用request爬取腾讯新闻

最新推荐文章于 2024-05-20 20:26:39 发布

和小刘的岁岁年年370

最新推荐文章于 2024-05-20 20:26:39 发布

阅读量272

点赞数 2

文章标签： python

本文链接：https://blog.csdn.net/weixin_68174842/article/details/125470088

版权

import requests
import json
import xlwt
import os

headers = {
    'referer': 'https://news.qq.com/',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.5060.53 Safari/537.36 Edg/103.0.1264.37'
}
rows = 0  # 行数


def getPage(url):
    try:
        re = requests.get(url, headers=headers)
        re.encoding = re.apparent_encoding
        return json.loads(re.text)
    except:
        print(re.status_code)

def parse_news(text):
    global rows
    try:
        content = text['data']['list']
    except:
        content = text['data']
    for item in content:
        source = item['url']
        title = item['title']
        sheet.write(rows, 0, title)
        sheet.write(rows, 1, source)
        rows += 1


if __name__ == '__main__':
    today_news_url = 'https://i.news.qq.com/trpc.qqnews_web.pc_base_srv.base_http_proxy/NinjaPageContentSync?pull_urls=news_top_2018'
    today_topic_url = 'https://i.news.qq.com/trpc.qqnews_web.pc_base_srv.base_http_proxy/NinjaPageContentSync?pull_urls=today_topic_2018'
    Excel_book = xlwt.Workbook()

    sheet = Excel_book.add_sheet('腾讯新闻')

    print("开始获取今日要闻>>>")
    today_news = getPage(today_news_url)
    sheet.write(rows, 0, '以下为今日要闻')
    rows += 1
    parse_news(today_news)
    print("...今日要闻获取完毕")
    print("开始获取今日话题>>>")
    today_topic = getPage(today_topic_url)
    sheet.write(rows, 0, "以下为今日话题")
    rows += 1
    parse_news(today_topic)
    print("...今日话题获取完毕")
    page = int(input("请输入你想获得的热点精选页数："))
    print("开始获取热点精选>>>")
    sheet.write(rows, 0, "以下为热点精选")
    rows += 1
    for i in range(page):
        hot_news_url = 'https://i.news.qq.com/trpc.qqnews_web.kv_srv.kv_srv_http_proxy/list?sub_srv_id=24hours&srv_id=pc&offset=' + str(
            i * 20) + '&limit=20&strategy=1&ext={%22pool%22:[%22top%22],%22is_filter%22:7,%22check_type%22:true}'
        hot_news = getPage(hot_news_url)
        parse_news(hot_news)
        print("...第%d页获取完毕" % (i + 1))
    Excel_book.save('09_腾讯新闻.xls')
    print("保存完毕！路径为{}\\09_腾讯新闻.xls".format(os.getcwd()))