[database]
connect = mysql
sleep = no
test = yes

# -*- coding:utf-8 -*-
__author__ = 'guoqianqian'
import os
import ConfigParser
import os
current_dir = os.path.abspath(os.path.dirname(__file__))
class OperationalError(Exception):
    """operation error."""
class Dictionary(dict):
    """ custom dict."""
    def __getattr__(self, key):
        return self.get(key, None)
    __setattr__ = dict.__setitem__
    __delattr__ = dict.__delitem__
class Config:
    def __init__(self, file_name="test", cfg=None):
        """
        @param file_name: file name without extension.
        @param cfg: configuration file path.
        """
        env = {}
        for key, value in os.environ.items():
            if key.startswith("TEST_"):
                env[key] = value
        config = ConfigParser.ConfigParser(env)
        if cfg:
            config.read(cfg)
        else:
            config.read(os.path.join(current_dir, "conf", "%s.conf" % file_name))
        for section in config.sections():
            setattr(self, section, Dictionary())
            for name, raw_value in config.items(section):
                try:
                    # Ugly fix to avoid '0' and '1' to be parsed as a
                    # boolean value.
                    # We raise an exception to goto fail^w parse it
                    # as integer.
                    if config.get(section, name) in ["0", "1"]:
                        raise ValueError
                    value = config.getboolean(section, name)
                except ValueError:
                    try:
                        value = config.getint(section, name)
                    except ValueError:
                        value = config.get(section, name)
                setattr(getattr(self, section), name, value)
    def get(self, section):
        """Get option.
        @param section: section to fetch.
        @return: option value.
        """
        try:
            return getattr(self, section)
        except AttributeError as e:
            raise OperationalError("Option %s is not found in "
                                         "configuration, error: %s" %
                                         (section, e))
if __name__ == "__main__":
    conf = Config()
    print conf.get("database").connect
    print conf.get("database").sleep
    print conf.get("database").test

demo
? ? conf
? ? ? ? test.conf
? ? config.py

import configparser
cf = configparser.ConfigParser()
cf.read("E:\Crawler\config.ini")  # 讀取配置文件，如果寫(xiě)文件的絕對(duì)路徑，就可以不用os模塊
secs = cf.sections()  # 獲取文件中所有的section(一個(gè)配置文件中可以有多個(gè)配置，如數(shù)據(jù)庫(kù)相關(guān)的配置，郵箱相關(guān)的配置，                        每個(gè)section由[]包裹，即[section])，并以列表的形式返回
print(secs)
options = cf.options("Mysql-Database")  # 獲取某個(gè)section名為Mysql-Database所對(duì)應(yīng)的鍵
print(options)
items = cf.items("Mysql-Database")  # 獲取section名為Mysql-Database所對(duì)應(yīng)的全部鍵值對(duì)
print(items)
host = cf.get("Mysql-Database", "host")  # 獲取[Mysql-Database]中host對(duì)應(yīng)的值
print(host)

import configparser
import os
root_dir = os.path.dirname(os.path.abspath('.'))  # 獲取當(dāng)前文件所在目錄的上一級(jí)目錄，即項(xiàng)目所在目錄E:\Crawler
cf = configparser.ConfigParser()
cf.read(root_dir+"/config.ini")  # 拼接得到config.ini文件的路徑，直接使用
secs = cf.sections()  # 獲取文件中所有的section(一個(gè)配置文件中可以有多個(gè)配置，如數(shù)據(jù)庫(kù)相關(guān)的配置，郵箱相關(guān)的配置，每個(gè)section由[]包裹，即[section])，并以列表的形式返回
print(secs)
options = cf.options("Mysql-Database")  # 獲取某個(gè)section名為Mysql-Database所對(duì)應(yīng)的鍵
print(options)
items = cf.items("Mysql-Database")  # 獲取section名為Mysql-Database所對(duì)應(yīng)的全部鍵值對(duì)
print(items)
host = cf.get("Mysql-Database", "host")  # 獲取[Mysql-Database]中host對(duì)應(yīng)的值
print(host)

import configparser
import os
root_dir = os.path.dirname(os.path.abspath('.'))  # 獲取當(dāng)前文件所在目錄的上一級(jí)目錄，即項(xiàng)目所在目錄E:\Crawler
configpath = os.path.join(root_dir, "config.ini")
cf = configparser.ConfigParser()
cf.read(configpath)  # 讀取配置文件
secs = cf.sections()  # 獲取文件中所有的section(一個(gè)配置文件中可以有多個(gè)配置，如數(shù)據(jù)庫(kù)相關(guān)的配置，郵箱相關(guān)的配置，每個(gè)section由[]包裹，即[section])，并以列表的形式返回
print(secs)
options = cf.options("Mysql-Database")  # 獲取某個(gè)section名為Mysql-Database所對(duì)應(yīng)的鍵
print(options)
items = cf.items("Mysql-Database")  # 獲取section名為Mysql-Database所對(duì)應(yīng)的全部鍵值對(duì)
print(items)
host = cf.get("Mysql-Database", "host")  # 獲取[Mysql-Database]中host對(duì)應(yīng)的值
print(host)

import configparser
import os
class ReadConfig:
    """定義一個(gè)讀取配置文件的類"""
    def __init__(self, filepath=None):
        if filepath:
            configpath = filepath
        else:
            root_dir = os.path.dirname(os.path.abspath('.'))
            configpath = os.path.join(root_dir, "config.ini")
        self.cf = configparser.ConfigParser()
        self.cf.read(configpath)
    def get_db(self, param):
        value = self.cf.get("Mysql-Database", param)
        return value
if __name__ == '__main__':
    test = ReadConfig()
    t = test.get_db("host")
    print(t)

