爬取豆瓣top250电影的所有信息并且存入表格和数据库
源码及注释:
import urllib.request, urllib.error
from bs4 import BeautifulSoup
import re
import xlwt
import sqlite3
def main():
dbpath = "movie.db"
base_url = "https://movie.douban.com/top250?start="
data_list = get_data(base_url)
save_xls(data_list)
save_db(data_list, dbpath)
def ask_url(url):
head = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:86.0) Gecko/20100101 Firefox/86.0"
}
request = urllib.request.Request(url=url, headers=head)
try:
response = urllib.request.urlopen(request)
html = response.read().decode("utf-8")
except urllib.error.URLError as e:
if hasattr(e, "code"):
print(e.code)
if hasattr(e, "reason"):
print(e.reason)
return html
def get_data(base_url):
data_list = []
for i in range(10):
url = base_url + str(i * 25)
html = ask_url(url)
soup = BeautifulSoup(html, "html.parser")
for item in soup.find_all("div", {"class": "item"}):
data = []
item = str(item)
link = re.findall(r'<a href="(.*?)">', item)[0]
data.append(link)
img_src = re.findall(r'<img alt=.*? class="" src="(.*?)"', item)[0]
data.append(img_src)
title = re.findall(r'<span class="title">(.*?)</span>', item)[0]
data.append(title)
other_title = re.findall(r'<span class="other">(.*?)</span>', item)[0]
if len(other_title) != 0:
data.append(other_title.replace("\xa0/\xa0", " "))
else:
data.append(" ")
rating = re.findall(r'<span class="rating_num" property="v:average">(.*?)</span>', item)[0]
data.append(rating)
rating_number = re.findall(r'span>(\d+)人评价</span>', item)[0]
data.append(rating_number)
inq = re.findall(r'<span class="inq">(.*?)</span>', item)
if len(inq) != 0:
inq = " ".join(inq)
data.append(inq.replace("。", " "))
else:
data.append("")
find_info = re.compile(r'<p class="">(.*?)</p>', re.S)
info = re.findall(find_info, item)[0]
info = info.replace("<br/>", " ")
info = info.replace("\n", " ")
info = info.strip()
data.append(info.replace("\xa0", " "))
data_list.append(data)
return data_list
def save_xls(data_list):
book = xlwt.Workbook(encoding="utf-8")
sheet = book.add_sheet("top250")
title = ["电影详情", "图片", "电影名", "其他名称", "评分", "评价人数", "评语", "其他信息"]
for i in range(8):
sheet.write(0, i, title[i])
for i in range(250):
data = data_list[i]
for j in range(8):
sheet.write(i + 1, j, data[j])
book.save("test.xls")
def create_db(dbpath):
con = sqlite3.connect(dbpath)
cur = con.cursor()
sql = '''
create table movie250
(
id integer primary key autoincrement,
link text,
img_scr text,
title varchar ,
other_title varchar ,
rating numeric ,
rating_number numeric ,
inq text,
info text
)
'''
cur.execute(sql)
cur.close()
con.close()
def save_db(data_list, dbpath):
con = sqlite3.connect(dbpath)
cur = con.cursor()
for data in data_list:
for index in range(len(data)):
data[index] = '"' + data[index] + '"'
sql = '''
insert into movie250
(
link,img_scr,title,other_title,rating,rating_number,inq,info
)
values (%s)''' % ",".join(data)
cur.execute(sql)
con.commit()
cur.close()
con.close()
if __name__ == '__main__':
main()