Python爬虫之爬取豆瓣top
import bs4 # 网页解析,获取数据
import re # 正则表达式,进行文字匹配
import urllib.request # 制定URL,获取网页数据
import urllib.parse
import xlwt # 进行Excel操作
import sqlite3 # 进行SQLite数据库操作
import time
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
def main():
baseurl = "https://movie.douban.com/top250?start="
# proxy_support = urllib.request.ProxyHandler({'http': random.choice(proxy_list)})
# askURL("https://movie.douban.com/top250?start=0")
# 1.爬取网页
datalist = getData(baseurl)
savepath = "豆瓣电影Top250.xls"
dbpath = "movies.db"
# # 3.保存数据
#saveData(datalist, savepath)
saveDataDB(datalist, dbpath)
# 影片信息的链接规则
findLink = re.compile(r'<a href="(.*?)">') # 创建正则表达式的对象,表示规则(字符串的模式)
# 影片图片的链接规则
findImgSrc = re.compile(r'img.*src="(.*?)"', re.S) # re.S让换行符包含在字符中
# 影片的片名
findTitle = re.compile(r'<span class="title">(.*)</span>')
# 影片评分
findRating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')
# 评价人数
findJudge = re.compile(r'<span>(\d*)人评价</span>')
# 概况
findInq = re.compile(r'<span class="inq">(.*)</span>')
# 影片的相关内容
findBd = re.compile(r'<p class="">(.*?)</p>', re.S)
# 爬取网页
def getData(baseurl):
dataList = []
for i in range(0, 10):
url = baseurl + str(i * 25)
html = askURL(url)
# 逐一解析数据
soup = bs4.BeautifulSoup(html, "html.parser") # 以html.parser形式解析html文档
for item in soup.find_all('div', class_="item"): # 查找符合要求的字符串,形成列表
data = [] # 保存一部电影的所有信息
item = str(item)
# 影片详情的链接
link = re.findall(findLink, item)[0] # re库用来通过正则表达式查找指定的字符串
data.append(link)
imgSrc = re.findall(findImgSrc, item)[0]
data.append(imgSrc)
titles = re.findall(findTitle, item)
if len(titles) == 2:
ctitle = titles[0] # 添加中文名
data.append(ctitle)
etitle = titles[1].replace("/", "")
data.append(etitle) # 添加外名
else:
data.append(titles[0])
data.append(' ') # 外名留空
rating = re.findall(findRating, item)
r = rating[0]
data.append(r) # 添加评分
judgeNum = re.findall(findJudge, item)
j = judgeNum[0]
data.append(j) # 添加评价人数
inq = re.findall(findInq,item) # 添加概述
if len(inq) != 0:
inq = inq[0].replace("。", "")
data.append(inq)
else:
data.append(" ") # 留空
bd = re.findall(findBd, item)[0] # 添加简介
bd = re.sub('<br(\s+)?/>(\s+)?', ' ', bd)
data.append(bd.strip()) # bd.strip()去掉空格
dataList.append(data) # 把处理好的一部电影信息放入dataList中
return dataList
# 得到指定一个URL的网页信息
def askURL(url):
time.sleep(0.1)
# 用户代理,表示告诉要访问的URL我们是一个什么类型的机器-浏览器(本质上是告诉浏览器我们可以接收什么水平的文件内容)
# 模拟浏览器头部信息,向我们要访问的服务器发送消息
# 随机从列表中选择IP、Header
head = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.93 Safari/537.36"
}
request = urllib.request.Request(url=url, headers=head)
html = ""
try:
response = urllib.request.urlopen(request)
html = response.read().decode("utf-8")
except Exception as result:
print(result)
return html
# 保存数据
def saveData(datalist, savepath):
print("save……")
book = xlwt.Workbook(encoding='utf-8')
sheet = book.add_sheet('豆瓣电影Top250', cell_overwrite_ok=True)
col = ("电影详情链接", "图片链接", "影片中文名", "影片海外名", "评分", "评价数", "概况", "相关信息")
for i in range(0, 8):
sheet.write(0, i, col[i])
for i in range(0, 250):
print("第%d条" % (i+1))
data = datalist[i]
for j in range(0, 8):
sheet.write(i+1, j, data[j]) # 写入数据
book.save(savepath) # 保存
def saveDataDB(datalist, dbpath):
init_db(dbpath)
conn = sqlite3.connect(dbpath)
cur = conn.cursor()
for data in datalist:
for index in range(len(data)):
if index == 4 or index == 5:
continue
data[index] = '"'+data[index]+'"'
sql = '''
insert into movie250(
info_link,pic_link,cname,ename,scroe,rated,instroduction,info)
values(%s)''' % (",".join(data))
cur.execute(sql)
conn.commit()
cur.close()
conn.close()
def init_db(dbpath):
sql = '''
create table movie250
(
id integer primary key autoincrement,
info_link text,
pic_link text,
cname varchar,
ename varchar,
scroe text,
rated text,
instroduction text,
info text
);
''' # 创建数据表
conn = sqlite3.connect(dbpath)
cursor = conn.cursor()
cursor.execute(sql)
conn.commit()
conn.close()
if __name__ == "__main__":
main()
# init_db('test.db')
print("爬取完毕")