import json
import requests
from requests.exceptions import RequestException
import time
from pyquery import PyQuery as pq
#链接检测返回
def get_one_page(url):
try:
headers = {
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 11_2_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.114 Safari/537.36'
}
response = requests.get(url,headers=headers)
response.encoding = 'utf-8'
if response.status_code == 200:
return response.text
return None
except RequestException:
return None
#解析网页
def parse_one_page(html):
doc = pq(html)
results = []
for i in doc('.list_009 li'):
sub_d = pq(i)
item ={
'nero':sub_d('a').text(),
'shij':sub_d('span').text()
}
results.append(item)
#保存文件
def write_to_file(content):
with open('result.txt','a',encoding='utf-8') as f:
f.write(json.dumps(content,ensure_ascii=False)+'\n')
#启动函数
def main(offset):
url = 'https://finance.sina.com.cn/roll/index.d.html?lid=1008&page={}'.format(offset)
html = get_one_page(url)
#print(html)
for item in parse_one_page(html):
print(item)
write_to_file(item)
#write_to_file(html)
#分页循环
if __name__ == '__main__':
for i in range(1,5):
main(offset=i+1)
print(f"==========正在采集第{i}页==========")
time.sleep(2)
print('爬取完成')
错误代码 TypeError: 'NoneType' object is not iterable