://www.baidu.com/") handler = urllib.request.HTTPBasicAuthHandler(password_mgr) # 创建HTTPBasicAuthHandler
for cookie in cookie_jar: opener = urllib.request.build_opener(handler) # 创建opner
print(cookie) response = opener.open(url, timeout=10) # 获取数据
# 发送在浏览器中获取的cookie,两种方式:(1)直接放到headers里,(2)构建cookie,添加到cookiejar中
headers = {"User-Agent": "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)",
"Cookie": "PHPSESSID=btqkg9amjrtoeev8coq0m78396; USERINFO=n6nxTHTY%2BJA39z6CpNB4eKN8f0KsYLjAQTwPe%2BhLHLruEbjaeh4ulhWAS5RysUM%2B; "}
request = urllib.request.Request(url, headers=headers)
cookie = http.cookiejar.Cookie(name="xx", value="xx", domain="xx")
cookie_jar.set_cookie(cookie)
response = opener.open("https://www.baidu.com/")
# 同时使用代理和cookiejar
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cookiejar=cookie_jar))
opener.add_handler(urllib.request.ProxyHandler(proxies={"http": "http://www.example.com:8888/"}))
response = opener.open("https://www.baidu.com/")