def page_category(url):
print('*****start page_categorie()开始单个分类页的爬取')
recipes = []
base_url = url
urls = [] # 放置页数的url,这里构造三页的page url
# 构建url，一共为三页
for x in range(1, 4):
urls.append(base_url + 'page/' + str(x) + '/')
# 针对url做遍历，和发出请求
for url in urls:
html = meishi_requests.get(url)
for item in html.xpath('//div[@id="J_list"]//li'):
temp = {}
temp['show_img'] = verify_text(
item.xpath('./div[@class="pic"]//img/@data-src'))
temp['show_title'] = verify_text(
item.xpath('./div[@class="detail"]//a/text()'))
temp['show_username'] = verify_text(
item.xpath(
'./div[@class="detail"]//p[@class="subline"]/a/text()'))
temp['material'] = verify_text(
item.xpath('.//p[@class="subcontent"]/text()'))
temp['detail'] = detail.parse_detail_recipe(
item.xpath('./div[@class="detail"]//a/@href')[0])
recipes.append(temp)
# break
# break
return recipes
print('*****start get_all_category()开始所有分类页的爬取')
def get_index_categories():
# 获取首页下分类的数据（只获取前两个）
print('*****start index_categories() 开始首页分类数据提取')
html = meishi_requests.get('https://www.meishichina.com/')
# 获取分类名，装到列表中(不用验证了，可确定性很大)
categories = html.xpath('//div[@class="w5"]//h3[position() <3]/a/text()')
# 获取列表下的食谱详细数据
all_recipes = []
for item in html.xpath(
'//div[@class="w5"]//div[@class="big4_list clear mt10"]/ul[position() < 3]'
):
recipes = []
for i in item.xpath('./li'):
temp = {}
temp['show_title'] = verify_text(i.xpath('.//p/text()'))
temp['show_username'] = verify_text(
i.xpath('.//a[@class="u"]/text()'))
temp['show_img'] = verify_text(i.xpath('.//img/@data-src'))
temp['detail'] = detail.parse_detail_recipe(
verify_text(i.xpath('.//a[1]/@href')))
recipes.append(temp)
all_recipes.append(recipes)
# 整合数据
for index, item in enumerate(all_recipes):
data = {}
data['categories'] = categories[index] if categories else ''
data['recipes'] = item
write_data('categories/index-categories', str(index + 1), data)
# 写入数据
print('*****done index_categories() 首页分类数据提取结束')
def get_all_categories():
# 获取所有分类中的菜单，其实也就获取页面前三十个，并且每个爬取3页
print('*****start get_all_categories()开始所有分类页的爬取')
html = meishi_requests.get('https://home.meishichina.com/recipe-type.html')
# 下面数据不用验证了，可确定性很大
for index, item in enumerate(
html.xpath('//div[@class="category_sub clear"][1]//li')):
data = {}
data['categories'] = item.xpath('./a/@title')[0]
data['recipes'] = page_category(item.xpath('./a/@href')[0])
write_data('categories/all-categories', str(index + 1), data)
# break
print('*****done get_all_categories()所有分类页的爬取结束')
def get_detail_categories():
# 爬取详细分类的数据
print('*****start get_detail_categories() 开始详细分类的数据提取')
# 请求菜谱分类页
html = meishi_requests.get('https://home.meishichina.com/recipe.html')
# 提取每个分类的名字(不用校验，数据可确定性已经很高)
for index, h3 in enumerate(html.xpath('//div[@class="ui_title"]//h3')):
data = {}
data['categories'] = h3.xpath('./a/text()')[0]
data['recipes'] = get_ajax_data(
h3.xpath('./a/@data')[0],
h3.xpath('./a/@order')[0])
# 写入数据
write_data('categories/detail-categories', str(index + 1), data)
print('*****done get_detail_categories() 详细分类的数据提取结束')
def get_slider_URL():
# 获取首页轮播图那里的url
print('*****start get_slider_URL()提取轮播图url')
data = {}
html = meishi_requests.get('https://www.meishichina.com/')
slider_pages_url = html.xpath(
'//div[@id="home_index_slider"]/ul/li/a[@title != "2020，人人都是美食家"]/@href'
)
imgs_url = html.xpath(
'//div[@id="home_index_slider"]/ul/li/a[@title != "2020，人人都是美食家"]/img/@src'
)
data['slider_pages_url'] = slider_pages_url
data['imgs_url'] = imgs_url
print('*****done get_slider_URL()提取轮播图url结束')
return data
def parse_menu_pages(temporary_data):
# 处理每个菜单页面中的数据
print('*****start parse_menu_pages(temporary_data) 开始菜单的页面数据处理')
