天天看點
傳回

爬蟲 requests與BeautifulSoup 子產品/方法/參數 詳解1. 方法2. 參數

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('使用者名', '密碼')
        
        r = requests.get("http://www.google.com",data={'xxx':'ffff'} proxies=proxyDict, auth=auth)
        print(r.text)
-----------------------------------------------------------------------------------------
2.8 檔案上傳 files
    # 發送檔案
        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

    内部：
        使用者名和密碼，使用者和密碼加密，放在請求頭中傳給背景。
        
            - "使用者:密碼"
            - base64("使用者:密碼")
            - "Basic base64("使用者|密碼")"
            - 請求頭：
                Authorization： "basic base64("使用者|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 逾時 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 大檔案下載下傳 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 确認 verify =False

BeautifulSoup

是一個子產品，該子產品用于接收一個HTML或XML字元串，然後将其進行格式化，之後遍可以使用他提供的方法進行快速查找指定元素，進而使得在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" target="_blank" rel="external nofollow"  class="sister" id="link2">Lacie</a> and
    <a href="http://example.com/tillie" target="_blank" rel="external nofollow"  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标簽
tag1 = soup.find(name='a')
# 找到所有的a标簽
tag2 = soup.find_all(name='a')
# 找到id＝link2的标簽
tag3 = soup.select('#link2')

安裝

pip3 install beautifulsoup4

1 、 name，标簽名稱

tag = soup.find('a')
	 name = tag.name # 擷取
 	 print(name)
	 tag.name = 'span' # 設定
	 print(soup)

2、 attr，标簽屬性

tag = soup.find('a')
	 attrs = tag.attrs    # 擷取
	 print(attrs)
	 tag.attrs = {'ik':123} # 設定
	 tag.attrs['id'] = 'iiiii' # 設定
	 print(soup)

3、 children,所有子标簽

body = soup.find('body')
	v = body.children

4、 children,所有子子孫孫标簽

body = soup.find('body')
	 v = body.descendants

5、clear,将标簽的所有子标簽全部清空（保留标簽名）

tag = soup.find('body')
	 tag.clear()
	 print(soup)

6、decompose,遞歸的删除所有的标簽

body = soup.find('body')
body.decompose()
print(soup)

7、 extract,遞歸的删除所有的标簽，并擷取删除的标簽

body = soup.find('body')
v = body.extract()
print(soup)

8、decode,轉換為字元串（含目前标簽）；decode_contents（不含目前标簽）

body = soup.find('body')
v = body.decode()
v = body.decode_contents()
print(v)

9、 encode,轉換為位元組（含目前标簽）；encode_contents（不含目前标簽）

body = soup.find('body')
v = body.encode()
v = body.encode_contents()
print(v)

10、 find,擷取比對的第一個标簽

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,擷取比對的所有标簽

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)

####### 清單 #######

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,擷取标簽屬性
tag = soup.find('a')
v = tag.get('id')
print(v)

12、 has_attr,檢查标簽是否具有該屬性

tag = soup.find('a')
v = tag.has_attr('id')
print(v)

13、 get_text,擷取标簽内部文本内容

tag = soup.find('a')
v = tag.get_text('id')
print(v)

14、 index,檢查标簽在某标簽中的索引位置

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,是否是空标簽(是否可以是空)或者自閉合标簽，

判斷是否是如下标簽：'br' , 'hr', 'input', 'img', 'meta','spacer', 'link', 'frame', 'base'

tag = soup.find('br')
v = tag.is_empty_element
print(v)

16、 目前的關聯标簽

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、 查找某标簽的關聯标簽

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" target="_blank" rel="external nofollow" ]')
 
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、 标簽的内容

tag = soup.find('span')
print(tag.string)          # 擷取
tag.string = 'new content' # 設定
print(soup)

tag = soup.find('body')
print(tag.string)
tag.string = 'xxx'
print(soup)

tag = soup.find('body')
v = tag.stripped_strings  # 遞歸内部擷取所有标簽的文本
print(v)

20、append在目前标簽内部追加一個标簽

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在目前标簽内部指定位置插入一個标簽

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 在目前标簽後面或前面插入

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 在目前标簽替換為指定标簽

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、 建立标簽之間的關系

tag = soup.find('div')
a = soup.find('a')
tag.setup(previous_sibling=a)
print(tag.previous_sibling)

25、 wrap，将指定标簽把目前标簽包裹起來

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，去掉目前标簽，将保留其包裹的标簽

tag = soup.find('a')
v = tag.unwrap()
print(soup)

摘自于 https://www.cnblogs.com/wupeiqi/articles/6283017.html

爬蟲 requests子產品 BeautifulSoup子產品
上一篇: Python爬蟲，爬取百度百科詞條
下一篇: BeautifulSoup4 css選擇器選中一個html标簽的class屬性擁有多個值的标簽

繼續閱讀