python之爬蟲_模塊

目錄

1、requests模塊
2、Beautifulsoup模塊

 

1、requests模塊 

一、介紹

Python標準庫中提供了：urllib、urllib二、httplib等模塊以供Http請求，可是，它的 API 太渣了。它是爲另外一個時代、另外一個互聯網所建立的。它須要巨量的工做，甚至包括各類方法覆蓋，來完成最簡單的任務。

Requests 是使用 Apache2 Licensed 許可證的 基於Python開發的HTTP 庫，其在Python內置模塊的基礎上進行了高度的封裝，從而使得Pythoner進行網絡請求時，變得美好了許多，使用Requests能夠垂手可得的完成瀏覽器可有的任何操做。

二、請求method介紹

（1）GET請求

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20

# 一、無參數實例    import  requests    ret  =  requests.get( 'https://github.com/timeline.json' ) ret.encoding = "gbk" print( ret.url) print( ret.text)  # str print( ret.content)  # bytes       # 二、有參數實例    import  requests    payload  =  { 'key1' :  'value1' ,  'key2' :  'value2' } ret  =  requests.get( "http://httpbin.org/get" , params = payload)    print  ret.url print  ret.text

（2）POST請求

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23

# 一、基本POST實例    import  requests    payload  =  { 'key1' :  'value1' ,  'key2' :  'value2' } ret  =  requests.post( "http://httpbin.org/post" , data = payload)    print  ret.text       # 二、發送請求頭和數據實例    import  requests import  json    url  =  'https://api.github.com/some/endpoint' payload  =  { 'some' :  'data' } headers  =  { 'content-type' :  'application/json' }    ret  =  requests.post(url, data = json.dumps(payload), headers = headers)    print  ret.text print  ret.cookies

（3）其餘請求

1 2 3 4 5 6 7 8 9 10

requests.get(url, params = None ,  * * kwargs) requests.post(url, data = None , json = None ,  * * kwargs) requests.put(url, data = None ,  * * kwargs) requests.head(url,  * * kwargs) requests.delete(url,  * * kwargs) requests.patch(url, data = None ,  * * kwargs) requests.options(url,  * * kwargs)    # 以上方法均是在此方法的基礎上構建 requests.request(method, url,  * * kwargs)

（4）代理

import requests
url = "http://www.baidu.com/"
headers = {
    "User-Agent":'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:62.0) Gecko/20100101 Firefox/62.0'
}
proxies={
    'http':'113.200.56.13:8010',  # 網上隨便找的一個代理，不穩定
}
res = requests.get(url=url,proxies=proxies)
res.encoding = "utf8"
print(res.text)  # 實驗成功

 

三、參數說明

def request(method, url, **kwargs):
    """Constructs and sends a :class:`Request <Request>`.

    :param method: method for the new :class:`Request` object.
    :param url: URL for the new :class:`Request` object.
    :param params: (optional) Dictionary or bytes to be sent in the query string for the :class:`Request`.
    :param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`.
    :param json: (optional) json data to send in the body of the :class:`Request`.
    :param headers: (optional) Dictionary of HTTP Headers to send with the :class:`Request`.
    :param cookies: (optional) Dict or CookieJar object to send with the :class:`Request`.
    :param files: (optional) Dictionary of ``'name': file-like-objects`` (or ``{'name': file-tuple}``) for multipart encoding upload.
        ``file-tuple`` can be a 2-tuple ``('filename', fileobj)``, 3-tuple ``('filename', fileobj, 'content_type')``
        or a 4-tuple ``('filename', fileobj, 'content_type', custom_headers)``, where ``'content-type'`` is a string
        defining the content type of the given file and ``custom_headers`` a dict-like object containing additional headers
        to add for the file.
    :param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth.
    :param timeout: (optional) How long to wait for the server to send data
        before giving up, as a float, or a :ref:`(connect timeout, read
        timeout) <timeouts>` tuple.
    :type timeout: float or tuple
    :param allow_redirects: (optional) Boolean. Set to True if POST/PUT/DELETE redirect following is allowed.
    :type allow_redirects: bool
    :param proxies: (optional) Dictionary mapping protocol to the URL of the proxy.
    :param verify: (optional) whether the SSL cert will be verified. A CA_BUNDLE path can also be provided. Defaults to ``True``.
    :param stream: (optional) if ``False``, the response content will be immediately downloaded.
    :param cert: (optional) if String, path to ssl client cert file (.pem). If Tuple, ('cert', 'key') pair.
    :return: :class:`Response <Response>` object
    :rtype: requests.Response

    Usage::