data = {}
# 提取首页显示的数据
data['home_title'] = temporary_data['home_title']
data['home_content'] = temporary_data['home_content']
data['username'] = temporary_data['username']
# 发起请求
html = meishi_requests.get(temporary_data['url'])
# 解析数据
data['page_data'] = {}
# 标题
data['page_data']['title'] = html.xpath(
'//a[@id="collect_title"]/text()')[0].strip()
# 创建时间
data['page_data']['creation_time'] = init_time(
html.xpath('//div[@class="collect_dp"]/span/text()')[0])
# 用户名
data['page_data']['username'] = temporary_data['username']
# 页面中的食谱信息
data['page_data']['recipes'] = []
for item in html.xpath('//div[@id="J_list"]//li'):
temp = {}
temp['show_img'] = verify_text(
item.xpath('./div[@class="pic"]//img/@data-src'))
temp['show_title'] = verify_text(item.xpath(
'./div[@class="detail"]//a/text()'))
temp['show_username'] = verify_text(item.xpath(
'./div[@class="detail"]//p[@class="subline"]/a/text()'))
temp['material'] = verify_text(
item.xpath('.//p[@class="subcontent"]/text()'))
temp['detail'] = detail.parse_detail_recipe(
item.xpath('./div[@class="detail"]//a/@href')[0])
data['page_data']['recipes'].append(temp)
# temp['detail']
# 格式化数据
# 把数据写入到文件
global INDEX
with open('./menu_data/'+str(INDEX)+'.txt', 'w', encoding='utf-8') as fp:
print('开始写入文件')
fp.write(json.dumps(data, ensure_ascii=False))
print('写入文件结束')
INDEX += 1
print('*****done parse_menu_pages(temporary_data) 菜单的页面数据处理完毕')
def parse_slider_pages(slider_page_url, slpage_img_url):
# 处理进入每个轮播图中的网页数据
print('*****start parse_slider_pages(slider_page_url)提取轮播图页面数据')
page_data = {} # slider_pages_data下的{}
page_data['img_url'] = slpage_img_url
html = meishi_requests.get(slider_page_url)
# 获取页面描述
page_data['desc'] = verify_text(html.xpath('//p[@id="mof_desc"]/text()'))
# 获取分标题和其内容
page_data['list'] = [] # slider_pages_data下的{}的list[]
# 标题
mo_result = verify_list(
html.xpath('//div[@class="mo" and position() < last()-1]/h2/text()'))
# 内容
p_list = verify_list(html.xpath('//div[@class="msb"]/p/text()'))
for index, p in enumerate(p_list):
p_list[index] = p.replace('\n', '').strip('')
# 每部分的菜谱
recipes_result = [] # slider_pages_data下的{}的list[]的对象下的recipes[]
msb_ul = verify_list(html.xpath('//div[@class="msb_list clear"]/ul'))
for item in msb_ul:
# 得到每个包含详细的菜谱li集合，丢给detail模块处理，然后返回一个列表
# print(item.xpath('.//li'))
recipes_result.append(
detail.parse_slider_recipes_pages(item.xpath('./li')))
# 把相对应的标题，内容，菜谱集合进行数据重组
for index, item in enumerate(recipes_result):
temp = {}
temp['title'] = mo_result[index] if mo_result else ''
temp['content'] = p_list[index] if p_list else ''
temp['recipes'] = recipes_result[index]
page_data['list'].append(temp)
global INDEX
with open('./slider_data/' + str(INDEX) + '.txt', 'w',
encoding='utf-8') as fp:
print('开始写入文件')
fp.write(json.dumps(page_data, ensure_ascii=False))
INDEX += 1
# print(json.dumps(page_data, ensure_ascii=False))
print('*****done parse_slider_pages(slider_page_url)提取轮播图页面数据结束')
def get_menus_URL():
# 获取首页菜单的各个url
print('*****start get_menus_URL() 开始提取首页的菜单url')
data_temp = []
# 发起请求
html = meishi_requests.get('https://www.meishichina.com/')
# 底下不要做验证，这边出错是得到数据致命性错误的，不能让程序修正
for item in html.xpath('//div[@id="w2_slider"]//li'):
temp = {}
temp['url'] = item.xpath('.//a/@href')[0]
temp['home_title'] = item.xpath('.//a/text()')[0].strip()
temp['home_content'] = init_text(item.xpath('./p/text()'))
temp['username'] = item.xpath('./p/span/text()')[0].strip()
data_temp.append(temp)
# print(json.dumps(temp,ensure_ascii=False))
print('*****done get_menus_URL() 提取首页的菜单url结束')
# 返回解析到的url,和首页中展示的数据
return data_temp