import requests
1. 方法
requests.get
requests.post
requests.put
requests.delete
...
requests.request(method='POST')
2. 參數
2.1 url
2.2 headers
2.3 cookies
2.4 params
2.5 data，傳請求體
requests.post(
....
date = {'user':'mouni','pwd':'123'}
)
顯示會以這種形式顯示
GET /index http1.1\r\nhost:c1.com\r\n\r\nuser=mouni&pwd=123
2.6 json，傳請求體
requests.post(
...,
json={'user':'alex','pwd':'123'}
)
顯示會以這種形式顯示
GET /index http1.1\r\nhost:c1.com\r\nContent-Type:application/json\r\n\r\n{"user":"mouni","pwd":123}
2.7 代理 proxies
# 無驗證
proxie_dict = {
"http": "61.172.249.96:80",
"https": "http://61.185.219.126:3128",
}
ret = requests.get("https://www.proxy360.cn/Proxy", proxies=proxie_dict)
# 驗證代理
from requests.auth import HTTPProxyAuth
proxyDict = {
'http': '77.75.105.165',
'https': '77.75.106.165'
}
auth = HTTPProxyAuth('用戶名', '密碼')
r = requests.get("http://www.google.com",data={'xxx':'ffff'} proxies=proxyDict, auth=auth)
print(r.text)
-----------------------------------------------------------------------------------------
2.8 文件上傳 files
# 發送文件
file_dict = {
'f1': open('xxxx.log', 'rb')
}
requests.request(
method='POST',
url='http://127.0.0.1:8000/test/',
files=file_dict
)
2.9 認證 auth
內部：
用戶名和密碼，用戶和密碼加密，放在請求頭中傳給後臺。
- "用戶:密碼"
- base64("用戶:密碼")
- "Basic base64("用戶|密碼")"
- 請求頭：
Authorization： "basic base64("用戶|密碼")"
from requests.auth import HTTPBasicAuth, HTTPDigestAuth
ret = requests.get('https://api.github.com/user', auth=HTTPBasicAuth('wupeiqi', 'sdfasdfasdf'))
print(ret.text)
2.10 超時 timeout
# ret = requests.get('http://google.com/', timeout=1)
# print(ret)
# ret = requests.get('http://google.com/', timeout=(5, 1))
# print(ret)
2.11 允許重定向 allow_redirects
ret = requests.get('http://127.0.0.1:8000/test/', allow_redirects=False)
print(ret.text)
2.12 大文件下載 stream
from contextlib import closing
with closing(requests.get('http://httpbin.org/get', stream=True)) as r1:
# 在此處理響應。
for i in r1.iter_content():
print(i)
2.13 證書 cert
- 百度、騰訊 => 不用攜帶證書（系統幫你做了）
- 自定義證書
requests.get('http://127.0.0.1:8000/test/', cert="xxxx/xxx/xxx.pem")
requests.get('http://127.0.0.1:8000/test/', cert=("xxxx/xxx/xxx.pem","xxx.xxx.xx.key"))
2.14 確認 verify =False
BeautifulSoup
是一個模塊，該模塊用於接收一個HTML或XML字符串，然後將其進行格式化，之後遍可以使用他提供的方法進行快速查找指定元素，從而使得在HTML或XML中查找指定元素變得簡單
from bs4 import BeautifulSoup
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
asdf
<div class="title">
<b>The Dormouse's story總共</b>
<h1>f</h1>
</div>
<div class="story">Once upon a time there were three little sisters; and their names were
<a class="sister0" id="link1">Els<span>f</span>ie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</div>
ad<br/>sf
<p class="story">...</p>
</body>
</html>
"""
soup = BeautifulSoup(html_doc, features="lxml")
# 找到第一個a標籤
tag1 = soup.find(name='a')
# 找到所有的a標籤
tag2 = soup.find_all(name='a')
# 找到id＝link2的標籤
tag3 = soup.select('#link2')
安裝
pip3 install beautifulsoup4
1 、 name，標籤名稱
tag = soup.find('a')
name = tag.name # 獲取
print(name)
tag.name = 'span' # 設置
print(soup)
