0.windows安装scrapy
1、安装wheel: 在控制台输入pip install wheel即可自动完成安装 2、安装lxml: 到 https://www.lfd.uci.edu/~gohlke/pythonlibs/,往下拉找到 lxml,下载适合自己电脑 操作系统及python版本的.whl文件。cp27、cp35等代表python版本2.7、3.5,win32代表 32位windows操作系统,win_amd64代表64位操作系统。 下载完成后,右键点击文件-属性-安全-对象名称,可以复制到文件地址。复制完成后回到控制 台,输入“pip install 右键粘贴地址",然后按回车即可完成安装。 3、安装PyOpenssl 到 https://pypi.python.org/pypi/pyOpenSSL#downloads ,往下拉找到下面文件后下 载。下载完成后同安装lxml的方法,对该PyOpenssl的whl文件进行安装. windows系统下的scrapy框架安装及测试 4、安装Twisted 到 https://www.lfd.uci.edu/~gohlke/pythonlibs/#Twisted,往下拉找到Twisted,下载 适合自己电脑操作系统及python版本的.whl文件。同安装lxml的方法将Twisted安装完成。 5、安装Pywin32 到 https://sourceforge.net/projects/pywin32/files/pywin32/Build 220/,下载适合自 己电脑操作系统及python版本的文件,下载完成后双击即可开始安装。程序会自动定位 python的目录,所以不用自己调整安装设置,一直下一步就行了。 6、安装scrapy 进行完1-5步后,安装scrapy就很简单了,在控制台输入 pip install scrapy即可完成安装。
1.No module named win32api
pip install pypiwin32
2.文件夹下的文件找不到,或者No module named 'scrapy.pipelines' 或者no module named ×××.items?
scrapy项目处于pycharm项目的子项目,所以pycharm找不到items 。我的解决办法是在scrapy项目上右键-》make_directory as -->sources roo如果项目文件夹变这个颜色就可以了。
3.No module named PIL
pip install pillow
4.下载图片到本地、并提取本地保存地址
1)在settings.py中打开 ITEM_PIPELINES 的注释,在 ITEM_PIPELINES 中加入 ITEM_PIPELINES = { 'spider_first.pipelines.SpiderFirstPipeline': 300, 'scrapy.pipelines.images.ImagesPipeline':5, #后面的数字代表执行优先级 ,当执行pipeine的时候会按照数字由小到大执行 } 2)settings.py中加入 IMAGES_URLS_FIELD ="image_url" #image_url是在items.py中配置的网络爬取得图片地址 #配置保存本地的地址 project_dir=os.path.abspath(os.path.dirname(__file__)) #获取当前爬虫项目的绝对路径 IMAGES_STORE=os.path.join(project_dir,'images') #组装新的图片路径
5.python 安装mysql模块
windows
pip install mysqlclient
ubuntu
sudo apt-get install libmysqlclent-dev
centos
sudo yum install python-devel mysql-devel
6. IndentationError: unindent does not match any outer indentation level
方法名开头的时候别用空格,用tab符号
7. 连接池的代码
from twisted.enterprise import adbapi import MySQLdb.cursors class MysqlTwistedPipline(object): #通过连接池的方式 def __init__(self,dbpool): self.dbpool = dbpool @classmethod def from_settings(cls, settings): dbparms = dict( host=settings["MYSQL_HOST"], db=settings["MYSQL_DBNAME"], user=settings["MYSQL_USER"], passwd=settings["MYSQL_PASSWORD"], charset=settings["MYSQL_CHARSET"], cursorclass=MySQLdb.cursors.DictCursor, use_unicode=settings["MYSQL_USE_UNICODE"], ) dbpool = adbapi.ConnectionPool("MySQLdb", **dbparms) return cls(dbpool) def process_item(self, item, spider): # 使用twisted将mysql插入变成异步执行 query = self.dbpool.runInteraction(self.do_insert, item) query.addErrback(self.handle_error, item, spider) # 处理异常 def handle_error(self, failure, item, spider): # 处理异步插入的异常 print(failure) def do_insert(self, cursor, item): insert_sql = """ insert into jobbole(post_url_id,post_url,re_selector,img_url,img_path,zan,shoucang,pinglun,zhengwen,riqi,fenlei) VALUES(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s) """ cursor.execute(insert_sql, ( item["post_url_id"], item["post_url"], item["re_selector"], item["img_url"][0], item["img_path"], item["zan"], item["shoucang"], item["pinglun"], item["zhengwen"], item["riqi"], item["fenlei"]))
8. 验证码爬虫的解决方案
1.如果一个网站有下载验证码的功能,对于我这种还没深入了解机器学习,只能通过人工的方式来进行解决验证码的问题,咱们就进行手动的验证码解析,通过下载图片,然后根据图片手动的输入坐标或者验证码来完成,本质的目的是为了能够完成登录打入敌人的内部,吸收他们里面的养分 2.如果是针对https://www.zhihu.com/captcha.gif?r=1514042860066&type=login&lang=cn 记住要跟登录的用户的获取的通过session来进行 header这边直接github很多 我就不粘贴了 session = requests.session() response = session.get("https://www.zhihu.com/",headers=header) 图片类别的下载我遇到的坑是 with open(file_name, 'wb') as f: f.write(response.content) f.close() 记住如果网页打开直接是图片直接使用response.content 而不是response.text.ecode() 对于一些网站返回的是 unicode json格式看的时候很不爽 解决方案是: print(response.text.encode('latin-1').decode('unicode_escape'))
9. 出现主键冲突的时候解决ON DUPLICATE KEY UPDATE(只限mysql)
insert into zhihu_question (zhihu_id,topics,url,title,content,creat_time,update_time,answer_num,comments_num,watch_user_num,click_num,crawl_time,crawl_update_time) VALUES(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s) ON DUPLICATE KEY UPDATE comments_num=VALUES(comments_num),watch_user_num=VALUES(watch_user_num),click_num=VALUES(click_num)
10. srcapy items方法很强大通过反向调用的方式就可以动态控制
items
class ZhihuQuestionItem(scrapy.Item): zhihu_id = scrapy.Field() topics = scrapy.Field() url = scrapy.Field() title = scrapy.Field() content = scrapy.Field() creat_time = scrapy.Field() update_time = scrapy.Field() answer_num = scrapy.Field() comments_num = scrapy.Field() watch_user_num = scrapy.Field() click_num = scrapy.Field() def get_insert_sql(self): insert_sql = """ insert into zhihu_question (zhihu_id,topics,url,title,content,creat_time,update_time,answer_num,comments_num,watch_user_num,click_num,crawl_time,crawl_update_time) VALUES(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s) ON DUPLICATE KEY UPDATE comments_num=VALUES(comments_num),watch_user_num=VALUES(watch_user_num),click_num=VALUES(click_num) """ zhihu_id = self["zhihu_id"][0] topics = ",".join(self["topics"]) url = "".join(self["url"]) title = "".join(self["title"]) content = "".join(self["content"]) creat_time = datetime.datetime.now().strftime(SQL_DATETIME_FORMAT) update_time = datetime.datetime.now().strftime(SQL_DATETIME_FORMAT) answer_num = self["answer_num"][0] comments_num = get_nums(self["comments_num"][0]) watch_user_num = self["watch_user_num"][0] click_num = self["watch_user_num"][1] crawl_time = datetime.datetime.now().strftime(SQL_DATETIME_FORMAT) crawl_update_time =datetime.datetime.now().strftime(SQL_DATETIME_FORMAT) params = (zhihu_id,topics,url,title,content,creat_time,update_time,answer_num,comments_num,watch_user_num,click_num,crawl_time,crawl_update_time) return insert_sql,params
pipelines.py
class MysqlTwistedZhihuPipline(object): #通过连接池的方式 def __init__(self,dbpool): self.dbpool = dbpool @classmethod def from_settings(cls, settings): dbparms = dict( host=settings["MYSQL_HOST"], db=settings["MYSQL_DBNAME"], user=settings["MYSQL_USER"], passwd=settings["MYSQL_PASSWORD"], charset=settings["MYSQL_CHARSET"], cursorclass=MySQLdb.cursors.DictCursor, use_unicode=settings["MYSQL_USE_UNICODE"], ) dbpool = adbapi.ConnectionPool("MySQLdb", **dbparms) return cls(dbpool) def process_item(self, item, spider): # 使用twisted将mysql插入变成异步执行 query = self.dbpool.runInteraction(self.do_insert, item) query.addErrback(self.handle_error, item, spider) # 处理异常 def handle_error(self, failure, item, spider): # 处理异步插入的异常 print(failure) def do_insert(self, cursor, item): insert_sql,params = item.get_insert_sql() cursor.execute(insert_sql, params)
9. 'dict' object has no attribute 'has_key' Python3以后删除了has_key()方法
if adict.has_key(key1): 修改为: if key1 in adict:
10. 爬虫Max retries exceeded with url
页面中的requests不要直接都requests.post 尽量统一requests.session()然后运行完关闭。s.keep_alive = False
s = requests.session() s.keep_alive = False
11. 阿里云centos安装python3最牛逼的教程(make编译的是深坑啊,建议用yum)
sudo yum install epel-release sudo yum install python34 wget --no-check-certificate https://bootstrap.pypa.io/get-pip.py python3 get-pip.py pip3 -V