基于python爬取新浪微博爬虫以及生成词云源码.zip

import os import re import sys from datetime import datetime, timedelta from urllib.parse import unquote import scrapy import dbscrapy.utils.util as util from scrapy.exceptions import CloseSpider from scrapy.utils.project import get_project_settings from dbscrapy.items import DbscrapyItem class SearchSpider(scrapy.Spider): # 提取了 settings.py 的信息 name = 'search' allowed_domains = ['weibo.com'] settings = get_project_settings() keyword_list = settings.get('KEYWORD_LIST') if not isinstance(keyword_list, list): if not os.path.isabs(keyword_list): keyword_list = os.getcwd() + os.sep + keyword_list if not os.path.isfile(keyword_list): sys.exit('不存在%s文件' % keyword_list) keyword_list = util.get_keyword_list(keyword_list) for i, keyword in enumerate(keyword_list): if len(keyword) > 2 and keyword[0] == '#' and keyword[-1] == '#': keyword_list[i] = '%23' + keyword[1:-1] + '%23' weibo_type = util.convert_weibo_type(settings.get('WEIBO_TYPE')) contain_type = util.convert_contain_type(settings.get('CONTAIN_TYPE')) regions = util.get_regions(settings.get('REGION')) base_url = 'https://s.weibo.com' start_date = settings.get('START_DATE', datetime.now().strftime('%Y-%m-%d')) end_date = settings.get('END_DATE', datetime.now().strftime('%Y-%m-%d')) if util.str_to_time(start_date) > util.str_to_time(end_date): sys.exit('settings.py配置错误，START_DATE值应早于或等于END_DATE值，请重新配置settings.py') further_threshold = settings.get('FURTHER_THRESHOLD', 46) mongo_error = False pymongo_error = False mysql_error = False pymysql_error = False def start_requests(self): start_date = datetime.strptime(self.start_date, '%Y-%m-%d') end_date = datetime.strptime(self.end_date, '%Y-%m-%d') + timedelta(days=1) start_str = start_date.strftime('%Y-%m-%d') + '-0' end_str = end_date.strftime('%Y-%m-%d') + '-0' for keyword in self.keyword_list: if not self.settings.get('REGION') or '全部' in self.settings.get( 'REGION'): base_url = 'https://s.weibo.com/weibo?q=%s' % keyword # https://s.weibo.com/weibo?q=人工智能 url = base_url + self.weibo_type # 0 https://s.weibo.com/weibo?q=人工智能&typeall=1 url += self.contain_type # 0 https://s.weibo.com/weibo?q=人工智能&typeall=1&timescope=custom:{2015-03-01}:{2020-03-01} url += '&timescope=custom:{}:{}'.format(start_str, end_str) yield scrapy.Request(url=url, callback=self.parse, meta={ 'base_url': base_url, 'keyword': keyword }) else: for region in self.regions.values(): base_url = ( 'https://s.weibo.com/weibo?q={}&region=custom:{}:1000' ).format(keyword, region['code']) url = base_url + self.weibo_type url += self.contain_type url += '&timescope=custom:{}:{}'.format(start_str, end_str) # 获取一个省的搜索结果 # meta: 可以将数据传入到parse_detail函数中 yield scrapy.Request(url=url, callback=self.parse, meta={ 'base_url': base_url, 'keyword': keyword, 'province': region }) def check_environment(self): """判断配置要求的软件是否已安装""" if self.pymongo_error: print('系统中可能没有安装pymongo库，请先运行 pip install pymongo ，再运行程序') raise CloseSpider() if self.mongo_error: print('系统中可能没有安装或启动MongoDB数据库，请先根据系统环境安装或启动MongoDB，再运行程序') raise CloseSpider() if self.pymysql_error: print('系统中可能没有安装pymysql库，请先运行 pip install pymysql ，再运行程序') raise CloseSpider() if self.mysql_error: print('系统中可能没有安装或正确配置MySQL数据库，请先根据系统环境安装或配置MySQL，再运行程序') raise CloseSpider() def parse(self, response): base_url = response.meta.get('base_url') keyword = response.meta.get('keyword') province = response.meta.get('province') is_empty = response.xpath( '//div[@class="card card-no-result s-pt20b40"]') page_count = len(response.xpath('//ul[@class="s-scroll"]/li')) if is_empty: print('当前页面搜索结果为空') elif page_count < self.further_threshold: # 解析当前页面 for weibo in self.parse_weibo(response): self.check_environment() yield weibo next_url = response.xpath( '//a[@class="next"]/@href').extract_first() if next_url: next_url = self.base_url + next_url yield scrapy.Request(url=next_url, callback=self.parse_page, meta={'keyword': keyword}) else: start_date = datetime.strptime(self.start_date, '%Y-%m-%d') end_date = datetime.strptime(self.end_date, '%Y-%m-%d') while start_date <= end_date: start_str = start_date.strftime('%Y-%m-%d') + '-0' start_date = start_date + timedelta(days=1) end_str = start_date.strftime('%Y-%m-%d') + '-0' url = base_url + self.weibo_type url += self.contain_type url += '&timescope=custom:{}:{}&page=1'.format( start_str, end_str) # 获取一天的搜索结果 yield scrapy.Request(url=url, callback=self.parse_by_day, meta={ 'base_url': base_url, 'keyword': keyword, 'province': province, 'date': start_str[:-2] }) def parse_by_day(self, response): """以天为单位筛选""" base_url = response.meta.get('base_url') keyword = response.meta.get('keyword') province = response.meta.get('province') is_empty = response.xpath( '//div[@class="card card-no-result s-pt20b40"]') date = response.meta.get('date') page_count = len(response.xpath('//ul[@class="s-scroll"]/li')) if is_empty: print('当前页面搜索结果为空') elif page_count < self.further_threshold: # 解析当前页面 for weibo in self.parse_weibo(response): self.check_environment() yield weibo next_url = response.xpath( '//a[@class="next"]/@href').extract_first() if next_url: next_url = self.base_url + next_url yield scrapy.Request(url=next_url, callback=self.parse_page, meta={'keyword': keyword}) else: start_date_str = date +