python爬取新闻门户网站的示例

项目地址：

https://github.com/python3spiders/allnewsspider

如何使用

每个文件夹下的代码就是对应平台的新闻爬虫

1. py 文件直接运行
2. pyd 文件需要，假设为 pengpai_news_spider.pyd

将 pyd 文件下载到本地，新建项目，把 pyd 文件放进去

项目根目录下新建 runner.py，写入以下代码即可运行并抓取

import pengpai_news_spider
pengpai_news_spider.main()

示例代码

百度新闻

# -*- coding: utf-8 -*-
# 文件备注信息       如果遇到打不开的情况，可以先在浏览器打开一下百度搜索引擎

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 '分钟' in unformatedtime:
        minute = unformatedtime[:unformatedtime.find('分钟')]
        minute = timedelta(minutes=int(minute))
        return (datetime.now() -
                minute).strftime('%y-%m-%d %h:%m')
    elif '小时' in unformatedtime:
        hour = unformatedtime[:unformatedtime.find('小时')]
        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()

        # ./ 是直接下级，.// 是直接/间接下级
        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('标题', title)
        print('来源', source)
        print('时间', 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 按时间排序 rtt=1 按焦点排序
    '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: 搜索关键词
    :param sortby: 排序规则，可选：focus(按焦点排序），time(按时间排序），默认 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 {} 页\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 = '马保国', sortby='focus')

以上就是python爬取新闻门户网站的示例的详细内容，更多关于python爬取新闻门户网站的资料请关注其它相关文章！