-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
5 changed files
with
146 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
File renamed without changes.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,139 @@ | ||
| { | ||
| "cells": [ | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": { | ||
| "ExecuteTime": { | ||
| "end_time": "2020-04-02T12:51:15.439691Z", | ||
| "start_time": "2020-04-02T12:51:15.436872Z" | ||
| } | ||
| }, | ||
| "outputs": [], | ||
| "source": [ | ||
| "import requests\n", | ||
| "from bs4 import BeautifulSoup as bs\n", | ||
| "from selenium import webdriver\n", | ||
| "import time" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": { | ||
| "ExecuteTime": { | ||
| "end_time": "2020-04-02T12:48:15.750997Z", | ||
| "start_time": "2020-04-02T12:48:15.748665Z" | ||
| } | ||
| }, | ||
| "outputs": [], | ||
| "source": [ | ||
| "dir_path = '电工学/'\n", | ||
| "url = 'http://www.icourse163.org/learn/HIT-1001998009?tid=1002098003#/learn/content'" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": { | ||
| "ExecuteTime": { | ||
| "end_time": "2020-04-02T13:01:23.895292Z", | ||
| "start_time": "2020-04-02T13:01:21.674177Z" | ||
| } | ||
| }, | ||
| "outputs": [], | ||
| "source": [ | ||
| "driver = webdriver.Chrome()" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": { | ||
| "ExecuteTime": { | ||
| "end_time": "2020-04-02T13:41:01.478542Z", | ||
| "start_time": "2020-04-02T13:36:20.629957Z" | ||
| } | ||
| }, | ||
| "outputs": [], | ||
| "source": [ | ||
| "driver.get(url) # 打开网页\n", | ||
| "last_file = ''\n", | ||
| "jump = 5\n", | ||
| "for i, ele in enumerate(driver.find_elements_by_class_name('j-titleName')[jump:]):\n", | ||
| " driver.get(url)\n", | ||
| " time.sleep(1) # 等待页面加载完成\n", | ||
| " driver.find_elements_by_class_name('j-titleName')[0].click()\n", | ||
| " driver.find_elements_by_class_name('j-titleName')[i+jump].click()\n", | ||
| " html = bs(driver.page_source, 'lxml') \n", | ||
| " # driver.get('http://www.baidu.com')\n", | ||
| " driver.find_elements_by_class_name('j-titleName')[0].click()\n", | ||
| " for j, ll in enumerate(html.select('.u-learnLesson.normal.f-cb.f-pr')):\n", | ||
| " print(i, j)\n", | ||
| " driver.get(url)\n", | ||
| " time.sleep(1)\n", | ||
| " driver.find_elements_by_class_name('j-titleName')[0].click()\n", | ||
| " driver.find_elements_by_class_name('j-titleName')[i+jump].click()\n", | ||
| "# driver.find_elements_by_class_name('lsicon')[j].click()\n", | ||
| " html = bs(driver.page_source, 'lxml') \n", | ||
| " driver.find_element_by_id(html.select('.u-learnLesson.normal.f-cb.f-pr')[j]['id']).click()\n", | ||
| " time.sleep(1)\n", | ||
| " html = bs(driver.page_source, 'lxml') \n", | ||
| " file_path = dir_path + html.select('.up.j-up.f-thide')[1].text.replace(' ', '') + '.pdf'\n", | ||
| " if last_file == file_path:\n", | ||
| " print('jump', j)\n", | ||
| " continue\n", | ||
| "# if len(html.select('li.f-fl')) == 1:\n", | ||
| "# continue\n", | ||
| " for fl in html.select('li.f-fl'):\n", | ||
| " if '文档' in fl['title']:\n", | ||
| " id_ = fl['id']\n", | ||
| " break\n", | ||
| " \n", | ||
| " driver.find_element_by_id(id_).click()\n", | ||
| " time.sleep(1)\n", | ||
| " html = bs(driver.page_source, 'lxml') \n", | ||
| " print(file_path)\n", | ||
| " r = requests.get(html.select('.j-downpdf')[0]['href'])\n", | ||
| " with open(file_path,\"wb\") as code:\n", | ||
| " code.write(r.content)\n", | ||
| " last_file = file_path" | ||
| ] | ||
| } | ||
| ], | ||
| "metadata": { | ||
| "hide_input": false, | ||
| "kernelspec": { | ||
| "display_name": "Python 3", | ||
| "language": "python", | ||
| "name": "python3" | ||
| }, | ||
| "language_info": { | ||
| "codemirror_mode": { | ||
| "name": "ipython", | ||
| "version": 3 | ||
| }, | ||
| "file_extension": ".py", | ||
| "mimetype": "text/x-python", | ||
| "name": "python", | ||
| "nbconvert_exporter": "python", | ||
| "pygments_lexer": "ipython3", | ||
| "version": "3.7.4" | ||
| }, | ||
| "toc": { | ||
| "base_numbering": 1, | ||
| "nav_menu": {}, | ||
| "number_sections": true, | ||
| "sideBar": true, | ||
| "skip_h1_title": false, | ||
| "title_cell": "Table of Contents", | ||
| "title_sidebar": "Contents", | ||
| "toc_cell": false, | ||
| "toc_position": {}, | ||
| "toc_section_display": true, | ||
| "toc_window_display": true | ||
| } | ||
| }, | ||
| "nbformat": 4, | ||
| "nbformat_minor": 2 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters