day_5：Ajax数据爬取

浏览器调试模式下Network选项XHR筛选出Ajax请求（Request Headers的X-Requested-With:XMLHttpRequest）

#  个人微博爬取，存入csv（字段：时间、评论、转发、点赞、内容）
import requests
import json
import csv

def get_html(path, page):
    params = {
        'type': 'uid',
        'value': 2830678474,
        'containerid': 1076032830678474,
        'page': page
    }
    headers = {
        'Referer': 'https://m.weibo.cn/u/2830678474',
        'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1'
    }
    try:
        r = requests.get(url=path, params=params, headers=headers)
        r.raise_for_status()
        return r.text
    except:
        print('status_code is not 200')
        return None

def detail_html(txt):
    data = txt.get('data')
    page = data.get('cardlistInfo').get('page')
    cards = data.get('cards')
    with open('weibo.csv', 'a', encoding='utf-8') as csvfile:
        fieldnames = ['created_at', 'attitudes_count', 'comments_count', 'reposts_count', 'content']
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
        for card in cards:
            if card.get('card_type') != 9:  # 去除广告
                continue
            mblog = card.get('mblog')
            data = {
                'created_at' : mblog.get('created_at'),  # 创建时间
                'attitudes_count': mblog.get('attitudes_count'),  # 点赞数量
                'comments_count': mblog.get('comments_count'),  # 评论数量
                'reposts_count': mblog.get('reposts_count'),  # 转发数量
                'content': mblog.get('text')  # 文本内容
            }
            writer.writerow(data)
    return page

if __name__ == '__main__':
    path = 'https://m.weibo.cn/api/container/getIndex'
    page = 1
    with open('weibo.csv', 'w', encoding='utf-8') as csvfile:
        fieldnames = ['created_at', 'attitudes_count', 'comments_count', 'reposts_count', 'content']
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
        writer.writeheader()
    while page:
        txt = json.loads(get_html(path, page))
        if txt:
            page = detail_html(txt)
            print(page)