      >>> import requests
      >>> req = requests.request('GET', 'http://httpbin.org/get')
      <Response [200]>
    """

參數列表

參數說明

def param_method_url():
    # requests.request(method='get', url='http://127.0.0.1:8000/test/')
    # requests.request(method='post', url='http://127.0.0.1:8000/test/')
    pass


def param_param():
    # - 能夠是字典
    # - 能夠是字符串
    # - 能夠是字節（ascii編碼之內）

    # requests.request(method='get',
    # url='http://127.0.0.1:8000/test/',
    # params={'k1': 'v1', 'k2': '水電費'})

    # requests.request(method='get',
    # url='http://127.0.0.1:8000/test/',
    # params="k1=v1&k2=水電費&k3=v3&k3=vv3")

    # requests.request(method='get',
    # url='http://127.0.0.1:8000/test/',
    # params=bytes("k1=v1&k2=k2&k3=v3&k3=vv3", encoding='utf8'))

    # 錯誤
    # requests.request(method='get',
    # url='http://127.0.0.1:8000/test/',
    # params=bytes("k1=v1&k2=水電費&k3=v3&k3=vv3", encoding='utf8'))
    pass


def param_data():
    # 能夠是字典
    # 能夠是字符串
    # 能夠是字節
    # 能夠是文件對象

    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # data={'k1': 'v1', 'k2': '水電費'})

    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # data="k1=v1; k2=v2; k3=v3; k3=v4"
    # )

    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # data="k1=v1;k2=v2;k3=v3;k3=v4",
    # headers={'Content-Type': 'application/x-www-form-urlencoded'}
    # )

    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # data=open('data_file.py', mode='r', encoding='utf-8'), # 文件內容是：k1=v1;k2=v2;k3=v3;k3=v4
    # headers={'Content-Type': 'application/x-www-form-urlencoded'}
    # )
    pass


def param_json():
    # 將json中對應的數據進行序列化成一個字符串，json.dumps(...)
    # 而後發送到服務器端的body中，而且Content-Type是 {'Content-Type': 'application/json'}
    requests.request(method='POST',
                     url='http://127.0.0.1:8000/test/',
                     json={'k1': 'v1', 'k2': '水電費'})


def param_headers():
    # 發送請求頭到服務器端
    requests.request(method='POST',
                     url='http://127.0.0.1:8000/test/',
                     json={'k1': 'v1', 'k2': '水電費'},
                     headers={'Content-Type': 'application/x-www-form-urlencoded'}
                     )


def param_cookies():
    # 發送Cookie到服務器端
    requests.request(method='POST',
                     url='http://127.0.0.1:8000/test/',
                     data={'k1': 'v1', 'k2': 'v2'},
                     cookies={'cook1': 'value1'},
                     )
    # 也能夠使用CookieJar（字典形式就是在此基礎上封裝）
    from http.cookiejar import CookieJar
    from http.cookiejar import Cookie

    obj = CookieJar()
    obj.set_cookie(Cookie(version=0, name='c1', value='v1', port=None, domain='', path='/', secure=False, expires=None,
                          discard=True, comment=None, comment_url=None, rest={'HttpOnly': None}, rfc2109=False,
                          port_specified=False, domain_specified=False, domain_initial_dot=False, path_specified=False)
                   )
    requests.request(method='POST',
                     url='http://127.0.0.1:8000/test/',
                     data={'k1': 'v1', 'k2': 'v2'},
                     cookies=obj)


def param_files():
    # 發送文件
    # file_dict = {
    # 'f1': open('readme', 'rb')
    # }
    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # files=file_dict)

    # 發送文件，定製文件名
    # file_dict = {
    # 'f1': ('test.txt', open('readme', 'rb'))
    # }
    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # files=file_dict)

    # 發送文件，定製文件名
    # file_dict = {
    # 'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf")
    # }
    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # files=file_dict)

    # 發送文件，定製文件名
    # file_dict = {
    #     'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf", 'application/text', {'k1': '0'})
    # }
    # requests.request(method='POST',
    #                  url='http://127.0.0.1:8000/test/',
    #                  files=file_dict)

    pass


def param_auth():
    from requests.auth import HTTPBasicAuth, HTTPDigestAuth

    ret = requests.get('https://api.github.com/user', auth=HTTPBasicAuth('wupeiqi', 'sdfasdfasdf'))
    print(ret.text)

    # ret = requests.get('http://192.168.1.1',
    # auth=HTTPBasicAuth('admin', 'admin'))
    # ret.encoding = 'gbk'
    # print(ret.text)

