爬虫—美食天下各类菜谱的菜单信息_爬取美食信息点赞人气

最新推荐文章于 2024-05-04 15:02:21 发布

2401_84140580

最新推荐文章于 2024-05-04 15:02:21 发布

阅读量28

点赞数 19

分类专栏：程序员文章标签：爬虫美食 windows

本文链接：https://blog.csdn.net/2401_84140580/article/details/138385517

版权

程序员专栏收录该内容

130 篇文章 0 订阅

订阅专栏

        return response.text
    else:
        return response.status_code
except Exception as e:
    return e

def htmlToTree(html):
return etree.HTML(html)

def elementToString(element):
return etree.tostring(element, pretty_print=True, encoding=‘utf-8’).decode(‘utf-8’)

def parseHtml(html):
allcategory = []
tree = htmlToTree(html)
path = ‘//div[@class=“wrap”]//div[@class=“category_box mt20”]/div[@class=“category_sub clear”]’
data = tree.xpath(path)
for item in data:
category_list = []
div = elementToString(item)
div_tree = htmlToTree(div)
category = div_tree.xpath(‘//h3/text()’)[0]
category_name = div_tree.xpath(‘//ul/li/a/text()’)
category_url = div_tree.xpath(‘//ul/li/a/@href’)
category_list.append(category)
category_list.append(dict(zip(category_name, category_url)))
allcategory.append(category_list)
return allcategory

def writerCsv(food_list, category_name, name):
try:
title = [key for key in food_list[0].keys()] # 表头的代码去掉
if ‘/’ in name or category_name:
name = name.replace(‘/’, ‘’)
category_name = category_name.replace(‘/’, ‘’)
path = os.path.join(os.getcwd() + ‘\source\{0}’.format(category_name))
flag = makedir(path)
csvdata = open(‘source/{0}/{1}.csv’.format(category_name, name), ‘a’, encoding=‘utf-8’)
dictwriter = csv.DictWriter(csvdata, fieldnames=title)
dictwriter.writeheader()
# for data in food_dict:
# dictWriter.writerow(data)
dictwriter.writerows(food_list)
csvdata.close()
return True
except Exception as e:
return False

def parseRecipe(html, category_name, name):
tree = htmlToTree(html)
path = ‘//div[@class=“wrap”]//div[@id=“J_list”]/ul/li’
data = tree.xpath(path)
food_list = []
if data is not None and data != []:
for item in data[0:1]:
food_dict = {}
li = elementToString(item)
li_tree = htmlToTree(li)
food_name = li_tree.xpath(‘//div[@class=“pic”]/a/@title’)[0]
food_detailUrl = li_tree.xpath(‘//div[@class=“pic”]/a/@href’)[0]
food_content = str(
li_tree.xpath(‘//div[@class=“detail”]/p[@class=“subcontent”]/text()’)[0])[3:-1]
food_dict[“菜名”] = food_name
food_dict[“详情链接”] = food_detailUrl
food_dict[“原料”] = food_content
food_list.append(food_dict)
res = writerCsv(food_list, category_name, name)
return res

def getRecipePerCate(data):
res = bool()
for items in data[:4]:
category_name = items[0]
for name, url in items[1].items():
html = getHtml(url)
res = parseRecipe(html, category_name, name)
if res:
return “写入成功”
else:
return “写入失败”

if name == ‘__main__’:
url = ‘https://home.meishichina.com/recipe-type.html’

最后

Python崛起并且风靡，因为优点多、应用领域广、被大牛们认可。学习 Python 门槛很低，但它的晋级路线很多，通过它你能进入机器学习、数据挖掘、大数据，CS等更加高级的领域。Python可以做网络应用，可以做科学计算，数据分析，可以做网络爬虫，可以做机器学习、自然语言处理、可以写游戏、可以做桌面应用…Python可以做的很多，你需要学好基础，再选择明确的方向。这里给大家分享一份全套的 Python 学习资料，给那些想学习 Python 的小伙伴们一点帮助！