python爬取新闻门户网站的示例

时间:2022-07-01 12:04:22

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

?
1
2
import pengpai_news_spider
pengpai_news_spider.main()

示例代码

百度新闻

?
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
# -*- 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服务器之家其它相关文章!

原文链接:https://github.com/Python3Spiders/AllNewsSpider