def get_train_info(self):
train = {'name': self.get_train_name(), 'courses': []}
current_page = 1
while (current_page):
url = 'http://edu.51cto.com/center/wejob/usr/courseajax?train_id=%d&page=%d&size=1000'%\
(self.train_id,current_page)
res = self.session.get(url)
res = json.loads(res.text)['data']
current_page = res['current_page'] + 1 if res[
'current_page'] < res['count_page'] else 0
for i in res['data']:
course = {
'course_name':
cto.filename_reg_check(i['course_name'].encode('utf-8')),
'train_id':
i['train_id'],
'train_course_id':
i['train_course_id'],
'lesson_num':
i['lesson_num'],
'number':
i['number']
}
train['courses'].append(course)
return train
def get_course_info(self, course_id):
infos = []
current_page = 1
while (current_page):
url = 'https://edu.51cto.com/center/wejob/user/course-info-ajax?&train_course_id=%d&page=%d&size=20' % (
course_id, current_page)
res = self.session.get(url).text
data = json.loads(res)['data']
current_page = data['current_page'] + 1 if data[
'current_page'] < data['count_page'] else 0
data_list = data['data'] #qxx 可能是lesson的list, 也可能是chapter的list
if data_list[0].has_key("lesson_id"):
#data_list是lesson的list
for lesson in data_list:
info = self.parse_lesson(lesson)
infos.append(info)
else:
#data_list是chapter的list
for chapter in data_list:
chapter_name = chapter["chapter_name"]
chapter_name = cto.filename_reg_check(chapter_name)
chapter_sort = chapter["chapter_sort"]
chapter_sort_name = chapter_sort + ". " + chapter_name
lessons = chapter[
"list"] #chapter["list"] 可能是lesson的list; 也可能是dict, key是分页的序号, value是lesson;
lessons = lessons if type(
lessons) is list else lessons.values()
for lesson in lessons:
info = self.parse_lesson(lesson, chapter_sort_name)
infos.append(info)
return infos
def get_train_info(self):
train = {'name': self.get_train_name(), 'courses': []}
current_page = 1
while (current_page):
url = 'https://edu.51cto.com/center/wejob/user/train-course-ajax?train_id=%d&page=%d&size=20' % \
(self.train_id, current_page)
res = self.session.get(url)
try:
res = json.loads(res.text)
except ValueError as e:
print "接口响应异常", "%s" % e
print res.text
exit()
res = res['data']
current_page = res['current_page'] + 1 if res['current_page'] < res['count_page'] else 0
for i in res['data']:
course = {
'course_name': cto.filename_reg_check(i['course_name'].encode('utf-8')),
'train_id': i['train_id'],
'train_course_id': i['train_course_id'],
'lesson_num': i['lesson_num'],
'number': i['sort'] # 课程的序号
}
train['courses'].append(course)
return train
def get_course_info(self, course_id):
infos = []
current_page = 1
while (current_page):
url = 'https://edu.51cto.com/center/wejob/user/course-info-ajax?&train_course_id=%d&page=%d&size=20' % (
course_id, current_page)
res = self.session.get(url).text
data = json.loads(res)['data']
current_page = data['current_page'] + 1 if data[
'current_page'] < data['count_page'] else 0
pages = data['data'][0]['list']
# 判断list里的数据是list还是dict
f = lambda m, pages: pages[m] if type(pages) is dict else m
for m in pages:
m = f(m, pages)
lesson_name = m[u'lesson_name']
lesson_name = cto.filename_reg_check(lesson_name)
info = {
'lesson_name': lesson_name,
'lesson_id': m['lesson_id'],
'video_id': m['video_id']
}
infos.append(info)
return infos
def get_train_name(self):
url = 'http://edu.51cto.com/center/wejob/index/view?id=%d&force=3&orig=try' % (
self.train_id)
res = self.session.get(url).text
soup = BeautifulSoup(res, 'html.parser')
title = soup.find('h2', id='CourseTitle')
if title == None:
exit('找不到该课程')
return cto.filename_reg_check(title.string)
def get_train_name(self):
url = 'http://edu.51cto.com/center/wejob/index/view?id=%d&force=3&orig=try' % (self.train_id)
res = self.session.get(url)
tree = html.fromstring(res.text)
title = tree.xpath("//div[@class='basismes']/div")[0].get("title")
print title
if title == None:
exit('找不到该课程')
return cto.filename_reg_check(title)
def parse_lesson(self, lesson, chapter_sort_name=""):
"""
lesson是服务器返回的lesson的完整信息;
这里处理一下可以记录lesson的结构;
"""
lesson_name = lesson[u'lesson_name']
lesson_name = cto.filename_reg_check(lesson_name)
info = {
'lesson_name': lesson_name,
'lesson_id': lesson['lesson_id'],
'video_id': lesson['video_id'],
"lesson_type": lesson["lesson_type"],
"chapter_sort_name": chapter_sort_name,
"show_number": lesson["show_number"]
}
return info
def get_course_info(self, course_id):
infos = []
current_page = 1
while (current_page):
url = 'http://edu.51cto.com/center/wejob/usr/course-infoajax?train_id=%d&train_course_id=%d&page=%d&size=20'\
%(self.train_id, course_id,current_page)
res = self.session.get(url).text
data = json.loads(res)['data']
current_page = data['current_page'] + 1 if data[
'current_page'] < data['count_page'] else 0
pages = data['data']
for m in pages:
info = {
'lesson_name': cto.filename_reg_check(m['lesson_name']),
'lesson_id': m['lesson_id'],
'video_id': m['video_id']
}
infos.append(info)
return infos
