89某头条搜索

仅供学习参考！！

控制台图

存入excel图（从新运行，会覆盖，建议重新命名）

完整代码

import requests
from urllib.parse import quote
import pandas as pd
import time
import json
import re


def collect(key, total):
    resLs = []
    for page in range(total):
        url = f'https://so.toutiao.com/search?keyword={quote(key)}&pd=information&dvpf=pc&page_num={page}'
        headers = {
            'User-Agent': ua,
            'Cookie': ck
        }
        res = requests.get(url=url, headers=headers).content.decode('utf-8')
        ex = 'data-for=s-result-json data-used-by=hydrate>(.*?)</script>'
        pattern = re.compile(ex)
        for dic in pattern.findall(res):
            try:
                dic = json.loads(dic)
                title = dic['data']['title']
                abstract = dic['data']['abstract']
                date = time.strftime('%Y-%m-%d', time.localtime(int(dic['data']['publish_time'])))
                source = dic['data']['source']
                comment = dic['data']['comment_count']
                href = dic['data']['source_url']
                record = {
                    'title': title,
                    'abstract': abstract,
                    'date': date,
                    'source': source,
                    'href': href,
                    'comment': comment
                }
                resLs.append(record)
                print(record)
            except KeyError:
                pass
            except Exception as e:
                print(str(e))
            time.sleep(1)
    pd.DataFrame(resLs).to_excel('今日头条搜索.xlsx', index=False, encoding='utf-8')


if __name__ == '__main__':
    ua = 'Mozilla/5.0(WindowsNT10.0;Win64;x64)AppleWebKit/537.36(KHTML,likeGecko)Chrome/91.0.4472.106Safari/537.36'
    ck = 'passport_csrf_token=72948754528a79a9bf062bf1733fc133; tt_webid=7078110223483389448; _S_DPR=1.25; _S_IPAD=0; MONITOR_WEB_ID=7078110223483389448; ttwid=1%7ChKYuO5fu4IwwB_lSa1vsppRwr8U2VaXqA7O3OhsuYpA%7C1648012935%7C5497cee960112e92e59f927c732a5b71043db6617e25e79f2af45faa8144898c; _S_WIN_WH=394_754'
    key = input("输入查询的关键字：")
    page = int(input("采集的页数:"))
    collect(key, page)