爬蟲請求urllib. parse模塊你知多少

from urllib import parse as p
import urllib.request

def use_urlparse(url):
    # 1、urlparse(url=,scheme=,allow_fragments=) url識別和分段
    # scheme 當url不含有協議時生效
    result = p.urlparse(url=url)
    print("協議："+result[0])
    print("域名："+result[1])
    print("訪問路徑："+result[2])
    print("參數："+result[3])
    print("查詢條件："+result[4])

    # 2、urlunparse() url合成
    data=[]
    for i in range(len(result)):
        data.append(result[i])
    print(p.urlunparse(data))

def use_urlsplit(url):
    # 3、urlsplit() 與urlparse類似將param和path和並了
    data_url = p.urlsplit(url=url)
    print(data_url)

    # 4、urlunsplit() 與urlunparse()類似
    print(p.urlunsplit(data_url))

# 5、urljoin 鏈接合成 第一個參數爲基礎鏈接，第二個參數爲基礎鏈接
def use_urljoin():
    # 分析基礎鏈接，並對新連接缺失部分盡心補充
    print(p.urljoin('http://www.baidu.com', 'FAQ.html '))
    print(p.urljoin('http://www.baidu.com ', 'https://cuiqingcai.com/FAQ.html'))
    print(p.urljoin ('http://www.baidu.com/about.html', 'https://www.cuiqingcai.com/FAQ.html'))
    print(p.urljoin('http://www.baidu.com/about.html','https://cuiqingcai.com/FAQ.html?question=2'))

# 6、urlencode 字典轉請求參數
def use_urlopen_data():
    url = "http://www.baidu.com"
    # urlopen data 參數
    data={
        'wd':'csdn'
    }
    # 格式化參數
    # 將參數字典轉化爲字符串
    form_data = p.urlencode(data).encode()
    response = urllib.request.urlopen(url=url,data=form_data)
    print(response.read())

# 7、將請求參數化成字典或元組
def use_parse_qs_qsl(query):
    # 返回字典
    print(p.parse_qs(query))
    # 返回元組
    print(p.parse_qsl(query))

# 8、quote 中文參數編碼與解碼
def use_quote(word):
    # URL編碼
    url = 'https://www.baidu.com/s?wd='+p.quote(word)
    print(url)
    # URL解碼
    print(p.unquote(url))

if __name__ == '__main__':
    url = 'https://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=1&rsv_idx=1&tn=baidu&wd=%E6%83%85%E6%AD%8C&oq=yue&rsv_pq=dacbcb5f00043218&rsv_t=fae8tkAseCzI6Y%2FJ3EvIm%2BG4Zy1%2BnWO3oZ%2BaCJXmJwazl7yBr48QuZswiF4&rqlang=cn&rsv_enter=1&rsv_dl=tb&inputT=1744&rsv_sug3=11&rsv_sug1=6&rsv_sug7=100&rsv_sug2=0&rsv_sug4=1744'
    query = 'ie=utf-8&f=8&rsv_bp=1&rsv_idx=1&tn=baidu&wd=%E6%83%85%E6%AD%8C&oq=yue&rsv_pq=dacbcb5f00043218&rsv_t=fae8tkAseCzI6Y%2FJ3EvIm%2BG4Zy1%2BnWO3oZ%2BaCJXmJwazl7yBr48QuZswiF4&rqlang=cn&rsv_enter=1&rsv_dl=tb&inputT=1744&rsv_sug3=11&rsv_sug1=6&rsv_sug7=100&rsv_sug2=0&rsv_sug4=1744'
    use_urlparse(url)
    use_urlsplit(url)
    use_urljoin()
    use_urlopen_data()
    use_parse_qs_qsl(query)
    use_quote('魏振東')