2019-01-26 基金项目标题一键式下载

为日常随笔,仅是自己日常工作的随手一记,并非系统性的知识介绍,如有不慎浏览至此的同学,可以屏蔽。

import os

from docx import Document
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait

os.chdir(r'C:\Users\MTC\Desktop\New')

if not os.path.exists(r'基金.docx'):
    document=Document()
    document.save(r'基金.docx')

browser=webdriver.Chrome()
browser.get('http://fund.sciencenet.cn/')

document=Document(r'基金.docx')
Num=38

page = 0
for i in range(0, Num):
    page = page + 1
    b = browser.find_elements_by_class_name('t')
    for i in range(1, len(b)):
        print(b[i].text)
        paragraph = document.add_paragraph(b[i].text)
        paragraph.runs[0].bold = True
        document.save(r'基金.docx')

        # b[i].find_elements_by_tag_name('a')[0].click()
        # Wait=WebDriverWait(browser,20)
        # Wait.until(EC.presence_of_all_elements_located(By.XPath,'/html/body/div[4]/p'))
        #
        # c = browser.find_elements_by_class_name("jben")
        # for ii in c:
        #     document.add_paragraph(ii.text)

#         b[i].find_elements_by_tag_name('a')[0].click()
#         time.sleep(5)
#         c = browser.find_elements_by_class_name("jben")
#         content_xia=c.text
#         document.add_paragraph(content_xia)
# browser.back()

    bnts=browser.find_elements_by_class_name('btn')
    for iii in bnts:
        if iii.text=='下一页':
            print(iii.text)
            iii.click()
            break
    Wait = WebDriverWait(browser, 20)
    Wait.until(EC.presence_of_all_elements_located((By.XPATH, '//*[@id="ft"]/span[3]')))

2019-1-26
办公室散记

你可能感兴趣的:(2019-01-26 基金项目标题一键式下载)