python爬取新聞門戶網站的示例
項目地址:
https://github.com/Python3Spiders/AllNewsSpider
如何使用
每個文件夾下的代碼就是對應平臺的新聞爬蟲
- py 文件直接運行
- pyd 文件需要,假設為 pengpai_news_spider.pyd
將 pyd 文件下載到本地,新建項目,把 pyd 文件放進去
項目根目錄下新建 runner.py,寫入以下代碼即可運行並抓取
import pengpai_news_spider pengpai_news_spider.main()
示例代碼
百度新聞
# -*- coding: utf-8 -*- # 文件備註信息 如果遇到打不開的情況,可以先在瀏覽器打開一下百度搜索引擎 import requests from datetime import datetime, timedelta from lxml import etree import csv import os from time import sleep from random import randint def parseTime(unformatedTime): if '分鐘' in unformatedTime: minute = unformatedTime[:unformatedTime.find('分鐘')] minute = timedelta(minutes=int(minute)) return (datetime.now() - minute).strftime('%Y-%m-%d %H:%M') elif '小時' in unformatedTime: hour = unformatedTime[:unformatedTime.find('小時')] hour = timedelta(hours=int(hour)) return (datetime.now() - hour).strftime('%Y-%m-%d %H:%M') else: return unformatedTime def dealHtml(html): results = html.xpath('//div[@class="result-op c-container xpath-log new-pmd"]') saveData = [] for result in results: title = result.xpath('.//h3/a')[0] title = title.xpath('string(.)').strip() summary = result.xpath('.//span[@class="c-font-normal c-color-text"]')[0] summary = summary.xpath('string(.)').strip() # ./ 是直接下級,.// 是直接/間接下級 infos = result.xpath('.//div[@class="news-source"]')[0] source, dateTime = infos.xpath(".//span[last()-1]/text()")[0], \ infos.xpath(".//span[last()]/text()")[0] dateTime = parseTime(dateTime) print('標題', title) print('來源', source) print('時間', dateTime) print('概要', summary) print('\n') saveData.append({ 'title': title, 'source': source, 'time': dateTime, 'summary': summary }) with open(fileName, 'a+', encoding='utf-8-sig', newline='') as f: writer = csv.writer(f) for row in saveData: writer.writerow([row['title'], row['source'], row['time'], row['summary']]) headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36', 'Referer': 'https://www.baidu.com/s?rtt=1&bsst=1&cl=2&tn=news&word=%B0%D9%B6%C8%D0%C2%CE%C5&fr=zhidao' } url = 'https://www.baidu.com/s' params = { 'ie': 'utf-8', 'medium': 0, # rtt=4 按時間排序 rtt=1 按焦點排序 'rtt': 1, 'bsst': 1, 'rsv_dl': 'news_t_sk', 'cl': 2, 'tn': 'news', 'rsv_bp': 1, 'oq': '', 'rsv_btype': 't', 'f': 8, } def doSpider(keyword, sortBy = 'focus'): ''' :param keyword: 搜索關鍵詞 :param sortBy: 排序規則,可選:focus(按焦點排序),time(按時間排序),默認 focus :return: ''' global fileName fileName = '{}.csv'.format(keyword) if not os.path.exists(fileName): with open(fileName, 'w+', encoding='utf-8-sig', newline='') as f: writer = csv.writer(f) writer.writerow(['title', 'source', 'time', 'summary']) params['wd'] = keyword if sortBy == 'time': params['rtt'] = 4 response = requests.get(url=url, params=params, headers=headers) html = etree.HTML(response.text) dealHtml(html) total = html.xpath('//div[@id="header_top_bar"]/span/text()')[0] total = total.replace(',', '') total = int(total[7:-1]) pageNum = total // 10 for page in range(1, pageNum): print('第 {} 頁\n\n'.format(page)) headers['Referer'] = response.url params['pn'] = page * 10 response = requests.get(url=url, headers=headers, params=params) html = etree.HTML(response.text) dealHtml(html) sleep(randint(2, 4)) ... if __name__ == "__main__": doSpider(keyword = '馬保國', sortBy='focus')
以上就是python爬取新聞門戶網站的示例的詳細內容,更多關於python爬取新聞門戶網站的資料請關註WalkonNet其它相關文章!
推薦閱讀:
- python使用xpath獲取頁面元素的使用
- 教你如何利用python3爬蟲爬取漫畫島-非人哉漫畫
- python百行代碼實現漢服圈圖片爬取
- Python 京東雲無線寶消息推送功能
- 用python實現爬取奧特曼圖片實例