数据采集与融合技术_实验3
-
作业①:
1)中国气象网图片的爬取
– 要求:要求:指定一个网站,爬取这个网站中的所有的所有图片,例如中国气象网(http://www.weather.com.cn)。
– 分别使用单线程和多线程的方式爬取。(限定爬取图片数量为学号后3位)
– 输出信息:将下载的Url信息在控制台输出,并将下载的图片存储在images子文件夹中,并给出截图。
完成过程(单线程):
1.向页面发送请求,获取图片所在网页链接:
def get_url(start_url):
req = urllib.request.Request(start_url, headers=headers)
data = urllib.request.urlopen(req)
data = data.read()
dammit = UnicodeDammit(data, ["utf-8", "gbk"])
data = dammit.unicode_markup
soup = BeautifulSoup(data, "lxml")
urls = soup.select("a")
i = 0
for a in urls:
href = a["href"]
imageSpider(href, i + 1)
i = i + 1
if count > 110: # 爬取110张
break
2.爬取该网页下的所有图片的下载链接并下载到本地:
def imageSpider(start_url, cous):
try:
urls = []
req = urllib.request.Request(start_url, headers=headers)
data = urllib.request.urlopen(req)
data = data.read()
dammit = UnicodeDammit(data, ["utf-8", "gbk"])
data = dammit.unicode_markup
soup = BeautifulSoup(data, "lxml")
images = soup.select("img")
for image in images:
try:
if count > 110:
break
src = image["src"]
url = urllib.request.urljoin(start_url, src)
if url not in urls:
urls.append(url)
print(url)
download(url, cous)
except Exception as err:
print(err)
except Exception as err:
print(err)
3.下载图片到指定路径函数:
def download(url, cous):
global count
try:
count = count + 1
# 提取文件后缀扩展名
if url[len(url) - 4] == ".":
ext = url[len(url) - 4:]
else:
ext = ""
req = urllib.request.Request(url, headers=headers)
data = urllib.request.urlopen(req, timeout=100)
data = data.read()
path = r"C:\Users\黄杜恩\PycharmProjects\pythonProject3\images\\" + "第" + str(count) + "张" + ".jpg" # 指定下载路径
with open(path, 'wb') as f:
f.write(data)
f.close()
print("downloaded " + str(cous) + "页" + str(count) + ext)
except Exception as err:
print(err)
4.输出结果展示:
5.爬取图片结果:
6.代码地址:https://gitee.com/huang-dunn/crawl_project/blob/master/实验三作业1/project_three_test1_1.py
完成过程(多线程):
1.修改单线程代码部分:
def imageSpider(start_url, cous):
global threads
global count
try:
urls = []
req = urllib.request.Request(start_url, headers=headers)
data = urllib.request.urlopen(req)
data = data.read()
dammit = UnicodeDammit(data, ["utf-8", "gbk"])
data = dammit.unicode_markup
soup = BeautifulSoup(data, "lxml")
images = soup.select("img")
for image in images:
try:
if count >= 110:
break
src = image["src"]
url = urllib.request.urljoin(start_url, src)
if url not in urls:
urls.append(url)
count = count+1
T = threading.Thread(target=download, args=(url, cous, count))
T.setDaemon(False)
T.start()
threads.append(T)
except Exception as err:
print(err)
except Exception as err:
print(err)
主函数添加以下部分
get_url(start_url)
threads = []
for t in threads:
t.join()
2.运行结果展示:
3.代码地址:https://gitee.com/huang-dunn/crawl_project/blob/master/实验三作业1/project_three_test1_2.py
2)心得体会:加深了对多线程爬取图片方法的编程理解。
-
作业②
1)
– 要求:使用scrapy框架复现作业①
– 输出信息:同作业①
完成过程:
1.编写item类:
class Pro3Test2Item(scrapy.Item):
data = scrapy.Field() # 图片数据
count = scrapy.Field() # 图片总数
ext = scrapy.Field() # 文件后缀
url = scrapy.Field() # 图片链接
2.编写spiders类:
class Test2Spider(scrapy.Spider):
name = 'pic_test'
global count
count = 1
# allowed_domains = ['XXX.com']
# start_urls = ['http://www.weather.com.cn/']
def start_requests(self):
yield scrapy.Request(url='http://www.weather.com.cn', callback=self.parse)
def parse(self, response):
href_list = response.xpath("//a/@href") # 爬取初始网页下图片的所在网页链接
for href in href_list:
# print(href.extract())e
H = str(href.extract())
if count > PIC_LIMIT:
return
if len(H) > 0 and H[0] == 'h':
yield scrapy.Request(url=href.extract(), callback=self.parse1)
def parse1(self, response):
a_list = response.xpath("//img/@src") # 爬取图片下载链接
for a in a_list:
if count > PIC_LIMIT:
return
# print(a.extract())
url = urllib.request.urljoin(response.url, a.extract())
# print(url)
yield scrapy.Request(url=url, callback=self.parse2)
def parse2(self, response):
