from urllib import request
import re

url = "http://www.baidu.com"
result = request.urlopen(url)
# 打印状态码
print(result.code)

# 快速爬取网页的三种方法
# 爬到内存中（方法1）
data1 = result.read().decode("utf-8", "ignore")
print(data1)

# 爬到内存中（方法2）
data2 = request.urlopen(request.Request(url)).read().decode("utf-8", "ignore")
print(data2)

# 保存到硬盘
request.urlretrieve(url, filename="C:/baidu.html")

# 循环爬取慕课网页面数据
for i in range(100, 200):
    url = "https://coding.imooc.com/class/" + str(i) + ".html"
    data = request.urlopen(url).read().decode("utf-8", "ignore")
    title = '<h1>(.*?)</h1>'
    price = '<div class="cur-price">￥(.*?)</div>'
    title_result = re.compile(title, re.S).findall(data)
    price_result = re.compile(price, re.S).findall(data)
    if len(title_result) > 0:
        print(title_result[0])
    else:
        continue
    if len(price_result) > 0:
        print(price_result[0])
    else:
        print("免费")
    print("------------------------")