協程提取上海人民法院網站信息

　　協程提取上海人民法院網站信息：

import gevent
import gevent.monkey
import selenium
import selenium.webdriver
import urllib.request
from bs4 import BeautifulSoup
import time
gevent.monkey.patch_all()  #自動切換

def download(url,start,end,file):
    driver = selenium.webdriver.PhantomJS(executable_path=r"D:\python爬蟲視頻\爬蟲代碼\seleniumText\phantomjs-2.1.1-windows\bin\phantomjs.exe")
    driver.get(url)
    gevent.sleep(10)
    #0，100 ；100-200 ；200-300
    try:
        for i in range(start,end):
            js="javascript:goPage('"+str(i)+"')"
            driver.execute_script(js)  # 共有1175頁
            print("js is run",i)
            gevent.sleep(10)  #循環提取頁面
            #提取頁面的數據
            soup = BeautifulSoup(driver.page_source, "lxml")  # 解析數據
            table = soup.find("table", attrs={"id": "report"})  # attrs 爲屬性
            trs = table.find("tr").find_next_siblings()  # .find_next_siblings() 從下一個查找
            for tr in trs:
                tds = tr.find_all("td")
                linestr=""   #拼合數據
                for td in tds:
                    linestr+=td.text
                    linestr+=" # "   #分割  好作切割
                linestr += "\r\n"
                print(linestr)
                file.write(linestr.encode("utf-8",errors="ignore"))  #寫入保存文件
    except:
        pass
    driver.quit()

url="http://www.hshfy.sh.cn/shfy/gweb2017/ktgg_search.jsp?zd=splc"
file=open("save.text","wb")  #保存文件
#建立一個列表，加載多個任務,    #gevent.joinall  表示所有加入協程
gevent.joinall([gevent.spawn(download,url,0,235,file),   #0,2 設置分配抓取頁數
gevent.spawn(download,url,235,470,file),        #file  爲共享一個文件
gevent.spawn(download,url,470,705,file),
gevent.spawn(download,url,705,940,file),
gevent.spawn(download,url,940,1175,file),
                ])
file.close()