import requests
from urllib.parse import urlencode
from pyquery import PyQuery as pq
base_url = 'https://m.weibo.cn/api/container/getIndex?'
headers = {
'Referer': 'https://m.weibo.cn/u/2830678474',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
'x-requested-with': 'XMLHttpRequest',
}
def get_page(page):
params = {
'type': 'uid',
'value': '2830678474',
'containerid': '1076032830678474',
'page': page
}
url = base_url + urlencode(params)
try:
response = requests.get(url, headers=headers)
if response.status_code == 200:
return response.json()
except requests.ConnectionError as e:
print('Error', e.args)
def parse_page(json):
if json:
items = json.get('data').get('cards')
for item in items:
if item.get('mblog'):
item = item.get('mblog')
weibo = {}
weibo['id'] = item.get('id')
weibo['text'] = pq(item.get('text')).text()
weibo['attitudes'] = item.get('attitudes_count')
weibo['comments'] = item.get('comments_count')
weibo['reposts'] = item.get('reposts_count')
yield weibo
if __name__ == '__main__':
for page in range(1, 11):
json = get_page(page)
results = parse_page(json)
for result in results:
print(result)
代码参照了崔庆才老师的,但是在运行的时候出现了错误:TypeError: 'NoneType' object is not iterable
找了好久,才发现部分数据里面没有mblog这个key,所以在使用item.get('mblog')时,返回的数据为None。然后主动判断下item.get('mblog')是否为空,就可以搞定了。
Ajax数据爬取之微博m站(错误:TypeError: 'NoneType' object is not iterable)
最新推荐文章于 2024-10-23 19:09:34 发布