ErosJohn's Learning House
阿新 • • 發佈:2018-12-14
0x01
上次爬取ichunqiu網課發現它是post請求,為了爬取後續課程名,修改了一下程式碼。
0x02
程式碼如下:
(歡迎探討)
import requests
import json
url = 'https://www.ichunqiu.com/courses/ajaxCourses'
def lesson(url, text, page):
headers = {
'Host': 'www.ichunqiu.com',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:62.0) Gecko/20100101 Firefox/62.0' ,
'Accept': 'application/json, text/javascript, */*; q=0.01',
'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
'Accept-Encoding': 'gzip, deflate',
'Referer': 'https://www.ichunqiu.com/courses',
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8' ,
'X-Requested-With': 'XMLHttpRequest',
}
r = requests.post(url=url, headers=headers, data=text)
data = json.loads(r.text)
name_length = len(data['course']['result'])
for i in range(0, name_length):
print("{0:2} {1:30}".format((page - 1) * 20 + (i + 1),data['course'][ 'result'][i]['courseName']))
for page in range(1, 5):
text = {
'courseTag': '',
'courseDiffcuty': '',
' IsExp': '',
'producerId': '',
'orderField': '',
'orderDirection': '',
'pageIndex': page,
' tagType': '',
'isOpen': '',
}
lesson(url, text, page)