python爬虫(一)之 抓取极氪网站汽车文章

极氪汽车文章爬虫

闲来没事,将极氪网站的汽车文章吃干抹尽,全部抓取到本地,还是有点小小的难度。不能抓取太快,太快容易被封禁IP,不过就算被封了问题也不大,大不了重启路由器,然后你的IP里面又是一条好汉,又可以在网络随心所欲地抓取数据。

python 复制代码
import random
import requests
import json
import csv
from lxml import etree
import time
import base64
import re
from Crypto.Cipher import AES

"""
极氪爬虫逆向

https://blog.csdn.net/2301_79445611/article/details/133840084

"""


class Kr36:

    def __init__(self):
        self.article_list_pre_url = "https://gateway.36kr.com/api/mis/nav/ifm/subNav/flow"

        self.start_page = 1
        self.end_page = 1000
        self.init_page_callback = "eyJmaXJzdElkIjo0NTIzNzYyLCJsYXN0SWQiOjQ1MjIzOTAsImZpcnN0Q3JlYXRlVGltZSI6MTcxMDQxODU0MjA2NywibGFzdENyZWF0ZVRpbWUiOjE3MTAzMjk5MTM0MTl9"
        self.payload = json.dumps({
            "partner_id": "web",
            "timestamp": 1710253726028,
            "param": {
                "subnavType": 1,
                "subnavNick": "travel",
                "pageSize": 30,
                "pageEvent": 1,
                "pageCallback": "eyJmaXJzdElkIjo0NTE5NDg3LCJsYXN0SWQiOjQ1MTc1NzksImZpcnN0Q3JlYXRlVGltZSI6MTcxMDEzMDE5OTM4MywibGFzdENyZWF0ZVRpbWUiOjE3MDk4NTUyMzkxMzl9",
                "siteId": 1,
                "platformId": 2
            }
        })

        self.article_list_headers = {
            'Accept': '*/*',
            'Accept-Language': 'zh-CN,zh;q=0.9',
            'Connection': 'keep-alive',
            'Content-Type': 'application/json',
            'Cookie': 'sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%2218e330f24e210f-09e7e5136418ef-26001b51-1821369-18e330f24e3257b%22%2C%22%24device_id%22%3A%2218e330f24e210f-09e7e5136418ef-26001b51-1821369-18e330f24e3257b%22%2C%22props%22%3A%7B%22%24latest_traffic_source_type%22%3A%22%E7%9B%B4%E6%8E%A5%E6%B5%81%E9%87%8F%22%2C%22%24latest_referrer%22%3A%22%22%2C%22%24latest_referrer_host%22%3A%22%22%2C%22%24latest_search_keyword%22%3A%22%E6%9C%AA%E5%8F%96%E5%88%B0%E5%80%BC_%E7%9B%B4%E6%8E%A5%E6%89%93%E5%BC%80%22%7D%7D; tfstk=enSMvVNZXN8175m5p1K_xdJHfjzdCftXwsnvMnd48BRIbq59kwAcT6ANBtefiE5dimB9XtCng_CY1EesXI5HfMQtDCF6mt5Jm7F82uB1CIt4w7CpcU8wcEV4JbERCOMEIjyR8unD7DJAc9HIGUqPYrLyZYLloFBmJpdPQCWOBMl2-V69tFYhAdXHaOur0mSHIFjrr2urNOnXL-IElqTwdpARo9nzs4osO423K4Ze7p9_xJ2nlqTwdpA8KJ0r8FJBCkf..; Hm_lvt_1684191ccae0314c6254306a8333d090=1710253616,1710345937,1710421835; Hm_lvt_713123c60a0e86982326bae1a51083e1=1710253616,1710345937,1710421835; aliyungf_tc=4c273ea1e0ec1ba7c726c1d40e9f785731cff0f77ce5ac27f88ffeb1a6079cab; acw_tc=1a0c398517104218376678635e141118f68f5ec0ce2ac3421247f3e3c09817; Hm_lpvt_1684191ccae0314c6254306a8333d090=1710421897; Hm_lpvt_713123c60a0e86982326bae1a51083e1=1710421897',
            'Origin': 'https://36kr.com',
            'Referer': 'https://36kr.com/',
            'Sec-Fetch-Dest': 'empty',
            'Sec-Fetch-Mode': 'cors',
            'Sec-Fetch-Site': 'same-site',
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36',
            'sec-ch-ua': '"Chromium";v="122", "Not(A:Brand";v="24", "Google Chrome";v="122"',
            'sec-ch-ua-mobile': '?0',
            'sec-ch-ua-platform': '"Windows"'
        }

