微博爬取数据

标签：sts   pos   拼接   val   XML   根据   des   rate   完成   

import requests
from urllib.parse import urlencode
from pyquery import PyQuery as pq
#from pymongo import MongoClient

base_url = ‘https://m.weibo.cn/api/container/getIndex?‘
headers = {
    ‘Host‘: ‘m.weibo.cn‘,   #服务器根据Host这一行中的值来确定本次请求的是哪个具体的网站
    ‘Referer‘: ‘https://m.weibo.cn/u/2830678474‘,  #从哪里来
    ‘User-Agent‘: ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36‘,
    ‘X-Requested-With‘: ‘XMLHttpRequest‘,
}

max_page = 10


def get_page(page):
    params = {
        ‘type‘: ‘uid‘,
        ‘value‘: ‘2830678474‘,
        ‘containerid‘: ‘1076032830678474‘,
        ‘page‘: page
    }
    url = base_url + urlencode(params)     #拼接url
    print("拼接完成的url",url)
    try:
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            #print(response.text)
            return response.json(), page
    except requests.ConnectionError as e:
        print(‘Error‘, e.args)


def parse_page(json, page: int):
    if json:
        print("json************json",json)
        items = json.get(‘data‘).get(‘cards‘)
        for index, item in enumerate(items):
            if page == 1 and index == 1:
                continue
            else:
                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


# def save_to_mongo(result):
#     if collection.insert(result):
#         print(‘Saved to Mongo‘)


if __name__ == ‘__main__‘:
    for page in range(1, max_page + 1):
        json = get_page(page)
        results = parse_page(*json)
        for result in results:
            print(result)
            #save_to_mongo(result)

微博爬取数据

标签：sts   pos   拼接   val   XML   根据   des   rate   完成   

原文地址：https://www.cnblogs.com/yuanjia8888/p/9999745.html