|
| 1 | +# -*- coding: utf-8 -*- |
| 2 | +# 作者: inspurer(月小水长) |
| 3 | +# 创建时间: 2020/11/27 22:10 |
| 4 | +# 运行环境 Python3.6+ |
| 5 | +# github https://github.com/inspurer |
| 6 | +# qq邮箱 2391527690@qq.com |
| 7 | +# 微信公众号 月小水长(ID: inspurer) |
| 8 | +# 文件备注信息 todo |
| 9 | + |
| 10 | +import requests |
| 11 | + |
| 12 | +from datetime import datetime, timedelta |
| 13 | + |
| 14 | +from lxml import etree |
| 15 | + |
| 16 | +import csv |
| 17 | + |
| 18 | +import os |
| 19 | + |
| 20 | +from time import sleep |
| 21 | +from random import randint |
| 22 | + |
| 23 | + |
| 24 | +def parseTime(unformatedTime): |
| 25 | + if '分钟' in unformatedTime: |
| 26 | + minute = unformatedTime[:unformatedTime.find('分钟')] |
| 27 | + minute = timedelta(minutes=int(minute)) |
| 28 | + return (datetime.now() - |
| 29 | + minute).strftime('%Y-%m-%d %H:%M') |
| 30 | + elif '小时' in unformatedTime: |
| 31 | + hour = unformatedTime[:unformatedTime.find('小时')] |
| 32 | + hour = timedelta(hours=int(hour)) |
| 33 | + return (datetime.now() - |
| 34 | + hour).strftime('%Y-%m-%d %H:%M') |
| 35 | + else: |
| 36 | + return unformatedTime |
| 37 | + |
| 38 | + |
| 39 | +def dealHtml(html): |
| 40 | + results = html.xpath('//div[@class="result-op c-container xpath-log new-pmd"]') |
| 41 | + |
| 42 | + saveData = [] |
| 43 | + |
| 44 | + for result in results: |
| 45 | + title = result.xpath('.//h3/a')[0] |
| 46 | + title = title.xpath('string(.)').strip() |
| 47 | + |
| 48 | + summary = result.xpath('.//span[@class="c-font-normal c-color-text"]')[0] |
| 49 | + summary = summary.xpath('string(.)').strip() |
| 50 | + |
| 51 | + # ./ 是直接下级，.// 是直接/间接下级 |
| 52 | + infos = result.xpath('.//div[@class="news-source"]')[0] |
| 53 | + source, dateTime = infos.xpath(".//span[last()-1]/text()")[0], \ |
| 54 | + infos.xpath(".//span[last()]/text()")[0] |
| 55 | + |
| 56 | + dateTime = parseTime(dateTime) |
| 57 | + |
| 58 | + print('标题', title) |
| 59 | + print('来源', source) |
| 60 | + print('时间', dateTime) |
| 61 | + print('概要', summary) |
| 62 | + print('\n') |
| 63 | + |
| 64 | + saveData.append({ |
| 65 | + 'title': title, |
| 66 | + 'source': source, |
| 67 | + 'time': dateTime, |
| 68 | + 'summary': summary |
| 69 | + }) |
| 70 | + with open(fileName, 'a+', encoding='utf-8-sig', newline='') as f: |
| 71 | + writer = csv.writer(f) |
| 72 | + for row in saveData: |
| 73 | + writer.writerow([row['title'], row['source'], row['time'], row['summary']]) |
| 74 | + |
| 75 | + |
| 76 | +headers = { |
| 77 | + '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', |
| 78 | + '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' |
| 79 | +} |
| 80 | + |
| 81 | +url = 'https://www.baidu.com/s' |
| 82 | + |
| 83 | +params = { |
| 84 | + 'ie': 'utf-8', |
| 85 | + 'medium': 0, |
| 86 | + # rtt=4 按时间排序 rtt=1 按焦点排序 |
| 87 | + 'rtt': 1, |
| 88 | + 'bsst': 1, |
| 89 | + 'rsv_dl': 'news_t_sk', |
| 90 | + 'cl': 2, |
| 91 | + 'tn': 'news', |
| 92 | + 'rsv_bp': 1, |
| 93 | + 'oq': '', |
| 94 | + 'rsv_btype': 't', |
| 95 | + 'f': 8, |
| 96 | +} |
| 97 | + |
| 98 | + |
| 99 | +def doSpider(keyword, sortBy = 'focus'): |
| 100 | + ''' |
| 101 | + :param keyword: 搜索关键词 |
| 102 | + :param sortBy: 排序规则，可选：focus(按焦点排序），time(按时间排序），默认 focus |
| 103 | + :return: |
| 104 | + ''' |
| 105 | + global fileName |
| 106 | + fileName = '{}.csv'.format(keyword) |
| 107 | + |
| 108 | + if not os.path.exists(fileName): |
| 109 | + with open(fileName, 'w+', encoding='utf-8-sig', newline='') as f: |
| 110 | + writer = csv.writer(f) |
| 111 | + writer.writerow(['title', 'source', 'time', 'summary']) |
| 112 | + |
| 113 | + params['wd'] = keyword |
| 114 | + if sortBy == 'time': |
| 115 | + params['rtt'] = 4 |
| 116 | + |
| 117 | + response = requests.get(url=url, params=params, headers=headers) |
| 118 | + |
| 119 | + html = etree.HTML(response.text) |
| 120 | + |
| 121 | + dealHtml(html) |
| 122 | + |
| 123 | + total = html.xpath('//div[@id="header_top_bar"]/span/text()')[0] |
| 124 | + |
| 125 | + total = total.replace(',', '') |
| 126 | + |
| 127 | + total = int(total[7:-1]) |
| 128 | + |
| 129 | + pageNum = total // 10 |
| 130 | + |
| 131 | + for page in range(1, pageNum): |
| 132 | + print('第 {} 页\n\n'.format(page)) |
| 133 | + headers['Referer'] = response.url |
| 134 | + params['pn'] = page * 10 |
| 135 | + |
| 136 | + response = requests.get(url=url, headers=headers, params=params) |
| 137 | + |
| 138 | + html = etree.HTML(response.text) |
| 139 | + |
| 140 | + dealHtml(html) |
| 141 | + |
| 142 | + sleep(randint(2, 4)) |
| 143 | + ... |
| 144 | + |
| 145 | + |
| 146 | +if __name__ == "__main__": |
| 147 | + doSpider(keyword = '马保国', sortBy='focus') |
0 commit comments