爬取豆瓣top250的电影数据,保存至excel中,再将数据导入MySQL中
from bs4 import BeautifulSoup
import re
import urllib.request, urllib.error
import xlwt
findLink = re.compile(r'<a href="(.*?)">')
findimg = re.compile(r'<img.*src="(.*?)"', re.S)
findTitle = re.compile(r'<span class="title">(.*)</span>')
findscore = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')
findnum = re.compile(r'<span>(\d*)人评价</span>')
findinq = re.compile(r'<span class="inq">(.*)</span>')
findcontext = re.compile(r'<p class="">(.*?)</p>', re.S)
def main():
url1 = "https://movie.douban.com/top250?start="
datalist = getData(url1)
savepath = "豆瓣1.xls"
saveData(datalist, savepath)
def getData(url1):
datalist = []
for i in range(0, 10):
url2 = url1 + str(i * 25)
html1 = askURL(url2)
soup = BeautifulSoup(html1, "html.parser")
for item in soup.find_all('div', class_="item"):
data = []
item = str(item)
link = re.findall(findLink, item)[0]
data.append(link)
img = re.findall(findimg, item)[0]
data.append(img)
title = re.findall(findTitle, item)
if len(title) == 2:
ctitle = title[0]
data.append(ctitle)
otitle = title[1].replace("/", "")
data.append(otitle)
else:
data.append(title[0])
data.append(" ")
score = re.findall(findscore, item)[0]
data.append(score)
Num = re.findall(findnum, item)[0]
data.append(Num)
inq = re.findall(findinq, item)
if len(inq) != 0:
inq = inq[0].replace("。", " ")
data.append(inq)
else:
data.append(" ")
context = re.findall(findcontext, item)[0]
context = re.sub('<br(\s+)?/>(\s+)?', " ", context)
context = re.sub('/', " ", context)
data.append(context.strip())
datalist.append(data)
return datalist
def askURL(url):
head = {"User-Agent": "User-Agent: Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.107 Mobile Safari/537.36"}
req = urllib.request.Request(url, headers=head)
html = ""
try:
response = urllib.request.urlopen(req)
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 saveData(datalist, savepath):
workbook = xlwt.Workbook(encoding="utf-8", style_compression=0)
sheet = workbook.add_sheet('豆瓣电影top250', cell_overwrite_ok=True)
col = ("电影链接", "图片链接", "影片中文名", "影片外国名", "评分", "评分数", "概况", "sss")
for i in range(0, 8):
sheet.write(0, i, col[i])
for i in range(0, 250):
print("%d条" % i)
data = datalist[i]
for j in range(0, 8):
sheet.write(i + 1, j, data[j])
workbook.save(savepath)
if __name__ == "__main__":
main()
print("爬取完毕")
将excel表的数据导入mysql中
from sqlalchemy import create_engine
import pymysql
import pandas as pd
engine = create_engine('mysql+pymysql://root:1234@localhost:3308/house?charset=utf8')
print(engine)
formlist = pd.read_sql_query('show tables', con=engine)
print('house数据库数据表清单为:','\n', formlist)
data = pd.read_excel('E:/pachong/pachong_new/豆瓣1.xls')
print('爬下的资料为:',data)
data.to_sql('douban', con=engine, index=False, if_exists='replace')