用Python怎样实现爬取门户网站，代码是什么-群英

上一篇：pytorch中的nn.Sequential(*net[3: 5])表示什么，怎么应用的下一篇：在Python中怎么实现员工基本数据的可视化效果

本篇内容介绍了“用Python怎样实现爬取门户网站，代码是什么”的有关知识，在实际项目的操作过程或是学习过程中，不少人都会遇到这样的问题，接下来就让小编带大家学习一下如何处理这些情况吧！希望大家仔细阅读，能够学有所成！

如何使用

每个文件夹下的代码就是对应平台的新闻爬虫

py 文件直接运行
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')

到此这篇关于“用Python怎样实现爬取门户网站，代码是什么”的文章就介绍到这了,更多相关内容请搜索群英网络以前的文章或继续浏览下面的相关文章，希望大家以后多多支持群英网络！