        self.article_detail_headers = {
            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
            'Accept-Language': 'zh-CN,zh;q=0.9',
            'Cache-Control': 'max-age=0',
            'Connection': 'keep-alive',
            'Cookie': 'sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%2218e330f24e210f-09e7e5136418ef-26001b51-1821369-18e330f24e3257b%22%2C%22%24device_id%22%3A%2218e330f24e210f-09e7e5136418ef-26001b51-1821369-18e330f24e3257b%22%2C%22props%22%3A%7B%22%24latest_traffic_source_type%22%3A%22%E7%9B%B4%E6%8E%A5%E6%B5%81%E9%87%8F%22%2C%22%24latest_referrer%22%3A%22%22%2C%22%24latest_referrer_host%22%3A%22%22%2C%22%24latest_search_keyword%22%3A%22%E6%9C%AA%E5%8F%96%E5%88%B0%E5%80%BC_%E7%9B%B4%E6%8E%A5%E6%89%93%E5%BC%80%22%7D%7D; tfstk=enSMvVNZXN8175m5p1K_xdJHfjzdCftXwsnvMnd48BRIbq59kwAcT6ANBtefiE5dimB9XtCng_CY1EesXI5HfMQtDCF6mt5Jm7F82uB1CIt4w7CpcU8wcEV4JbERCOMEIjyR8unD7DJAc9HIGUqPYrLyZYLloFBmJpdPQCWOBMl2-V69tFYhAdXHaOur0mSHIFjrr2urNOnXL-IElqTwdpARo9nzs4osO423K4Ze7p9_xJ2nlqTwdpA8KJ0r8FJBCkf..; aliyungf_tc=c8a95eb5a40ff7daafa6a84507110db651dad31ea165d934af3ec32b3f6514cf; acw_tc=ac11000117104218364426625e82f18159f99e101f9e32e840da085962de21; Hm_lvt_1684191ccae0314c6254306a8333d090=1710253616,1710345937,1710421835; Hm_lvt_713123c60a0e86982326bae1a51083e1=1710253616,1710345937,1710421835; Hm_lpvt_1684191ccae0314c6254306a8333d090=1710421976; Hm_lpvt_713123c60a0e86982326bae1a51083e1=1710421976; SERVERID=6754aaff36cb16c614a357bbc08228ea|1710421983|1710421837',
            'Sec-Fetch-Dest': 'document',
            'Sec-Fetch-Mode': 'navigate',
            'Sec-Fetch-Site': 'same-origin',
            'Sec-Fetch-User': '?1',
            'Upgrade-Insecure-Requests': '1',
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36',
            'sec-ch-ua': '"Chromium";v="122", "Not(A:Brand";v="24", "Google Chrome";v="122"',
            'sec-ch-ua-mobile': '?0',
            'sec-ch-ua-platform': '"Windows"'
        }

        self.cookies = {
            "sensorsdata2015jssdkcross": "^%^7B^%^22distinct_id^%^22^%^3A^%^2218b2931b25d63d-08aa76c3e8a47a-78505770-1821369-18b2931b25e11b9^%^22^%^2C^%^22^%^24device_id^%^22^%^3A^%^2218b2931b25d63d-08aa76c3e8a47a-78505770-1821369-18b2931b25e11b9^%^22^%^2C^%^22props^%^22^%^3A^%^7B^%^22^%^24latest_traffic_source_type^%^22^%^3A^%^22^%^E7^%^9B^%^B4^%^E6^%^8E^%^A5^%^E6^%^B5^%^81^%^E9^%^87^%^8F^%^22^%^2C^%^22^%^24latest_referrer^%^22^%^3A^%^22^%^22^%^2C^%^22^%^24latest_referrer_host^%^22^%^3A^%^22^%^22^%^2C^%^22^%^24latest_search_keyword^%^22^%^3A^%^22^%^E6^%^9C^%^AA^%^E5^%^8F^%^96^%^E5^%^88^%^B0^%^E5^%^80^%^BC_^%^E7^%^9B^%^B4^%^E6^%^8E^%^A5^%^E6^%^89^%^93^%^E5^%^BC^%^80^%^22^%^7D^%^7D",
            "aliyungf_tc": "87a15f620fd2d71d70704946aa353992ba8148f24a896fdd26a3f2dda630d053",
            "acw_tc": "0a6fd1ef16973374951548793e6f60efb7406e5628b6676540af7b96b8de7d",
            "Hm_lvt_1684191ccae0314c6254306a8333d090": "1697203204,1697337496",
            "Hm_lvt_713123c60a0e86982326bae1a51083e1": "1697203204,1697337496",
            "Hm_lpvt_713123c60a0e86982326bae1a51083e1": "1697337578",
            "Hm_lpvt_1684191ccae0314c6254306a8333d090": "1697337578",
            "SERVERID": "d36083915ff24d6bb8cb3b8490c52181^|1697337581^|1697337496"
        }

    def post_request(self, url, headers, payload):
        response = requests.request("POST", url, headers=headers, data=payload)
        return response.text

    def get_request(self, url, headers, cookies):
        response = requests.get(url, headers=headers, cookies=cookies)
        return response.text