    # ret = requests.get('http://httpbin.org/digest-auth/auth/user/pass', auth=HTTPDigestAuth('user', 'pass'))
    # print(ret)
    #


def param_timeout():
    # ret = requests.get('http://google.com/', timeout=1)
    # print(ret)

    # ret = requests.get('http://google.com/', timeout=(5, 1))
    # print(ret)
    pass


def param_allow_redirects():
    ret = requests.get('http://127.0.0.1:8000/test/', allow_redirects=False)
    print(ret.text)


def param_proxies():
    # proxies = {
    # "http": "61.172.249.96:80",
    # "https": "http://61.185.219.126:3128",
    # }

    # proxies = {'http://10.20.1.128': 'http://10.10.1.10:5323'}

    # ret = requests.get("http://www.proxy360.cn/Proxy", proxies=proxies)
    # print(ret.headers)


    # from requests.auth import HTTPProxyAuth
    #
    # proxyDict = {
    # 'http': '77.75.105.165',
    # 'https': '77.75.105.165'
    # }
    # auth = HTTPProxyAuth('username', 'mypassword')
    #
    # r = requests.get("http://www.google.com", proxies=proxyDict, auth=auth)
    # print(r.text)

    pass


def param_stream():
    ret = requests.get('http://127.0.0.1:8000/test/', stream=True)
    print(ret.content)
    ret.close()

    # from contextlib import closing
    # with closing(requests.get('http://httpbin.org/get', stream=True)) as r:
    # # 在此處理響應。
    # for i in r.iter_content():
    # print(i)


def requests_session():
    import requests

    session = requests.Session()

    ### 一、首先登錄任何頁面，獲取cookie

    i1 = session.get(url="http://dig.chouti.com/help/service")

    ### 二、用戶登錄，攜帶上一次的cookie，後臺對cookie中的 gpsd 進行受權
    i2 = session.post(
        url="http://dig.chouti.com/login",
        data={
            'phone': "8615131255089",
            'password': "xxxxxx",
            'oneMonth': ""
        }
    )

    i3 = session.post(
        url="http://dig.chouti.com/link/vote?linksId=8589623",
    )
    print(i3.text)

參數示例

 官方文檔：http://cn.python-requests.org/zh_CN/latest/user/quickstart.html#id4

2、Beautifulsoup模塊

可參考：https://blog.csdn.net/xxf813/article/details/81605197

一、介紹

BeautifulSoup是一個模塊，該模塊用於接收一個HTML或XML字符串，而後將其進行格式化，以後遍能夠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。

二、簡單使用

pip3 install beautifulsoup4

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')
# 找到全部的a標籤
tag2 = soup.find_all(name='a')
# 找到id＝link2的標籤
tag3 = soup.select('#link2')

簡單使用

三、方法說明

1. name，標籤名稱

# tag = soup.find('a')
# name = tag.name # 獲取
# print(name)
# tag.name = 'span' # 設置
# print(soup)

name

2. attrs，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)

attr

3. children,全部子標籤

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

children

4. descendants,全部子子孫孫標籤

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

descendants

5. clear,將標籤的全部子標籤所有清空（保留標籤名）

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

clear

6. decompose,遞歸的刪除全部的標籤

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

decompose

7. extract,遞歸的刪除全部的標籤，並獲取刪除的標籤。（跟父有關係）

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

extract

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)

decode

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)

encode

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)

find

11. find_all,獲取匹配的全部標籤

# 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)

find_all

12. has_attr,檢查標籤是否具備該屬性

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

has_attr

13. get_text,獲取標籤內部文本內容

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

get_text

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)

index

15. is_empty_element,是不是空標籤(是否能夠是空)或者自閉合標籤，

     判斷是不是以下標籤：'br' , 'hr', 'input', 'img', 'meta','spacer', 'link', 'frame', 'base'

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

is_empty_element

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

當前的關聯標籤（next、previous等）

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

查看某標籤的關聯標籤

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)

select，select_one，CSS選擇器

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  # 遞歸內部獲取全部標籤的文本
# print(v)

標籤內容（string等）

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)

append

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)

insert

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)

insert_after,insert_before

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)

replace_with

24. 建立標籤之間的關係

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

建立標籤之間的關係

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)

wrap

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)

unwrap

 更多參數官方：http://beautifulsoup.readthedocs.io/zh_CN/v4.4.0/

示例

# # -*- coding:utf-8 -*-
# import requests
# from bs4 import BeautifulSoup
#
#
# response = requests.get("http://www.autohome.com.cn/news/")
# response.encoding = "gbk"
#
# # print(type(response.text))  # str
#
#
# soup = BeautifulSoup(response.text,"html.parser")
#
# tag = soup.find(id='auto0channel0lazyload-article')
# print(tag)
# tag = soup.find(name="h3")
# print(tag)
# tag = soup.find(name="h3",attr={"class":"xxx"})

# 全部新聞
# 標題，簡介，url，圖片



import requests
from bs4 import BeautifulSoup

#
html = requests.get("http://www.autohome.com.cn/news/")
html.encoding = "gbk"
print(type(html.text))  # <class 'str'>
print(type(html.content))  # <class 'bytes'>


soup = BeautifulSoup(html,"html.parser")

li_list = soup.find(id="auto-channel-lazyload-article").find_all(name="li")
for li in li_list:
    title = li.find(name="h3")
    if not title:
        continue
    print('\033[1;32m[標題]\033[0m',title.text)
    summary = li.find(name="p")
    print('\033[1;33m[簡介]\033[0m',summary.text)

    # attrs = li.find("a").attrs
    # print(attrs)
    url = li.find("a").get("href")
    print('\033[1;34m[url]\033[0m',url)

    img = li.find("img").get("src")
    print('\033[1;35m[img]\033[0m',img)

    res = requests.get("http:%s" % (img,))


    # file_name = img.rsplit("/",1)[1]
    # with open(file_name,"wb") as f:
    #     f.write(res.content)

    print("\033[1;31m==================================================================\033[0m")

汽車之家 某些頁面

# -*- coding:utf-8 -*-

import requests
from bs4 import BeautifulSoup

# 獲取token
r1 = requests.get("https://github.com/login")
r1.encoding = "gbk"
s1 = BeautifulSoup(r1.text,"html.parser")
token = s1.find(name="input",attrs={"name":"authenticity_token"}).get("value")
r1_cookie_dict = r1.cookies.get_dict()
print(token)



# 將用戶名、密碼、token發送到post的url
'''
commit:Sign in
utf8:✓
authenticity_token:r31RX8eQeShWRxUnEyYXtQHVmIlrw6sZmwdyy/IYP0dCzV1m4covQQZz+d8qUuc9mT8qIxjjx0U3YjKN9ZvLHA==
login:asdf
password:asdf
'''
r2 = requests.post(
    url="https://github.com/session",
    data={
        "utf8":"✓",
        "authenticity_token":token,
        "login":"fat39@163.com",
        "password":"123!@#qwe",
        "commit":"Sign in"
    },
    cookies=r1_cookie_dict,
)

r2_cookie_dict = r2.cookies.get_dict()
print(r2_cookie_dict)

# 帶cookie訪問
cookie_dict = {}
cookie_dict.update(r1_cookie_dict)
cookie_dict.update(r2_cookie_dict)
r3 = requests.get(
    url="https://github.com/settings/emails",
    cookies=cookie_dict,
)

print(r3.text)





############################################
#!/usr/bin/env python
# -*- coding:utf-8 -*-

import requests
from bs4 import BeautifulSoup

# ############## 方式一 ##############
#
# # 1. 訪問登錄頁面，獲取 authenticity_token
# i1 = requests.get('https://github.com/login')
# soup1 = BeautifulSoup(i1.text, features='lxml')
# tag = soup1.find(name='input', attrs={'name': 'authenticity_token'})
# authenticity_token = tag.get('value')
# c1 = i1.cookies.get_dict()
# i1.close()
#
# # 1. 攜帶authenticity_token和用戶名密碼等信息，發送用戶驗證
# form_data = {
# "authenticity_token": authenticity_token,
#     "utf8": "",
#     "commit": "Sign in",
#     "login": "wupeiqi@live.com",
#     'password': 'xxoo'
# }
#
# i2 = requests.post('https://github.com/session', data=form_data, cookies=c1)
# c2 = i2.cookies.get_dict()
# c1.update(c2)
# i3 = requests.get('https://github.com/settings/repositories', cookies=c1)
#
# soup3 = BeautifulSoup(i3.text, features='lxml')
# list_group = soup3.find(name='div', class_='listgroup')
#
# from bs4.element import Tag
#
# for child in list_group.children:
#     if isinstance(child, Tag):
#         project_tag = child.find(name='a', class_='mr-1')
#         size_tag = child.find(name='small')
#         temp = "項目:%s(%s); 項目路徑:%s" % (project_tag.get('href'), size_tag.string, project_tag.string, )
#         print(temp)



