爬虫实战（证券交易）

#链接
url="http://www.cninfo.com.cn/new/fulltextSearch?notautosubmit=&keyWord=%E5%B9%B3%E5%AE%89%E9%93%B6%E8%A1%8C%E4%BE%9B%E5%BA%94%E9%93%BE%E9%87%91%E8%9E%8D%E5%B9%B3%E5%8F%B0"

如图：

但是获取不到数据？

方法：刷新获取链接文本
如图：

结果如图：

然后json处理或者正则匹配

import csv
import random
from lxml import etree
from mouse import move,click
from bs4 import BeautifulSoup
from selenium import webdriver
from pyquery import PyQuery as pq
import time
import re
# from selenium.webdriver.support import expected_conditions as EC
# from selenium.webdriver.support.wait import WebDriverWait
# from selenium.webdriver.common.by import By
# from selenium.webdriver import Chrome, ChromeOptions
# from selenium.webdriver.chrome.options import Options
# from selenium.webdriver.common.keys import Keys

path = '.chromedriver.exe'
browser = webdriver.Chrome(executable_path=path)
import pandas as pd
wrong=[]
data=pd.read_csv("全部A股12(1).csv",encoding="gbk")
for j in range(2506,3001):
    id= data.iloc[j]["证券代码"].split(".")[0]
    name=data.iloc[j]["证券名称"]+"供应链金融战略联盟"
    num=0
    for i in range(1,10):
        url = 'http://www.cninfo.com.cn/new/fulltextSearch/full?searchkey={}&sdate=&edate=&isfulltext=true&sortName=nothing&sortType=desc&pageNum={}'.format(name,i)
        browser.get(url)
        browser.maximize_window()
        time.sleep(2)
        
        source = browser.page_source
        titles = re.findall(r'"secCode":"(.*?)","secName":"(.*?)","orgId":"(.*?)","announcementId":"(.*?)","announcementTitle":"(.*?)","announcementTime":(.*?),"adjunctUrl":"(.*?)","adjunctSize":(.*?)"announcementContent":"(.*?)","orgName"',source)
        
        for t in titles:
            datas=[]
            new_id=t[0]
            if id==new_id:
                times=int(t[6].split("/")[1].split("-")[0])
                if times<=2021 and times>=2009:
                    
                    text=pq(pq(t[4]+t[8]).text()).text()
                    datas.append(new_id)
                    datas.append(text)
                    datas.append(times)
                    with open('供应链金融战略联盟新.csv', 'a', newline='', encoding='utf-8-sig') as fp:
                        writer = csv.writer(fp)
                        writer.writerow(datas)
                    print(t)
                    num=num+1
            if num>=15:
                
                break
            if num<15:
                wrong.append(data.iloc[j]["证券名称"])
                print(name,num)


# self.titles = re.findall(r'target="_blank">(.*?)',self.page)
#         for title in self.titles:

数据链接：https://pan.baidu.com/s/1Ekm0LlilTweM62gtXGCB3A
提取码：pwhk