global count
count += 1
if count > PIC_LIMIT:
return
item = Pro3Test2Item()
item["ext"] = response.url[-4:]
item["data"] = response.body
item["count"] = count
item["url"] = response.url
return item
3.编写pipeline类:
class Pro3Test2Pipeline:
def process_item(self, item, spider):
path = "D:/py_download/" + "第" + str(item["count"]) + "张" + item["ext"] # 指定下载路径
with open(path, 'wb') as f:
f.write(item["data"])
f.close()
print("downloaded " + str(item["count"]) + "张" + item["ext"] + " 图片链接:" + item["url"])
return item
4.输出结果展示:
5.图片爬取结果:
6.代码链接:https://gitee.com/huang-dunn/crawl_project/tree/master/实验三作业2
2)心得体会:对scrapy框架的使用更加的熟练,对xpath匹配文本也理解的更深。
-
作业③
1)
– 要求:爬取豆瓣电影数据使用scrapy和xpath,并将内容存储到数据库,同时将图片存储在
– imgs路径下。
– 候选网站: https://movie.douban.com/top250
– 输出信息:
序号 | 电影名称 | 导演 | 演员 | 简介 | 电影评分 | 电影封面 |
---|---|---|---|---|---|---|
1 | 肖申克的救赎 | 弗兰克·德拉邦特 | 蒂姆·罗宾斯 | 希望让人自由 | 9.7 | ./imgs/xsk.jpg |
2... |
完成过程:
1.编写item类:
class Pro3Test3Item(scrapy.Item):
no = scrapy.Field() # 序号
name = scrapy.Field() # 电影名称
director = scrapy.Field() # 导演
actor = scrapy.Field() # 演员
grade = scrapy.Field() # 电影评分
url = scrapy.Field() # 图片链接
inf = scrapy.Field() # 简介
pass
2.编写spiders类:
class MovieSpider(scrapy.Spider):
name = 'movie'
# allowed_domains = ['XXX.com']
# start_urls = ['http://XXX.com/']
def start_requests(self):
cookie = {}
for i in range(0, 11):
yield scrapy.Request(url='https://movie.douban.com/top250?start=' + str(i * 25) + '&filter=',
callback=self.parse)
def parse(self, response):
li_list = response.xpath('//*[@id="content"]/div/div[1]/ol/li') #使用Xpath进行信息标识
item = Pro3Test3Item()
for li in li_list:
item["no"] = li.xpath('./div/div[1]/em/text()').extract_first().strip()
item["name"] = li.xpath('./div/div[2]/div[1]/a/span[1]/text()').extract_first()
temp_ = li.xpath('./div/div[2]/div[2]/p[1]/text()[1]').extract_first().split(" ")[9]
temp = temp_.split(":")
item["director"] = temp[1].split(" ")[0]
if len(temp) > 2:
item["actor"] = temp[2]
else:
item["actor"] = 'None'
item["grade"] = li.xpath('./div/div[2]/div[2]/div/span[2]//text()').extract_first()
item["inf"] = li.xpath('./div/div[2]/div[2]/p[2]/span/text()').extract_first()
if item["inf"] == '':
item["inf"] = 'None'
item["url"] = li.xpath('./div/div[1]/a/img/@src').extract_first()
print(item["no"], item["name"], item["director"], item["grade"], item["inf"])
yield item
3.编写数据库类:
class MovieDB:
def __init__(self):
self.con = sqlite3.connect("movies.db")
self.cursor = self.con.cursor()
def openDB(self):
try:
self.cursor.execute(
"create table movies (序号 int(128),电影名称 varchar(128),导演 varchar(128),"
"演员 varchar(128),简介 varchar(128),电影评分 varchar(128),电影封面 varchar(128),"
"constraint pk_movies primary key (序号))")
except:
self.cursor.execute("delete from movies")
def closeDB(self):
self.con.commit()
self.con.close()
def insert(self, no, name, director, actor, grade, inf, image):
try:
self.cursor.execute("insert into movies (序号,电影名称,导演,演员,简介,电影评分,电影封面) "
"values (?,?,?,?,?,?,?)",
(int(no), name, director, actor, inf, grade, image))
except Exception as err:
print(err)
4.编写pipeline类:
class Pro3Test3Pipeline:
def __init__(self):
self.db = MovieDB()
def open_spider(self, spider):
self.db.openDB()
def process_item(self, item, spider):
data = requests.get(item['url']).content
path = r"D:/example/pro3_test3/pro3_test3/images/" + "第" + str(item["no"]) + "张" + ".jpg" # 指定下载路径
with open(path, 'wb') as f:
f.write(data)
f.close()
print("downloaded " + str(item["no"]) + "张" + "jpg" + " 图片链接:" + item["url"])
self.db.insert(int(item["no"]), item["name"], item["director"], item["actor"], item["grade"], item["inf"],
item["url"])
return item
def close_spider(self, spider):
self.db.closeDB()
5.输出结果展示:
6.爬取图片展示:
7.数据库存储结果展示:
8.相关代码链接:https://gitee.com/huang-dunn/crawl_project/tree/master/实验3作业3