爬虫学习第四天，URL中的urlparse玉urlunparse

URL

urlparse

urllib.parse.urlparse(urlstring,scheme=’’,allow_fragments=True)

from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html;uesr?id=5#comment')
print(type(result),result)

from urllib.parse import urlparse
result = urlparse('www.baidu.com/index.html;uesr?id=5#comment',scheme='https')
print(result)```


```javascript
from urllib.parse import urlparse

result = urlparse('http://www.baidu.com/index.html;uesr?id=5#comment',scheme='https')
print(result)

from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html;uesr?id=5#comment',allow_fragments=False)
print(result)

from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html#comment',allow_fragments=False)
print(result)

urlunparse

from urllib.parse import urlunparse

data = ['http','www.baidu.com','index.html','user','a=6','comment']
print(urlunparse(data))

urljoin

from urllib.parse import urljoin

print(urljoin('http://www.baidu.com','FAQ.html'))
print(urljoin('http://www.baidu.com','https://cuiqingcai.com/FAQ.html'))
print(urljoin('http://www.baidu.com/about.html','https://cuiqingcai.com/FAQ.html'))
print(urljoin('http://www.baidu.com/about.html','https://cuiqingcai.com/FAQ.html?question=2'))
print(urljoin('http://www.baidu.com?wd=abc','https://cuiqingcai.com/index.php'))
print(urljoin('http://www.baidu.com','?category=2#comment'))
print(urljoin('www.baidu.com','?category=2#comment'))
print(urljoin('www.baidu.com#comment','?category=2'))

urlencode

from urllib.parse import urlencode

params = {
    'name':'germey',
    'age': 22
}
base_url = 'http://www.baidu.com?'
url = base_url + urlencode(params)
print(url)