# -*- coding: utf-8 -*-
import requests
from lxml import etree
import json
import csv
fp = open('./腾讯新闻.csv','w+', newline='', encoding='utf-8')
writer = csv.writer(fp)
writer.writerow(('标题', '更新时间', '出版时间', '网址', '评论数', '媒体', '类别', '主类别'))
def get_infos(self):
url = 'https://i.news.qq.com/trpc.qqnews_web.kv_srv.kv_srv_http_proxy/list?sub_srv_id=world&srv_id=pc&offset=0&limit=20&strategy=1&ext={%22pool%22:[%22high%22,%22top%22],%22is_filter%22:10,%22check_type%22:true}'
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.77 Safari/537..36 Edg/91.0.864.37'}
res = requests.get(url, headers=headers)
res.encoding = 'utf-8'
data = json.loads(res.content.decode("utf-8"))
titles = [i['title'] for i in data['data']['list']]
updates = [i['update_time'] for i in data['data']['list']]
publishs = [i['publish_time'] for i in data['data']['list']]
urls = [i['url'] for i in data['data']['list']]
comments = [i['comment_num'] for i in data['data']['list']]
medias = [i['media_name'] for i in data['data']['list']]
categorys = [i['category_cn'] for i in data['data']['list']]
sub_categorys = [i['sub_category_cn'] for i in data['data']['list']]
for title, update,publish,url,comment,media,category,sub_category in zip(titles,updates,publishs,urls,comments,medias,categorys,sub_categorys):
info = {
'标题': title,
'更新时间': update,
'出版时间': publish,
'网址': url,
'评论数': comment,
'媒体': media,
'类别': category,
'主类别': sub_category
}
print(info)
# writer.writerow([title, update, publish, url, comment, media, category, sub_category])
writer.writerow([title, update, publish, url, comment, media, category, sub_category])
#urls_info = ['https://i.news.qq.com/trpc.qqnews_web.kv_srv.kv_srv_http_proxy/list?sub_srv_id=world&srv_id=pc&offset={}&limit=20&strategy=1&ext={%22pool%22:[%22top%22],%22is_filter%22:2,%22check_type%22:true}'.format(str(i)) for i in range(0, 200, 20)]
if __name__ == '__main__':
urls_info = [f'https://i.news.qq.com/trpc.qqnews_web.kv_srv.kv_srv_http_proxy/list?sub_srv_id=world&srv_id=pc&offset={i}&limit=20&strategy=1&ext=' + '{%22pool%22:[%22top%22],%22is_filter%22:2,%22check_type%22:true}' for i in range(0, 200, 20)]
for urls_info1 in urls_info:
get_infos(urls_info)
fp.close()
求大佬教一下，为什么从腾讯新闻网爬下来的数据 csv写不进，把代码发我一下，十分感谢！！！
在同级目录下创建"腾讯新闻.csv"
把fp = open('./腾讯新闻.csv','w+', newline='', encoding='utf-8')
改成fp = open('腾讯新闻.csv','w+', newline='', encoding='utf-8')
之后运行试试。
简而言之就是第6行的路径不对，同级目录不用加 ./
您好，我是有问必答小助手，您的问题已经有小伙伴解答了，您看下是否解决，可以追评进行沟通哦~
如果有您比较满意的答案 / 帮您提供解决思路的答案，可以点击【采纳】按钮，给回答的小伙伴一些鼓励哦～～
ps:问答VIP仅需29元，即可享受5次/月 有问必答服务，了解详情>>>https://vip.csdn.net/askvip?utm_source=1146287632