常规动态网页爬取

1.抓取动态网页“http://www.ptpress.com.cn”内容，将新书推荐中生活板块的书籍书名、价格和作者爬取并保存。

import requests
import json
import openpyxlurl = 'https://www.ptpress.com.cn/recommendBook/getRecommendBookListForPortal?bookTagId=d5cbb56d-09ef-41f5-9110-ced741048f5f'
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 ''(KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36 Edg/95.0.1020.44','Cookie':'gr_user_id=796019e3-dc58-40f5-a6df-892a38008bcd; ''acw_tc=2760822416373059896443147efcf3dd457a5539d63a07fdafd12f3041cd93; ''JSESSIONID=A0FD72E84771D06417CF145392DAA679; ''gr_session_id_9311c428042bb76e=1a1d8cc2-0de9-4409-adc4-07de4cdb503f;'' gr_session_id_9311c428042bb76e_1a1d8cc2-0de9-4409-adc4-07de4cdb503f=true'
}
text_json = requests.get(url=url,headers=headers)
res = json.loads(text_json.content)
def save_execl(res):wb1 = openpyxl.Workbook()sheet = wb1.activesheet.title = "人民邮电新书推荐"title = ['书名', '作者', '价格']sheet.append(title)for re in res['data']:author, discountPrice = json_detail(re['bookId'])sheet.append([re['bookName'], author, discountPrice])wb1.save('生活类新书基本信息.xlsx')def json_detail(bookid):url = 'https://www.ptpress.com.cn/bookinfo/getBookDetailsById'bookid = bookidparams = {'bookId': bookid,}text_json = requests.post(url=url, headers=headers, params=params)res = json.loads(text_json.content)['data']Book_data = res['bookDetail']['data']author = res['author']discountPrice = res['discountPrice']print(res['bookName'], author, discountPrice)return author, discountPricesave_execl(res)

爬取结果：