爬取futurelearn课程网

Posted 2020-11-23 yangbiao6

 1 import requests
 2 from bs4 import BeautifulSoup 
 3 import bs4
 4 import re
 5 import csv
 6 #import pandas as pd
 7 # r = requests.get("https://www.futurelearn.com/courses/climate-change-the-solutions,timeout = 30")
 8 # r.encoding = r.apparent_encoding
 9 # print(r.text)
10 def gethtmlText(url,code=‘utf-8‘):
11     try:
12         r = requests.get(url,timeout = 30)
13         r.raise_for_status()
14         r.encoding = r.apparent_encoding
15         return r.text
16     except:
17         print("获取失败")
18 #爬取基本列表
19 def getCourseList(lst,html):
20     soup = BeautifulSoup(html,‘html.parser‘)
21     div_href = soup.find_all(‘div‘,class_= ‘m-grid-of-cards m-grid-of-cards--compact‘)
22     cop = re.compile(‘href="(.*?)">‘)
23     href_get = re.findall(cop,str(div_href))
24     m =  r‘" role="button‘
25     z = ""
26     j = ‘courses‘
27     #print(href_get)
28     #print(type(href_get))
29     for i in href_get:
30         j = ‘courses‘
31         if j  in i:
32             if m in i:
33                 i=i.replace(m,z)
34                 #print("https://www.futurelearn.com"+i)
35             else:
36                 pass
37                 #print("https://www.futurelearn.com"+i)
38             i = "https://www.futurelearn.com"+i
39             lst.append(i)
40         #    print(lst)
41         else:
42             pass
43 def CourseList(lst):
44     list_1 = []
45     for i in lst:
46         list_ = []
47         url = i
48         r = requests.get(url,timeout = 30)
49 
50         r.encoding = r.apparent_encoding
51         html=r.text
52         x = BeautifulSoup(html,‘html.parser‘)
53         
54         for i in x.find_all(‘h1‘,class_ = ‘m-dual-billboard__heading‘):
55             list_.append(i.text)
56         #print(list_)
57         
58         for a in x.find_all(‘span‘,class_ = ‘m-key-info__content‘):
59               list_.append(a.text)
60         print(list_)
61         
62         for b in x.find(‘div‘,class_ = "a-content a-content--tight").find_all("p"):
63             #print(a.text)
64               list_.append(b.text)
65         print(list_)
66 
67          c = x.find(‘section‘,class_ = ‘a-section a-section--alt-adjacent‘).find_all(‘p‘):
68             list_.append(c.text)
69         print(list_)
70     #     list_1.append(list_)
71     # print(list_1)
72     
73     
74 # def write_dictionary_to_csv(list_1,filename):
75 #     file_name=‘{}.csv‘.format(filename)
76 #     name = [‘课程名‘,‘课时‘,‘学习任务‘,‘课程性质‘,‘额外费用‘,‘介绍‘,‘话题‘，‘开始时间‘,‘服务对象‘,‘‘]
77 #     test = pd.DataFrame(columns = name,data = list_1)
78 #     test.to_csv(file_name)
79     
80 def main():
81     star_url = "https://www.futurelearn.com/courses/categories/science-engineering-and-maths-courses?all_courses=1"
82     infoList = []
83     url = star_url
84     file_name_ = ‘courses‘
85     html = getHTMLText(url)
86     getCourseList(infoList,html)
87 
88     CourseList(infoList)
89     #write_dictionary_to_csv(infoList,file_name_)
90 
91 main()