# ############## 方式二 ##############
# session = requests.Session()
# # 1. 訪問登錄頁面，獲取 authenticity_token
# i1 = session.get('https://github.com/login')
# soup1 = BeautifulSoup(i1.text, features='lxml')
# tag = soup1.find(name='input', attrs={'name': 'authenticity_token'})
# authenticity_token = tag.get('value')
# c1 = i1.cookies.get_dict()
# i1.close()
#
# # 1. 攜帶authenticity_token和用戶名密碼等信息，發送用戶驗證
# form_data = {
#     "authenticity_token": authenticity_token,
#     "utf8": "",
#     "commit": "Sign in",
#     "login": "wupeiqi@live.com",
#     'password': 'xxoo'
# }
#
# i2 = session.post('https://github.com/session', data=form_data)
# c2 = i2.cookies.get_dict()
# c1.update(c2)
# i3 = session.get('https://github.com/settings/repositories')
#
# soup3 = BeautifulSoup(i3.text, features='lxml')
# list_group = soup3.find(name='div', class_='listgroup')
#
# from bs4.element import Tag
#
# for child in list_group.children:
#     if isinstance(child, Tag):
#         project_tag = child.find(name='a', class_='mr-1')
#         size_tag = child.find(name='small')
#         temp = "項目:%s(%s); 項目路徑:%s" % (project_tag.get('href'), size_tag.string, project_tag.string, )
#         print(temp)

自動登陸github

#!/usr/bin/env python
# -*- coding:utf-8 -*-
import time

import requests
from bs4 import BeautifulSoup

session = requests.Session()

i1 = session.get(
    url='https://www.zhihu.com/#signin',
    headers={
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36',
    }
)

soup1 = BeautifulSoup(i1.text, 'lxml')
xsrf_tag = soup1.find(name='input', attrs={'name': '_xsrf'})
xsrf = xsrf_tag.get('value')

current_time = time.time()
i2 = session.get(
    url='https://www.zhihu.com/captcha.gif',
    params={'r': current_time, 'type': 'login'},
    headers={
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36',
    })

with open('zhihu.gif', 'wb') as f:
    f.write(i2.content)

captcha = input('請打開zhihu.gif文件，查看並輸入驗證碼：')
form_data = {
    "_xsrf": xsrf,
    'password': 'xxooxxoo',
    "captcha": 'captcha',
    'email': '424662508@qq.com'
}
i3 = session.post(
    url='https://www.zhihu.com/login/email',
    data=form_data,
    headers={
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36',
    }
)

i4 = session.get(
    url='https://www.zhihu.com/settings/profile',
    headers={
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36',
    }
)

soup4 = BeautifulSoup(i4.text, 'lxml')
tag = soup4.find(id='rename-section')
nick_name = tag.find('span',class_='name').string
print(nick_name)

知乎

知乎

#!/usr/bin/env python
# -*- coding:utf-8 -*-
import re
import json
import base64

import rsa
import requests


def js_encrypt(text):
    b64der = 'MIGfMA0GCSqGSIb3DQEBAQUAA4GNADCBiQKBgQCp0wHYbg/NOPO3nzMD3dndwS0MccuMeXCHgVlGOoYyFwLdS24Im2e7YyhB0wrUsyYf0/nhzCzBK8ZC9eCWqd0aHbdgOQT6CuFQBMjbyGYvlVYU2ZP7kG9Ft6YV6oc9ambuO7nPZh+bvXH0zDKfi02prknrScAKC0XhadTHT3Al0QIDAQAB'
    der = base64.standard_b64decode(b64der)

    pk = rsa.PublicKey.load_pkcs1_openssl_der(der)
    v1 = rsa.encrypt(bytes(text, 'utf8'), pk)
    value = base64.encodebytes(v1).replace(b'\n', b'')
    value = value.decode('utf8')

    return value


session = requests.Session()

i1 = session.get('https://passport.cnblogs.com/user/signin')
rep = re.compile("'VerificationToken': '(.*)'")
v = re.search(rep, i1.text)
verification_token = v.group(1)

form_data = {
    'input1': js_encrypt('wptawy'),
    'input2': js_encrypt('asdfasdf'),
    'remember': False
}

i2 = session.post(url='https://passport.cnblogs.com/user/signin',
                  data=json.dumps(form_data),
                  headers={
                      'Content-Type': 'application/json; charset=UTF-8',
                      'X-Requested-With': 'XMLHttpRequest',
                      'VerificationToken': verification_token}
                  )

i3 = session.get(url='https://i.cnblogs.com/EditDiary.aspx')

print(i3.text)

博客園

博客園

 

 

參考or轉發

http://www.cnblogs.com/wupeiqi/articles/6283017.html