def parse(self, response):
for course in response.css('div.course-body')
item = CourseItem({
'name': course.css('div.course-name::text').extract_first(),
'description': course.css('div.course-desc::text').extract_first(),
'type': course.css('div.course-footer span.pull-right::text').extract_first(default='Free'),
'students': course.xpath('.//span[contains(@class, "pull-left")]/text()[2]').re_first('[^\d]*(\d+)[^\d]*')
})
yield item
def parse(self, response):
for course in response.css('div.course-body'):
# return the package CourseItem
item = CourseItem(
{'name': course.css('div.course-name::text').extract_first()})
yield item
def parse(self, response):
for i in response.css('li.col-12'):
item = CourseItem({
"name":
i.css('a::text').re_first('\s*(\w*)'),
"update_time":
i.css('relative-time::attr(datetime)').extract_first()
})
yield item
def parse(self, response):
for course in response.css('div.course-body'):
# 将返回结果包装为 CourseItem 其它地方同上一节
item = CourseItem({
'name': course.css('div.course-name::text').extract_first(),
'description': course.css('div.course-desc::text').extract_first(),
'type': course.css('div.course-footer span.pull-right::text').extract_first(default='免费'),
'students': course.xpath('.//span[contains(@class, "pull-left")]/text()[2]').re_first('[^\d]*(\d*)[^\d]*') })
#顺序要和Items.py里面写的一样
yield item #for每一次循环都要变成CourseItem传出去
def parse(self, response):
for i in response.css('li.col-12'):
item = CourseItem({
"name": i.css('a::text').re_first('\s*(\w*)'),
"update_time":i.css('relative-time::attr(datetime)').extract_first()
})
course_url = response.urljoin(i.xpath('.//a/@href').extract_first())
#print(course_url)
request = scrapy.Request(url=course_url,callback=self.parse_code)
request.meta['item'] = item
yield request
def parse(self, response):
for course in response.css('li.col-12'):
item = CourseItem({
'name':
course.xpath('.//h3/a/text()').re_first('(\S+)'),
'update_time':
course.xpath('.//relative-time/@datetime').extract_first()
})
course_url = response.urljoin(
course.xpath('.//h3/a/@href').extract_first())
request = scrapy.Request(course_url, callback=self.detail_parse)
request.meta['item'] = item
yield request
def parse(self, response):
for course in response.css('div.col-sm-12.col-md-3'):
item = CourseItem({
'name':
course.css('h6::text').extract_first().strip(),
'description':
course.css(
'div.course-description::text').extract_first().strip(),
'type':
course.css('span.course-type::text').extract_first().strip(),
'students':
course.css('span.students-count span::text').extract_first()
})
yield item
def parse(self, response):
for course in response.xpath('//div[@class="course-body"]'):
item = CourseItem()
item['name'] = course.xpath(
'.//div[class="course-name"]/text()').extract_first()
item['description'] = course.xpath(
'.//div[@class="course-desc"]/text()').extract_first()
item['type'] = course.xpath(
'.//span[contains(@class,"pull-right")]/text()').extract_first(
default="Free")
item['students'] = course.xpath(
'.//span[contains(@class,"pull-left")]/text()[2]').re_first(
'\s*(\d+)\s*')
yield item
def parse(self, response):
for course in response.xpath("//div[contains(@class, 'course-body')]"):
# 使用 xpath 语法对每个 course 提取数据
yield CourseItem({
# 课程名称
'name': course.xpath('.//div[contains(@class, "course-name")]/text()').extract_first(default="未知"),
# 课程描述
'description': course.xpath('.//div[contains(@class, "course-desc")]/text()').extract_first(default="空"),
# 课程类型，实验楼的课程有免费，会员，训练营三种，免费课程并没有字样显示，也就是说没有 span.pull-right 这个标签，没有这个标签就代表时免费课程，使用默认值 `免费｀就可以了。
'type':course.xpath(
'.//div[contains(@class, "course-footer")]/span[contains(@class, "pull-right")]/text()').extract_first(
default="免费"),
# 注意 // 前面的 .，没有点表示整个文档所有的 div.course-body，有 . 才表示当前迭代的这个 div.course-body
'students': course.xpath('.//span[contains(@class, "pull-left")]/text()[2]').re_first(
'[^\d]*(\d*)[^\d]*')
})
def parse(self, response):
print("*******************************************************")
print(response.url)
print("*******************************************************")
for course in response.xpath(
'//*[@id="__layout"]/div/div[1]/div/div[1]/div/ div[1]/div/div[2]/div[1]/div'
):
item = CourseItem({
'name':
course.xpath('.//h6[contains(@class,"course-name")]/text()'
).extract_first(),
'description':
course.xpath('.//div[contains(@class,"course-desc")]/text()'
).extract_first(),
'type':
course.xpath('.//span[contains(@class,"course-type")]/text()'
).extract_first(default='Free'),
'students':
course.xpath(
'.//span[contains(@class,"students-count")]/span/text()').
extract_first(),
})
yield item
