爬虫相关
requests
Python標準庫中提供了：urllib、urllib2、httplib等模塊以供Http請求，但是，它的 API 太渣了。它是為另一個時代、另一個互聯網所創建的。它需要巨量的工作，甚至包括各種方法覆蓋，來完成最簡單的任務。
Requests 是使用 Apache2 Licensed 許可證的 基于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可以輕而易舉的完成瀏覽器可有的任何操作。
1、GET請求
# 1、無參數實例import requestsret = requests.get('https://github.com/timeline.json')print ret.url print ret.text# 2、有參數實例import requestspayload = {'key1': 'value1', 'key2': 'value2'} ret = requests.get("http://httpbin.org/get", params=payload)print ret.url print ret.text2、POST請求
# 1、基本POST實例import requestspayload = {'key1': 'value1', 'key2': 'value2'} ret = requests.post("http://httpbin.org/post", data=payload)print ret.text# 2、發送請求頭和數據實例import requests import jsonurl = '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.cookies3、其他請求
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、更多參數
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 stringdefining the content type of the given file and ``custom_headers`` a dict-like object containing additional headersto 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 databefore giving up, as a float, or a :ref:`(connect timeout, readtimeout) <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.ResponseUsage::>>> import requests>>> req = requests.request('GET', 'http://httpbin.org/get')<Response [200]>""" 參數列表?
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/')passdef param_param():# - 可以是字典# - 可以是字符串# - 可以是字節（ascii編碼以內）# 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'))passdef param_data():# 可以是字典# 可以是字符串# 可以是字節# 可以是文件對象# 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'}# )passdef param_json():# 將json中對應的數據進行序列化成一個字符串，json.dumps(...)# 然后發送到服務器端的body中，并且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'},)# 也可以使用CookieJar（字典形式就是在此基礎上封裝）from http.cookiejar import CookieJarfrom http.cookiejar import Cookieobj = 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，定制文件名# 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，定制文件名# 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，定制文件名# 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)passdef param_auth():from requests.auth import HTTPBasicAuth, HTTPDigestAuthret = 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)passdef 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)passdef 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 requestssession = requests.Session()### 1、首先登陸任何頁面，獲取cookie i1 = session.get(url="http://dig.chouti.com/help/service")### 2、用戶登陸，攜帶上一次的cookie，后臺對cookie中的 gpsd 進行授權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
BeautifulSoup
BeautifulSoup是一個模塊，該模塊用于接收一個HTML或XML字符串，然后將其進行格式化，之后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 BeautifulSouphtml_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標簽 tag1 = soup.find(name='a') # 找到所有的a標簽 tag2 = soup.find_all(name='a') # 找到id＝link2的標簽 tag3 = soup.select('#link2')安裝：
pip3 install beautifulsoup4使用示例：
from bs4 import BeautifulSouphtml_doc = """ <html><head><title>The Dormouse's story</title></head> <body>... </body> </html> """soup = BeautifulSoup(html_doc, features="lxml")1. name，標簽名稱
# tag = soup.find('a') # name = tag.name # 獲取 # print(name) # tag.name = 'span' # 設置 # print(soup)2. attrs，標簽屬性
# 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,所有子標簽
# body = soup.find('body') # v = body.children4.descendants,所有子子孫孫標簽
# body = soup.find('body') # v = body.descendants5. clear,將標簽的所有子標簽全部清空（保留標簽名）
# tag = soup.find('body') # tag.clear() # print(soup)6. decompose,遞歸的刪除所有的標簽
# body = soup.find('body') # body.decompose() # print(soup)7. extract,遞歸的刪除所有的標簽，并獲取刪除的標簽
# body = soup.find('body') # v = body.extract() # print(soup)8.?decode,轉換為字符串（含當前標簽）；decode_contents（不含當前標簽）
# body = soup.find('body') # v = body.decode() # v = body.decode_contents() # print(v)9.?encode,轉換為字節（含當前標簽）；encode_contents（不含當前標簽）
# body = soup.find('body') # v = body.encode() # v = body.encode_contents() # print(v)10.?find,獲取匹配的第一個標簽
# 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,獲取匹配的所有標簽
# 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)# ####### 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)12. get, 獲取標簽屬性
## get,獲取標簽屬性 tag = soup.find('a') v = tag.get('id') print(v)13.?has_attr,檢查標簽是否具有該屬性
# tag = soup.find('a') # v = tag.has_attr('id') # print(v)14.?get_text,獲取標簽內部文本內容
# tag = soup.find('a') # v = tag.get_text() # print(v)15.?index,檢查標簽在某標簽中的索引位置
# 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)16.?is_empty_element,是否是空標簽(是否可以是空)或者自閉合標簽，
? ? ?判斷是否是如下標簽：'br' , 'hr', 'input', 'img', 'meta','spacer', 'link', 'frame', 'base'
# tag = soup.find('br') # v = tag.is_empty_element # print(v)17. 當前的關聯標簽
# 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.parents18. 查找某標簽的關聯標簽
# 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_all19.?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 Tagdef default_candidate_generator(tag):for child in tag.descendants:if not isinstance(child, Tag):continueif not child.has_attr('href'):continueyield childtags = 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):continueif not child.has_attr('href'):continueyield childtags = soup.find('body').select("a", _candidate_generator=default_candidate_generator, limit=1) print(type(tags), tags)20.?標簽的內容
# 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簽的文本 # print(v)21.append在當前標簽內部追加一個標簽
# 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)22.insert在當前標簽內部指定位置插入一個標簽
# 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)23.?insert_after,insert_before 在當前標簽后面或前面插入
# 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)24.?replace_with 在當前標簽替換為指定標簽
# 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)25.?創建標簽之間的關系
# tag = soup.find('div') # a = soup.find('a') # tag.setup(previous_sibling=a) # print(tag.previous_sibling)26.?wrap，將指定標簽把當前標簽包裹起來
# 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)27.?unwrap，去掉當前標簽，將保留其包裹的標簽
# tag = soup.find('a') # v = tag.unwrap() # print(soup)更多參數官方：http://beautifulsoup.readthedocs.io/zh_CN/v4.4.0/
一大波"自動登陸"示例
#!/usr/bin/env python # -*- coding:utf-8 -*- import requests# ############## 方式一 ############## """ # ## 1、首先登陸任何頁面，獲取cookie i1 = requests.get(url="http://dig.chouti.com/help/service") i1_cookies = i1.cookies.get_dict()# ## 2、用戶登陸，攜帶上一次的cookie，后臺對cookie中的 gpsd 進行授權 i2 = requests.post(url="http://dig.chouti.com/login",data={'phone': "8615131255089",'password': "xxooxxoo",'oneMonth': ""},cookies=i1_cookies )# ## 3、點贊（只需要攜帶已經被授權的gpsd即可） gpsd = i1_cookies['gpsd'] i3 = requests.post(url="http://dig.chouti.com/link/vote?linksId=8589523",cookies={'gpsd': gpsd} )print(i3.text) """# ############## 方式二 ############## """ import requestssession = requests.Session() i1 = session.get(url="http://dig.chouti.com/help/service") i2 = session.post(url="http://dig.chouti.com/login",data={'phone': "8615131255089",'password': "xxooxxoo",'oneMonth': ""} ) i3 = session.post(url="http://dig.chouti.com/link/vote?linksId=8589523" ) print(i3.text)""" 抽屜新熱榜 #!/usr/bin/env python # -*- coding:utf-8 -*-import requests from bs4 import BeautifulSoup# ############## 方式一 ############## # # # 1. 訪問登陸頁面，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. 訪問登陸頁面，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) github #!/usr/bin/env python # -*- coding:utf-8 -*- import timeimport requests from bs4 import BeautifulSoupsession = 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，查看并輸入驗證碼：') 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 #!/usr/bin/env python # -*- coding:utf-8 -*- import re import json import base64import rsa import requestsdef 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 valuesession = 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?
?
轉載于:https://www.cnblogs.com/Michael--chen/p/7446197.html
總結
- 上一篇： Effective C++ 条款05
- 下一篇： Eclipse Class Decomp