    def do_work(self):
        with open('36kr.csv', 'w', newline='', encoding='utf-8-sig') as file:
            writer = csv.writer(file)
            csv_title = ["标题", "作者", "发布时间", "原文地址", "正文"]
            writer.writerow(csv_title)

            page_no = 1
            pageCallback = self.init_page_callback
            while True:
                print("================> 当前第" + str(page_no) + "页 ============")
                payload = json.dumps({
                    "partner_id": "web",
                    "timestamp": int(round(time.time() * 1000)),
                    "param": {
                        "subnavType": 1,
                        "subnavNick": "travel",
                        "pageSize": 30,
                        "pageEvent": 1,
                        "pageCallback": pageCallback,
                        "siteId": 1,
                        "platformId": 2
                    }
                })
                # seconds = random.randint(30, 60)
                # time.sleep(seconds)
                text = self.post_request(self.article_list_pre_url, headers=self.article_list_headers, payload=payload)
                data = json.loads(text)["data"]
                pageCallback = data["pageCallback"]
                itemList = data["itemList"]
                self.write_page(writer, itemList)

                page_no += 1

    def write_page(self, writer, itemList):
        for item in itemList:
            # print(item["title"])
            # print(item["author"]["username"])
            # print(item["created_at"])
            # 获取文章详情内容
            # https://36kr.com/p/2686487273459590
            article_url = "https://36kr.com/p/" + str(item["itemId"])
            text = self.get_request(article_url, headers=self.article_detail_headers, cookies=self.cookies)

            tree = etree.HTML(text)
            data = tree.xpath('/html/body/script/text()')[0]
            baase64_data = re.findall('.*?state":"(.*?)","', data)[0]
            key = "efabccee-b754-4c".encode('utf-8')
            aes = AES.new(key, AES.MODE_ECB)
            data = aes.decrypt(base64.b64decode(baase64_data))
            decode_date = data.decode()
            replace_data = decode_date[0: decode_date.rfind('}') + 1]
            # print(replace_data)
            json_data = json.loads(replace_data)
            article_detail_data = json_data["articleDetail"]["articleDetailData"]
            # print(article_detail_data)

            time_struct = time.localtime(int(item["templateMaterial"]["publishTime"] / 1000))
            date = time.strftime("%Y-%m-%d %H:%M:%S", time_struct)

            row = [item["templateMaterial"]["widgetTitle"], item["templateMaterial"]["authorName"], article_url, date,
                   article_detail_data["data"]["widgetContent"]]
            writer.writerow(row)
            seconds = random.randint(20, 60)
            print("===========> 当前文章 " + article_url + " 写入完毕,等待" + str(seconds) + "秒继续")
            time.sleep(seconds)


if __name__ == '__main__':
    kr36 = Kr36()
    kr36.do_work()

上面即为爬虫代码,拿到代码之后可能没法直接运行,如果运行出错大概的原因可能有如下几种,首先可能为相应的包没有安装,其次可能代码中的cookie已发生过期,这两个问题都比较简单,在此不再赘述。解决上面的问题之后即可直接运行代码,耐心的登上个一段时间,就可以拿到你想要的数据啦。

最终生成的文件为一个CSV文件,名称为36kr.csv,存放在当前目录下。

写在最后

代码精选(www.codehuber.com),程序员的终身学习网站已上线!

如果这篇【文章】有帮助到你,希望可以给【JavaGPT】点个赞👍,创作不易,如果有对【后端技术 】、【前端领域 】感兴趣的小可爱,也欢迎关注❤️❤️❤️ 【JavaGPT】❤️❤️❤️,我将会给你带来巨大的【收获与惊喜】💝💝💝!

相关推荐
千天夜3 分钟前
使用UDP协议传输视频流!(分片、缓存)
python·网络协议·udp·视频流
测试界的酸菜鱼6 分钟前
Python 大数据展示屏实例
大数据·开发语言·python
羊小猪~~10 分钟前
神经网络基础--什么是正向传播??什么是方向传播??
人工智能·pytorch·python·深度学习·神经网络·算法·机器学习
放飞自我的Coder40 分钟前
【python ROUGE BLEU jiaba.cut NLP常用的指标计算】
python·自然语言处理·bleu·rouge·jieba分词
正义的彬彬侠1 小时前
【scikit-learn 1.2版本后】sklearn.datasets中load_boston报错 使用 fetch_openml 函数来加载波士顿房价
python·机器学习·sklearn
张小生1801 小时前
PyCharm中 argparse 库 的使用方法
python·pycharm
秃头佛爷1 小时前
Python使用PDF相关组件案例详解
python
Dxy12393102161 小时前
python下载pdf
数据库·python·pdf
叶知安1 小时前
如何用pycharm连接sagemath?
ide·python·pycharm
weixin_432702261 小时前
代码随想录算法训练营第五十五天|图论理论基础
数据结构·python·算法·深度优先·图论