2、 attr，標籤屬性
tag = soup.find('a')
attrs = tag.attrs # 獲取
print(attrs)
tag.attrs = {'ik':123} # 設置
tag.attrs['id'] = 'iiiii' # 設置
print(soup)
3、 children,所有子標籤
body = soup.find('body')
v = body.children
4、 children,所有子子孫孫標籤
body = soup.find('body')
v = body.descendants
5、clear,將標籤的所有子標籤全部清空（保留標籤名）
tag = soup.find('body')
tag.clear()
print(soup)
6、decompose,遞歸的刪除所有的標籤
body = soup.find('body')
body.decompose()
print(soup)
7、 extract,遞歸的刪除所有的標籤，並獲取刪除的標籤
body = soup.find('body')
v = body.extract()
print(soup)
8、decode,轉換爲字符串（含當前標籤）；decode_contents（不含當前標籤）
body = soup.find('body')
v = body.decode()
v = body.decode_contents()
print(v)
9、 encode,轉換爲字節（含當前標籤）；encode_contents（不含當前標籤）
body = soup.find('body')
v = body.encode()
v = body.encode_contents()
print(v)
10、 find,獲取匹配的第一個標籤
tag = soup.find('a')
print(tag)
tag = soup.find(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie')
tag = soup.find(name='a', class_='sister', recursive=True, text='Lacie')
print(tag)
11、 find_all,獲取匹配的所有標籤
tags = soup.find_all('a')
print(tags)
tags = soup.find_all('a',limit=1)
print(tags)
tags = soup.find_all(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie')
# tags = soup.find(name='a', class_='sister', recursive=True, text='Lacie')
print(tags)
####### 列表 #######
v = soup.find_all(name=['a','div'])
print(v)
v = soup.find_all(class_=['sister0', 'sister'])
print(v)
v = soup.find_all(text=['Tillie'])
print(v, type(v[0]))
v = soup.find_all(id=['link1','link2'])
print(v)
v = soup.find_all(href=['link1','link2'])
print(v)
####### 正則 #######
import re
rep = re.compile('p')
rep = re.compile('^p')
v = soup.find_all(name=rep)
print(v)
rep = re.compile('sister.*')
v = soup.find_all(class_=rep)
print(v)
rep = re.compile('http://www.oldboy.com/static/.*')
v = soup.find_all(href=rep)
print(v)
####### 方法篩選 #######
def func(tag):
return tag.has_attr('class') and tag.has_attr('id')
v = soup.find_all(name=func)
print(v)
## get,獲取標籤屬性
tag = soup.find('a')
v = tag.get('id')
print(v)
12、 has_attr,檢查標籤是否具有該屬性
tag = soup.find('a')
v = tag.has_attr('id')
print(v)
13、 get_text,獲取標籤內部文本內容
tag = soup.find('a')
v = tag.get_text('id')
print(v)
14、 index,檢查標籤在某標籤中的索引位置
tag = soup.find('body')
v = tag.index(tag.find('div'))
print(v)
tag = soup.find('body')
for i,v in enumerate(tag):
print(i,v)
15、 is_empty_element,是否是空標籤(是否可以是空)或者自閉合標籤，
判斷是否是如下標籤：'br' , 'hr', 'input', 'img', 'meta','spacer', 'link', 'frame', 'base'
tag = soup.find('br')
v = tag.is_empty_element
print(v)
16、 當前的關聯標籤
soup.next
soup.next_element
soup.next_elements
soup.next_sibling
soup.next_siblings
tag.previous
tag.previous_element
tag.previous_elements
tag.previous_sibling
tag.previous_siblings
tag.parent
tag.parents
17、 查找某標籤的關聯標籤
tag.find_next(...)
tag.find_all_next(...)
tag.find_next_sibling(...)
tag.find_next_siblings(...)
tag.find_previous(...)
tag.find_all_previous(...)
tag.find_previous_sibling(...)
tag.find_previous_siblings(...)
tag.find_parent(...)
tag.find_parents(...)
