Skip to content

Commit 8ffd4d3

Browse files
committed
add python_spider
1 parent 739349c commit 8ffd4d3

File tree

2 files changed

+89
-0
lines changed

2 files changed

+89
-0
lines changed

README.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -4,3 +4,5 @@
44
### python_base.py: 千行代码入门Python
55

66
### python_visual.py: 15张图入门Matplotlib
7+
8+
### python_spider.py: 一个很“水”的Python爬虫入门代码文件

python_spider.py

Lines changed: 87 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,87 @@
1+
# _*_ coding: utf-8 _*_
2+
3+
"""
4+
python_spider.py by xianhu
5+
"""
6+
7+
import urllib.error
8+
import urllib.parse
9+
import urllib.request
10+
import http.cookiejar
11+
12+
13+
# 最简单的方式
14+
response = urllib.request.urlopen("http://www.baidu.com", timeout=10)
15+
html = response.read().decode("utf-8")
16+
17+
18+
# 使用Request类
19+
request = urllib.request.Request("http://www.baidu.com/")
20+
response = urllib.request.urlopen(request, timeout=10)
21+
22+
23+
# 发送数据,即在urlopen()或者Request()中添加data参数
24+
url = "http://localhost/login.php"
25+
data = urllib.parse.urlencode({"act": "login", "email": "xianhu@qq.com", "password": "123456"})
26+
request1 = urllib.request.Request(url, data)# POST方法
27+
request2 = urllib.request.Request(url + "?%s" % data) # GET方法
28+
response = urllib.request.urlopen(request, timeout=10)
29+
30+
31+
# 发送Header,即在urlopen()或者Request()中添加headers参数
32+
headers = {"User-Agent": "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)"}
33+
request = urllib.request.Request(url, data=data, headers=headers) # 参数中添加header参数
34+
request.add_header("Referer", "http://www.baidu.com") # add_header函数,另一种添加header的方法
35+
response = urllib.request.urlopen(request, timeout=10)
36+
37+
38+
# 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
39+
headers = {"Referer": "http://www.baidu.com/"}
40+
41+
42+
# 引发异常:urllib.error.HTTPError, urllib.error.URLError, 两者存在继承关系
43+
try:
44+
urllib.request.urlopen(request, timeout=10)
45+
except urllib.error.HTTPError as e:
46+
print(e.code, e.reason)
47+
48+
49+
# 使用代理,以防止IP被封或IP次数受限:
50+
proxy = urllib.request.ProxyHandler({"http": "111.123.76.12:8080"})
51+
52+
opener = urllib.request.build_opener(proxy)# 利用代理创建opener实例(OpenerDirector实例)
53+
response = opener.open("https://www.baidu.com/")# 直接利用opener实例打开url
54+
55+
urllib.request.install_opener(opener)# 安装、设置全局的opener,然后利用urlopen打开url
56+
response = urllib.request.urlopen("https://www.baidu.com/")
57+
58+
59+
# 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。
60+
url = "http://ww3.sinaimg.cn/large/7d742c99tw1ee7dac2766j204q04qmxq.jpg"
61+
response = urllib.request.urlopen(url, timeout=120)
62+
with open("test.jpg", "wb") as file_img:
63+
file_img.write(response.read())
64+
65+
66+
# 使用cookie和cookiejar
67+
cookie_jar = http.cookiejar.CookieJar()
68+
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cookiejar=cookie_jar))
69+
response = opener.open("https://www.baidu.com/")
70+
for cookie in cookie_jar:
71+
print(cookie)
72+
73+
74+
# 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
75+
headers = {"User-Agent": "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)",
76+
"Cookie": "PHPSESSID=btqkg9amjrtoeev8coq0m78396; USERINFO=n6nxTHTY%2BJA39z6CpNB4eKN8f0KsYLjAQTwPe%2BhLHLruEbjaeh4ulhWAS5RysUM%2B; "}
77+
request = urllib.request.Request(url, headers=headers)
78+
79+
cookie = http.cookiejar.Cookie(name="xx", value="xx", domain="xx")
80+
cookie_jar.set_cookie(cookie)
81+
response = opener.open("https://www.baidu.com/")
82+
83+
84+
# 同时使用代理和cookiejar
85+
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cookiejar=cookie_jar))
86+
opener.add_handler(urllib.request.ProxyHandler(proxies={"http": "http://www.example.com:8888/"}))
87+
response = opener.open("https://www.baidu.com/")

0 commit comments

Comments
 (0)