爬虫第二篇：爬虫详解之存储数据

将数据存储到CSV文件

import urllib.request
import re
import csv

url = 'https://maoyan.com/board/4?offset=10'
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
}

# 获取页面
req = urllib.request.Request(url, headers=headers)
res = urllib.request.urlopen(req)
html = res.read().decode('utf-8')

# 解析页面
p = re.compile('<div class="movie-item-info">.*?title="(.*?)".*?class="star">(.*?)</p>.*?releasetime">(.*?)</p>',re.S)
rList = p.findall(html)

# 存储到CSV
for r in rList:
    r = [r[0].strip(),r[1].strip(),r[2].strip()]
    with open('my1.csv','a',newline="") as f:
        # 创建写入对象
        writer = csv.writer(f)
        writer.writerow(r)

将数据存储到mysql中

import urllib.request
import re
import pymysql
import warnings

warnings.filterwarnings("ignore")

url = 'https://maoyan.com/board/4?offset=10'
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
           }

# 创建数据库连接对象
db = pymysql.connect(
    "localhost",
    "root",
    "123456",
    "spiderdb",
    charset="utf8")
# 游标对象
cursor = db.cursor()

# 获取页面
req = urllib.request.Request(url, headers=headers)
res = urllib.request.urlopen(req)
html = res.read().decode('utf-8')

# 解析页面
p = re.compile(
    '<div class="movie-item-info">.*?title="(.*?)".*?class="star">(.*?)</p>.*?releasetime">(.*?)</p>', re.S)
rList = p.findall(html)
# 存储到CSV
ins = 'insert into film(
          name,star,releasetime) 
          values(%s,%s,%s)'
for r in rList:
    L = [r[0].strip(),
         r[1].strip(),
         r[2].strip()[5:15]
         ]
    cursor.execute(ins,L)
    db.commit()

将数据存储到pymongo中

import urllib.request
import re
import pymongo

url = 'https://maoyan.com/board/4?offset=10'
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
           }

# 创建连接对象
conn = pymongo.MongoClient("127.0.0.1", 27017)
db = conn["spiderdb"]
myset = db["film"]

# 获取页面
req = urllib.request.Request(url, headers=headers)
res = urllib.request.urlopen(req)
html = res.read().decode('utf-8')

# 解析页面
p = re.compile(
    '<div class="movie-item-info">.*?title="(.*?)".*?class="star">(.*?)</p>.*?releasetime">(.*?)</p>', re.S)
rList = p.findall(html)

# 存储到pymongo
for r in rList:
    d = {
        "name": r[0].strip(),
        "star": r[1].strip(),
        "releasetime": r[2].strip()
    }
    myset.insert_one(d)