爬虫Day2

人人网cookie

import json
from urllib import request, parse
from http import cookiejar
cookie_object=cookiejar.CookieJar()
handler=request.HTTPCookieProcessor(cookie_object)
opener=request.build_opener(handler)
url='http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=201872206105'
form={
    'email': '18410428710',
    'icode': '',
    'origURL': 'http://www.renren.com/home',
    'domain': 'renren.com',
    'key_id': '1',
    'captcha_type': 'web_login',
    'password': '0d69ca97e3834126e9976acb7b719862358bd8c37a29982b45ea8fbed229569f',
    'rkey': 'e4d47e9b8147031c0b57a9e6b5ffba2c',
    'f': 'https%3A%2F%2Fwww.sogou.com%2Flink%3Furl%3DDSOYnZeCC_r-h4h4RsVJtWYvcrgiTSe0',
}
form_bytes=parse.urlencode(form).encode('utf-8')
response=opener.open(url,form_bytes)
html_bytes=response.read()
res_dict=json.loads(html_bytes.decode('utf-8'))
home_url=res_dict['homeUrl']
response=opener.open(home_url)
html_bytes=response.read()
print(html_bytes.decode('utf-8'))

有道云翻译

import time
import random
import json
from demo import post
def md5_my(need_str):
    import hashlib
    md5_0=hashlib.md5()
    sign_bytes=need_str.encode('utf-8')
    md5_0.update(sign_bytes)
    sign_str=md5_0.hexdigest()
    return  sign_str
def translate(kw):
    url='http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'
    headers={
        'Accept': 'application/json, text/javascript, */*; q=0.01',
        # 'Accept-Encoding': 'gzip, deflate',
        'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
        'Connection': 'keep-alive',
        # 'Content-Length': '223',
        'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
        'Cookie': 'OUTFOX_SEARCH_USER_ID=-493176930@10.168.8.63; OUTFOX_SEARCH_USER_ID_NCOO=38624120.26076847; SESSION_FROM_COOKIE=unknown; JSESSIONID=aaabYcV4ZOU-JbQUha2uw; ___rl__test__cookies=1534210912076',
        '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 = int(time.time() * 1000 + random.randint(0, 10))
    # print(salt)
    salt_str = str(salt)
    S = "fanyideskweb"
    D = "ebSeFb%=XZ%T[KZ)c(sy!"
    sign_str = S + key + salt_str + D
    # md5 加密的方法
    sign_md5_str = md5_my(sign_str)
    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 类型的 str, 转化成, 字典
    res_dict = json.loads(html_bytes.decode('utf-8'))
    # print(html_bytes.decode('utf-8'))
    translate_res = res_dict['translateResult'][0][0]['tgt']
    return translate_res
if __name__=='__main__':
    ret=translate('成功')
    print(ret)

爬虫封装函数改进session版

from urllib import request, parse
from urllib.error import HTTPError, URLError
# 保存cookie
from http import cookiejar

class session(object):
    def __init__(self):
        cookie_object = cookiejar.CookieJar()
        # handler 对应着一个操作
        handler = request.HTTPCookieProcessor(cookie_object)
        # 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)

#a. get(url, headers=None)

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)
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
            form_str = parse.urlencode(form, encoding='utf-8')
            #print(form_str)
            form_bytes = form_str.encode('utf-8')
            req = request.Request(url, data=form_bytes, headers=headers)
        else:
            # GET
            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__':
    # url = 'http://fanyi.baidu.com/sug'
    # form = {
    #     'kw': '呵呵'
    # }
    # html_bytes = post(url, form=form)
    # print(html_bytes)

    url = 'http://www.baidu.com'
    html_byte = get(url)
    print(html_byte)

人人网session版

from tuozhan_all import session
import json
url = 'http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=2018721441132'
form = {
    'email': '18510556963',
    'icode': '',
    'origURL': 'http://www.renren.com/home',
    'domain': 'renren.com',
    'key_id': '1',
    'captcha_type': 'web_login',
    'password': '95cb2a1d59b918e0d16ab5d3535fb40103e4b546e651a3e3c99b91876927c78a',
    'rkey': 'a7bccfbafd7ee702247450942dff5611',
    'f': 'http%3A%2F%2Fwww.renren.com%2F966927992',
}
s = session()
html_bytes = s.post(url, form)
res_dict = json.loads(html_bytes.decode('utf-8'))
home_url = res_dict['homeUrl']
html_bytes = s.get(home_url)
print(html_bytes.decode('utf-8'))