分享一些關於Python爬蟲的原始碼，需要的朋友可以自行領取

# -*- coding:utf-8 -*-

import time
import requests
from bs4 import BeautifulSoup


class JD_crawl:
    def __init__(self, username, password):
        self.essay-headers = {
                        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36'
                                      ' (KHTML, like Gecko) Chrome/62.0.3202.89 Safari/537.36',
                        'Referer': 'https://www.jd.com/',
                        }
        self.login_url = "https://passport.jd.com/new/login.aspx"
        self.post_url = "https://passport.jd.com/uc/loginService"
        self.auth_url = "https://passport.jd.com/uc/showAuthCode"
        self.session = requests.session()
        self.username = username
        self.password = password

    def get_login_info(self):
        html = self.session.get(self.login_url, essay-headers=self.essay-headers).content
        soup = BeautifulSoup(html, 'lxml')

        uuid = soup.select('#uuid')[0].get('value')
        eid = soup.select('#eid')[0].get('value')
        fp = soup.select('input[name="fp"]')[0].get('value')  # session id
        _t = soup.select('input[name="_t"]')[0].get('value')  # token
        login_type = soup.select('input[name="loginType"]')[0].get('value')
        pub_key = soup.select('input[name="pubKey"]')[0].get('value')
        sa_token = soup.select('input[name="sa_token"]')[0].get('value')

        auth_page = self.session.post(self.auth_url,
                                      data={'loginName': self.username, 'nloginpwd': self.password}).text
        if 'true' in auth_page:
            auth_code_url = soup.select('#JD_Verification1')[0].get('src2')
            auth_code = str(self.get_auth_img(auth_code_url))
        else:
            auth_code = ''

        data = {
            'uuid': uuid,
            'eid': eid,
            'fp': fp,
            '_t': _t,
            'loginType': login_type,
            'loginname': self.username,
            'nloginpwd': self.password,
            'chkRememberMe': True,
            'pubKey': pub_key,
            'sa_token': sa_token,
            'authcode': auth_code
            }
        return data

    def get_auth_img(self, url):
        auth_code_url = 'http:{}&yys;={}'.format(url, str(int(time.time()*1000)))
        auth_img = self.session.get(auth_code_url, essay-headers=self.essay-headers)
        with open('authcode.jpg', 'wb') as f:
            f.write(auth_img.content)
        code_typein = input('請根據下載圖片輸入驗證碼：')
        return code_typein

    def login(self):
        data = self.get_login_info()
        essay-headers = {
                    'Referer': self.post_url,
                    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36'
                                  ' (KHTML, like Gecko) Chrome/62.0.3202.89 Safari/537.36',
                    'X-Requested-With': 'XMLHttpRequest'
                  }
        try:
            login_page = self.session.post(self.post_url, data=data, essay-headers=essay-headers)
            print(login_page.text)
        except Exception as e:
            print(e)

        # self.session.cookies.clear()

    def shopping(self):
        login = self.session.post('https://cart.jd.com/cart.action', essay-headers=self.essay-headers)
        print(login.text)


if __name__ == '__main__':
    un = input('請輸入京東賬號：')
    pwd = input('請輸入京東密碼：')
    jd = JD_crawl(un, pwd)
    jd.login()
    jd.shopping()

import re
import requests
from lxml import etree
from onexima import Xima


def get_id():
    """獲取排行榜每一本書的資訊"""
    main_url = "https://www.ximalaya.com/shangye/top/"
    essay-headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36"
    }
    r = requests.get(main_url, essay-headers=essay-headers)
    # 獲取到當前頁面的xml資料
    html = etree.HTML(r.content.decode())
    # 得到每一本書的位置的資訊
    div_list = html.xpath("//div[contains(@class,'e-2997888007 rrc-album-item')]")
    all_lsit = []  # 待會把每一本書的音訊以字典形式放進串列當中
    for div in div_list:
        author = {}  # 建立一個串列, 我們要獲取書的id和書的名字, 並且一一對應
        r = div.xpath("./a/@href")[0]  # 獲取到當前書的id所在資訊, 資料為: /renwen/4859823/
        print(r)
        # 所以得透過正則把正確的id取出來, id是為了傳入正確的id, 得到正確的json資料
        author['id'] = re.search(r'\/.*?\/(.*)\/', r).group(1)
        author['book_name'] = div.xpath("./a/div[3]/div[1]/span/text()")[0]
        # 向串列中傳入每一個音訊的資訊
        all_lsit.append(author)
    print(all_lsit)
    return all_lsit


# 呼叫函式得到所有每一本書的資訊, 是一個串列型別
all_lsit = get_id()
for i in all_lsit:
    # 遍歷串列, 把每本書對應的id和對應的書名傳到類裡面去
    x = Xima(i['id'], i['book_name'])
    x.run()