python中运用urllib.request简单抓取网页数据
urllib.request
1、抓取百度首页
1 from urllib import request 2 3 #url 4 #根据url获取数据，下载数据到本地 5 #正则orXpath处理数据 6 #数据转储 7 8 url = 'http://www.baidu.com/' 9 #获取数据 10 response = request.urlopen(url) 11 #读取数据 12 html_bytes = response.read() 13 #数据写入文件 14 with open('html_bytes','wb') as fb: 15 fb.write(html_bytes) 16 # print(response.read().decode('utf-8'))
2、抓取西刺代理首页
from urllib import request from urllib.error import HTTPError, URLError # url = 'http://www.xicidaili.com/' # #若出现urllib.error.HTTPError: HTTP Error 503: Service Temporarily Unavailable # #用以下方式处理,参数中添加form # user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36' # headers = { # 'User-Agent': user_agent # } # #定义Request # req = request.Request(url,headers=headers) # response = request.urlopen(req) # print(response.read().decode('utf-8')) #封装成函数 def urlrequest(url,headers=None): user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36' if headers == None: headers = { 'User-Agent': user_agent } # 定义Request try: req = request.Request(url,headers=headers) response = request.urlopen(req) html_bytes = response.read() return html_bytes except HTTPError as e: return e except URLError as e: return e if __name__ == '__main__':
#测试 print(urlrequest('http://www.baidu.com/').decode('utf-8')) print(urlrequest('http://www.xicidaili.com/').decode('utf-8'))
3、GET、POST请求
from urllib import request, parse from urllib.error import HTTPError, URLError import json #get请求 def get(url, headers=None): return urlrequest(url, headers=headers) #post请求 def post(url, form, headers=None): return json.loads(urlrequest(url, form, headers=headers)) def urlrequest(url, form=None, headers=None): html_bytes = b'' #判断是否传入请求头 if headers == None: user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36' headers = { 'User-Agent': user_agent } try: #判断是否传入form if form: # 字典转bytes # 1、先转字符串 form_str = parse.urlencode(form) # 2、转为bytes型 form_bytes = form_str.encode('utf-8') # 定义Request req = request.Request(url, data=form_bytes, headers=headers) else: req = request.Request(url, headers=headers) response = request.urlopen(req) html_bytes = response.read() except HTTPError as e: print(e) except URLError as e: print(e) return html_bytes if __name__ == '__main__': #post请求测试 url = 'http://fanyi.baidu.com/sug/' form = { 'kw':'呵呵' } html_dict = post(url,form=form) print(html_dict) print(html_dict['data'][0]['v']) #get请求测试 url = 'http://www.python.org' html_bytes = get(url) print(html_bytes.decode('utf-8'))
4、有道翻译加盐破解
import time, random, json from day01.tuozhan_all import post #有道翻译加盐破解 def md5_my(need_str): import hashlib #创建MD5对象 md5_o = hashlib.md5() #需要bytes类型作为参数 sign_bytes = need_str.encode('utf-8') md5_o.update(sign_bytes) sign_str = md5_o.hexdigest() return sign_str def trans(kw): #url url = 'http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule' #headers headers = { 'Accept': 'application/json, text/javascript, */*; q=0.01', #'Accept-Encoding': 'gzip, deflate', 'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.9', 'Connection': 'keep-alive', #'Content-Length': '241', 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', 'Cookie': 'OUTFOX_SEARCH_USER_ID=1371246944@10.169.0.83; OUTFOX_SEARCH_USER_ID_NCOO=175172091.56957078; JSESSIONID=aaa6Z2lldaepL-EYrr4uw; ___rl__test__cookies=1534249690001', 'Host': 'fanyi.youdao.com', 'Origin': 'http://fanyi.youdao.com', 'Referer': 'http://fanyi.youdao.com/', 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36', 'X-Requested-With': 'XMLHttpRequest' } key = kw # salt : ((new Date).getTime() + parseInt(10 * Math.random(), 10)) salt = int(time.time() * 1000 + random.randint(0, 10)) salt_str = str(salt) S = "fanyideskweb" D = "ebSeFb%=XZ%T[KZ)c(sy!" sign_str = S+key+salt_str+D sign_md5_str = md5_my(sign_str) #form form = { 'i': key, 'from': 'AUTO', 'to': 'AUTO', 'smartresult': 'dict', 'client': 'fanyideskweb', 'salt': salt_str, 'sign': sign_md5_str, 'doctype': 'json', 'version': '2.1', 'keyfrom': 'fanyi.web', 'action': 'FY_BY_REALTIME', 'typoResult': 'false', } html_bytes = post(url, form, headers=headers) #将json格式数据转化为字典 res_dict = json.loads(html_bytes.decode('utf-8')) print(res_dict) trans_res = res_dict['translateResult'][0][0]['tgt'] return trans_res if __name__ == '__main__': res = trans('青青河边草') print(res)
5、人人网首页数据抓取
from urllib import request, parse from urllib.error import HTTPError, URLError from http import cookiejar import json class session(object): def __init__(self): # 1、实例化cookie对象 cookie_obj = cookiejar.CookieJar() # 2、handler处理 handler = request.HTTPCookieProcessor(cookie_obj) # 3、opener 遇到有cookie的response的时候,调用handler内部的一个函数, 存储到cookie object self.opener = request.build_opener(handler) def get(self,url, headers=None): return get(url, headers, self.opener) def post(self, url, form, headers=None): return post(url, form, headers, self.opener) def get(url, headers=None, opener=None): return urlrequests(url, headers=headers, opener=opener) def post(url, form, headers=None, opener=None): return urlrequests(url, form, headers=headers, opener=opener) #b. post(url, form, headers=None) #1. 传入url #2. user_agent #3. headers #4. 定义Request #5. urlopen #6. 返回byte数组 def urlrequests(url, form=None, headers=None, opener=None): user_agent = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36' # 如果用户需要自行传入headers, 则覆盖之前的headers if headers == None: headers = { 'User-Agent': user_agent } html_bytes = b'' try: if form: # POST # 2.1 转换成str form_str = parse.urlencode(form) #print(form_str) # 2.2 转换成bytes form_bytes = form_str.encode('utf-8') req = request.Request(url, data=form_bytes, headers=headers) else: req = request.Request(url, headers=headers) if opener: response = opener.open(req) else: response = request.urlopen(req) html_bytes = response.read() except HTTPError as e: print(e) except URLError as e: print(e) return html_bytes if __name__ == '__main__': #测试--带cookies的请求 url = 'http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=201872221746' form = { 'email': '18573151260', 'icode': '', 'origURL': 'http: // www.renren.com / home', 'domain': 'renren.com', 'key_id': '1', 'captcha_type': 'web_login', 'password': '60a075bc14562c91baf36094ffe93d8fa9c1809a8501a43a7da131e1f119ae91', 'rkey': 'f9cd77eb1280ab74763c1f1552dc11c7', 'f': 'http%3A%2F%2Fwww.renren.com%2F967453528' } #实例化对象 s = session() #post请求 res = s.post(url,form) #获取的数据转为字典 res_dict = json.loads(res) #获取url，此时cookie以通过s对象传入cookies_obj中 home_url = res_dict['homeUrl'] #打开url,此时将cookie_obj中的cookie response = s.opener.open(home_url #打印获取的数据 print(response.read().decode('utf-8')) # url = 'http://www.baidu.com/' # html_byte = get(url) # print(html_byte.decode('utf-8'))
