python爬虫（五）之新出行汽车爬虫

news2024/10/5 19:11:09

python爬虫（五）之新出行汽车爬虫

接完最后一单，终于肝完了最后一个python爬虫——新出行爬虫，将https://www.xchuxing.com网站上所有的汽车爬虫全部抓取下来。

import requests
import json
import csv
from lxml import etree
import time


class Xchuxing:

    def __init__(self):
        self.article_list_pre_url = "https://www.xchuxing.com/official?category=1&page="
        self.start_page = 1
        self.end_page = 1000
        self.payload = {}
        self.article_list_headers = {
            'Accept': 'application/json, text/plain, */*',
            'Accept-Language': 'zh-CN,zh;q=0.9',
            'Cache-Control': 'no-cache',
            'Connection': 'keep-alive',
            'Cookie': 'community_new_sort=22af645d1859cb5ca6da0c484f1f37ea; Hm_lvt_55f107d825a4c4e989d543a8bf935508=1710252997; Hm_lpvt_55f107d825a4c4e989d543a8bf935508=1710253296',
            'Referer': 'https://www.xchuxing.com/official',
            'Sec-Fetch-Dest': 'empty',
            'Sec-Fetch-Mode': 'cors',
            'Sec-Fetch-Site': 'same-origin',
            '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',
            'X-Requested-With': 'XMLHttpRequest',
            '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': 'community_new_sort=22af645d1859cb5ca6da0c484f1f37ea; Hm_lvt_55f107d825a4c4e989d543a8bf935508=1710252997; Hm_lpvt_55f107d825a4c4e989d543a8bf935508=1710255840',
            'Referer': 'https://www.xchuxing.com/official',
            '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"'
        }

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

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

            for current_page in range(self.start_page, self.end_page):
                print("================> 当前第" + str(current_page) + "页，共" + str(self.end_page) + "页 ============")
                article_list_url = self.article_list_pre_url + str(current_page)
                text = self.get_request(article_list_url, headers=self.article_list_headers)
                data = json.loads(text)["data"]
                self.write_page(writer, data)

    def write_page(self, writer, data):
        for item in data:
            # print(item["title"])
            # print(item["author"]["username"])
            # print(item["created_at"])
            # 获取文章详情内容
            # https://www.xchuxing.com/article/116378
            article_url = "https://www.xchuxing.com/article/" + str(item["object_id"])
            text = self.get_request(article_url, headers=self.article_detail_headers)

            html = etree.HTML(text)
            result = html.xpath("normalize-space(//div[@class='content-main']/div[5])")
            # print(result)
            time_struct = time.localtime(item["created_at"])
            date = time.strftime("%Y-%m-%d %H:%M:%S", time_struct)

            row = [item["title"], item["author"]["username"], date, result]
            writer.writerow(row)
            print("===========> 当前文章 " + article_url + " 写入完毕", )


if __name__ == '__main__':
    xchuxing = Xchuxing()
    xchuxing.do_work()