python學習1：urllib

打印指定網頁數據

s = urllib.urlopen("http://www.sina.com")
for i in range(10):
    print("line %d: %s " % (i + 1, s.readline()))

輸出列表

def print_list(list):
for i in list:
    print(i)

打印所有行

lists = s.readlines()
    print_list(lists)
    print(s.getcode())

下載數據（帶進度條）

def retrieve():
    fname, msg = urllib.urlretrieve("http://www.sina.com", "index.html", reporthook=progress)
    print(fname)
    print_list(msg.items())

def progress(blk, blk_size, total_size):
    print("%d/%d - %.02f%%" % (blk * blk_size, total_size, (float)(blk * blk_size) * 100 / total_size))

編碼成URL

def urlencode():
    params = {"score": 100, "name": "爬蟲", "comment": "very good"}
    qs = urllib.urlencode(params)
    print(qs)

URL解碼成數據

import urlparse
def parse_qs():
    url = "https://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=0&rsv_idx=1&tn=baidu&wd=python&rsv_pq=a1a3e55800046021&rsv_t=3bcfmLc%2Fd4M1X4qWGjXjGFAEJByJA1q92Gki%2BNMAgWdmrg8xcfkWgJM6t74&rsv_enter=1&rsv_sug3=9&rsv_sug1=7&rsv_sug7=100&rsv_sug2=0&inputT=7085&rsv_sug4=7123"
    result = urlparse.urlparse(url)
    print(result)
    params = urlparse.parse_qs(result.query)
    print(params)