參數同find_all
18、 select,select_one, CSS選擇器
soup.select("title")
soup.select("p nth-of-type(3)")
soup.select("body a")
soup.select("html head title")
tag = soup.select("span,a")
soup.select("head > title")
soup.select("p > a")
soup.select("p > a:nth-of-type(2)")
soup.select("p > #link1")
soup.select("body > a")
soup.select("#link1 ~ .sister")
soup.select("#link1 + .sister")
soup.select(".sister")
soup.select("[class~=sister]")
soup.select("#link1")
soup.select("a#link2")
soup.select('a[href]')
soup.select('a[href="http://example.com/elsie"]')
soup.select('a[href^="http://example.com/"]')
soup.select('a[href$="tillie"]')
soup.select('a[href*=".com/el"]')
from bs4.element import Tag
def default_candidate_generator(tag):
for child in tag.descendants:
if not isinstance(child, Tag):
continue
if not child.has_attr('href'):
continue
yield child
tags = soup.find('body').select("a", _candidate_generator=default_candidate_generator)
print(type(tags), tags)
from bs4.element import Tag
def default_candidate_generator(tag):
for child in tag.descendants:
if not isinstance(child, Tag):
continue
if not child.has_attr('href'):
continue
yield child
tags = soup.find('body').select("a", _candidate_generator=default_candidate_generator, limit=1)
print(type(tags), tags)
19、 標籤的內容
tag = soup.find('span')
print(tag.string) # 獲取
tag.string = 'new content' # 設置
print(soup)
tag = soup.find('body')
print(tag.string)
tag.string = 'xxx'
print(soup)
tag = soup.find('body')
v = tag.stripped_strings # 遞歸內部獲取所有標籤的文本
print(v)
20、append在當前標籤內部追加一個標籤
tag = soup.find('body')
tag.append(soup.find('a'))
print(soup)
from bs4.element import Tag
obj = Tag(name='i',attrs={'id': 'it'})
obj.string = '我是一個新來的'
tag = soup.find('body')
tag.append(obj)
print(soup)
21、.insert在當前標籤內部指定位置插入一個標籤
from bs4.element import Tag
obj = Tag(name='i', attrs={'id': 'it'})
obj.string = '我是一個新來的'
tag = soup.find('body')
tag.insert(2, obj)
print(soup)
22、 insert_after,insert_before 在當前標籤後面或前面插入
from bs4.element import Tag
obj = Tag(name='i', attrs={'id': 'it'})
obj.string = '我是一個新來的'
tag = soup.find('body')
# tag.insert_before(obj)
tag.insert_after(obj)
print(soup)
23、 replace_with 在當前標籤替換爲指定標籤
from bs4.element import Tag
obj = Tag(name='i', attrs={'id': 'it'})
obj.string = '我是一個新來的'
tag = soup.find('div')
tag.replace_with(obj)
print(soup)
24、 創建標籤之間的關係
tag = soup.find('div')
a = soup.find('a')
tag.setup(previous_sibling=a)
print(tag.previous_sibling)
25、 wrap，將指定標籤把當前標籤包裹起來
from bs4.element import Tag
obj1 = Tag(name='div', attrs={'id': 'it'})
obj1.string = '我是一個新來的'
tag = soup.find('a')
v = tag.wrap(obj1)
print(soup)
tag = soup.find('a')
v = tag.wrap(soup.find('p'))
print(soup)
26、 unwrap，去掉當前標籤，將保留其包裹的標籤
tag = soup.find('a')
v = tag.unwrap()
print(soup)
摘自於 https://www.cnblogs.com/wupeiqi/articles/6283017.html