# coding: utf-8
# author: hmk
from common.readconfig import ReadConfig
import pymysql.cursors
class HandleMysql:
    def __init__(self):
        self.data = ReadConfig()
    def conn_mysql(self):
        """連接數(shù)據(jù)庫(kù)"""
        host = self.data.get_db("host")
        user = self.data.get_db("user")
        password = self.data.get_db("password")
        db = self.data.get_db("db")
        charset = self.data.get_db("charset")
        self.conn = pymysql.connect(host=host, user=user, password=password, db=db, charset=charset)
        self.cur = self.conn.cursor()
    def execute_sql(self, sql, data):
        """執(zhí)行操作數(shù)據(jù)的相關(guān)sql"""
        self.conn_mysql()
        self.cur.execute(sql, data)
        self.conn.commit()
    def search(self, sql):
        """執(zhí)行查詢sql"""
        self.conn_mysql()
        self.cur.execute(sql)
        return self.cur.fetchall()
    def close_mysql(self):
        """關(guān)閉數(shù)據(jù)庫(kù)連接"""
        self.cur.close()
        self.conn.close()
if __name__ == '__main__':
    test = HandleMysql()
    sql = "select * from maoyan_movie"
    for i in test.search(sql):
        print(i)

# coding: utf-8
# author: hmk
import requests
import re
from common import handleDB
class Crawler:
    """定義一個(gè)爬蟲(chóng)類"""
    def __init__(self):
        self.db = handleDB.HandleMysql()
    @staticmethod
    def get_html(url, header):
        response = requests.get(url=url, headers=header)
        if response.status_code == 200:
            return response.text
        else:
            return None
    @staticmethod
    def get_data(html, list_data):
        pattern = re.compile(r'<dd>.*?<i.*?>(\d+)</i>.*?'  # 匹配電影排名
                             r'<p class="name"><a.*?data-val=".*?">(.*?)'  # 匹配電影名稱
                             r'</a>.*?<p.*?class="releasetime">(.*?)</p>'  # 匹配上映時(shí)間
                             r'.*?<i.*?"integer">(.*?)</i>'  # 匹配分?jǐn)?shù)的整數(shù)位
                             r'.*?<i.*?"fraction">(.*?)</i>.*?</dd>', re.S)  # 匹配分?jǐn)?shù)小數(shù)位
        m = pattern.findall(html)
        for i in m:  # 因?yàn)槠ヅ涞降乃薪Y(jié)果會(huì)以列表形式返回，每部電影信息以元組形式保存，所以可以迭代處理每組電影信息
            ranking = i[0]  # 提取一組電影信息中的排名
            movie = i[1]  # 提取一組電影信息中的名稱
            release_time = i[2]  # 提取一組電影信息中的上映時(shí)間
            score = i[3] + i[4]  # 提取一組電影信息中的分?jǐn)?shù),這里把分?jǐn)?shù)的整數(shù)部分和小數(shù)部分拼在一起
            list_data.append([ranking, movie, release_time, score])  # 每提取一組電影信息就放到一個(gè)列表中，同時(shí)追加到一個(gè)大列表里，這樣最后得到的大列表就包含所有電影信息
    def write_data(self, sql, data):
        self.db.conn_mysql()
        try:
            self.db.execute_sql(sql, data)
            print('導(dǎo)入成功')
        except:
            print('導(dǎo)入失敗')
        self.db.close_mysql()
    def run_main(self):
        start_url = 'http://maoyan.com/board/4'
        depth = 10  # 爬取深度(翻頁(yè))
        header = {"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
                  "Accept-Encoding": "gzip, deflate, sdch",
                  "Accept-Language": "zh-CN,zh;q=0.8",
                  "Cache-Control": "max-age=0",
                  "Connection": "keep-alive",
                  "Host": "maoyan.com",
                  "Referer": "http://maoyan.com/board",
                  "Upgrade-Insecure-Requests": "1",
                  "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.75 Safari/537.36"}
        for i in range(depth):
            url = start_url + '?offset=' + str(10 * i)
            html = self.get_html(url, header)
            list_data = []
            self.get_data(html, list_data)
            for i in list_data:
                """這里的list_data參數(shù)是指正則匹配并處理后的列表數(shù)據(jù)(是一個(gè)大列表，包含所有電影信息，每個(gè)電影信息都存在各自的一個(gè)列表中；
                對(duì)大列表進(jìn)行迭代，提取每組電影信息，這樣提取到的每組電影信息都是一個(gè)小列表，然后就可以把每組電影信息寫(xiě)入數(shù)據(jù)庫(kù)了)"""
                movie = i  # 每組電影信息，這里可以看做是準(zhǔn)備插入數(shù)據(jù)庫(kù)的每組電影數(shù)據(jù)
                sql = "insert into maoyan_movie(ranking,movie,release_time,score) values(%s, %s, %s, %s)"  # sql插入語(yǔ)句
                self.write_data(sql, movie)
if __name__ == '__main__':
    test = Crawler()
    test.run_main()