一、不写入Mysql

以爬取哪儿网为例。

以下为脚本：

from pyspider.libs.base_handler import *

class Handler(BaseHandler):

crawl_config = {

}

@every(minutes=24 * 60)

def on_start(self):

self.crawl('https://travel.qunar.com/travelbook/list.htm', callback=self.index_page, validate_cert=False)

@config(age=100 * 24 * 60 * 60)

def index_page(self, response):

for each in response.doc('li > .tit > a').items():

self.crawl(each.attr.href, callback=self.detail_page, validate_cert=False, fetch_type='js')

next = response.doc('.next').attr.href

self.crawl(next, callback=self.index_page)

@config(priority=2)

def detail_page(self, response):

return {

"url": response.url,

"title": response.doc('#booktitle').text(),

"date": response.doc('.when .data').text(),

"day": response.doc('.howlong .data').text(),

"who": response.doc('.who .data').text(),

"text": response.doc('#b_panel_schedule').text(),

"image": response.doc('.cover_img').text(),

}

这个脚本里只是单纯的将结果打印在pyspider 的web ui中，并没有存到其它地方。

二、存入Mysql中

插入数据库的话，需要我们在调用它之前定义一个save_in_mysql函数。 并且需要将连接数据库等初始化放在__init__函数中。

注： pymysql.connect('localhost', '账号', '密码', '数据库', charset='utf8')

# 连接数据库

def __init__(self):

self.db = pymysql.connect('localhost', 'root', 'root', 'qunar', charset='utf8')

def save_in_mysql(self, url, title, date, day, who, text, image):

try:

cursor = self.db.cursor()

sql = 'INSERT INTO qunar(url, title, date, day, who, text, image) \

VALUES (%s, %s , %s, %s, %s, %s, %s)' # 插入数据库的SQL语句

print(sql)

cursor.execute(sql, (url, title, date, day, who, text, image))

print(cursor.lastrowid)

self.db.commit()

except Exception as e:

print(e)

self.db.rollback()

然后在detail_page中调用save_in_mysql函数:

@config(priority=2)

def detail_page(self, response):

url = response.url

title = response.doc('title').text()

date = response.doc('.when .data').text()

day = response.doc('.howlong .data').text()

who = response.doc('.who .data').text()

text = response.doc('#b_panel_schedule').text()[0:100].replace('\"', '\'', 10)

image = response.doc('.cover_img').attr.src

# 插入数据库

self.save_in_mysql(url, title, date, day, who, text, image)

return {

"url": response.url,

"title": response.doc('title').text(),

"date": response.doc('.when .data').text(),

"day": response.doc('.howlong .data').text(),

"who": response.doc('.who .data').text(),

"text": response.doc('#b_panel_schedule').text(),

"image": response.doc('.cover_img').attr.src

}

三、完整代码、数据库建设及运行结果 (代码可直接跑)

#!/usr/bin/env python

# -*- encoding: utf-8 -*-

# Created on 2019-07-02 21:37:08

# Project: qunar

from pyspider.libs.base_handler import *

import pymysql

class Handler(BaseHandler):

crawl_config = {

}

# 连接数据库

def __init__(self):

self.db = pymysql.connect('localhost', 'root', 'root', 'qunar', charset='utf8')

def save_in_mysql(self, url, title, date, day, who, text, image):

try:

cursor = self.db.cursor()

sql = 'INSERT INTO qunar(url, title, date, day, who, text, image) \

VALUES (%s, %s , %s, %s, %s, %s, %s)' # 插入数据库的SQL语句

print(sql)

cursor.execute(sql, (url, title, date, day, who, text, image))

print(cursor.lastrowid)

self.db.commit()

except Exception as e:

print(e)

self.db.rollback()

@every(minutes=24 * 60)

def on_start(self):

self.crawl('http://travel.qunar.com/travelbook/list.htm', callback=self.index_page)

@config(age=10 * 24 * 60 * 60)

def index_page(self, response):

for each in response.doc('li > .tit > a').items():

self.crawl(each.attr.href, callback=self.detail_page, fetch_type='js')

next_url = response.doc('.next').attr.href

self.crawl(next_url, callback=self.index_page)

@config(priority=2)

def detail_page(self, response):

url = response.url

title = response.doc('title').text()

date = response.doc('.when .data').text()

day = response.doc('.howlong .data').text()

who = response.doc('.who .data').text()

text = response.doc('#b_panel_schedule').text()[0:100].replace('\"', '\'', 10)

image = response.doc('.cover_img').attr.src

# 存入数据库

self.save_in_mysql(url, title, date, day, who, text, image)

return {

"url": response.url,

"title": response.doc('title').text(),

"date": response.doc('.when .data').text(),

"day": response.doc('.howlong .data').text(),

"who": response.doc('.who .data').text(),

"text": response.doc('#b_panel_schedule').text(),

"image": response.doc('.cover_img').attr.src

}

数据库建设：

结果：