金融爬虫思密达

# -*- codeing = utf-8 -*-
# @Time : 2020-6-30 11:19
# @Author : WwwYiNan
# @File : 浙江金融.py
# @Software : PyCharm

from selenium import webdriver
from selenium.webdriver.chrome.options import Options

options = Options()
options.headless = True
driver = webdriver.Chrome(executable_path=r'F:\GOOGLE下载\chromedriver_win32\chromedriver.exe', options=options)


def get_url(url):
    driver.get(url)
    data = driver.find_elements_by_css_selector('#form1 > div.ny_main.clearfix > div.ny_r > div.tzgg2 > ul > li')

    urls = []
    for i in data:
        # print(i.find_element_by_css_selector('li> a').get_attribute('href'))
        urls.append(i.find_element_by_css_selector('li> a').get_attribute('href'))
    return urls


def lyh(get_urls):
    driver.get(get_urls)

    zhengwen = driver.find_element_by_css_selector(
        '#form1 > div.ny_main.clearfix > div.ny_r > div.news_det.clearfix').text

    title = driver.find_element_by_css_selector('div.news_det.clearfix > p').text
    # zhengwen = driver.find_element_by_css_selector('#form1 > div.ny_main.clearfix > div.ny_r > div.about').text

    list = {
        '标题': title,
        "正文": zhengwen
    }

    return list


if __name__ == '__main__':
    for i in range(1, 2):
        url = 'http://www.zfc.edu.cn/tzgg.aspx?c_kind=2&c_kind2=3&c_kind3=&c_kind4=&keyn=&pageIndex=' + str(i)
        print(url)
        urls = get_url(url)

        for j in urls:
            print(lyh(j))