python3.x爬虫实战：阿里巴巴网站定向信息抓取

#!/usr/bin/env python3# -*- coding: utf-8 -*-import requestsimport refrom bs4 import BeautifulSoupfrom selenium import webdriverfrom selenium.common.exceptions import TimeoutExceptionfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.support import expected_conditions as ECimport pymongoimport timefrom pymongo.collection import ReturnDocumentb=webdriver.Chrome()wait=WebDriverWait(b,10)KEY_WORD="建筑"URL="https://www.XXXXXXXXX.com"MONGO_URL='localhost'MONGO_DB='albbs'MONGO_TABLE='supplier'client=pymongo.MongoClient(MONGO_URL)db=client[MONGO_DB]def search():    try:        b.get(URL)        ul=b.find_element_by_css_selector("#masthead > div.ali-search.fd-right > div.searchtypeContainer > ul")        ul.click()        b.find_element(By.XPATH,"//*[@id='masthead']/div[2]/div[1]/ul/li[2]").click()        input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#alisearch-keywords")))        submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, "#alisearch-submit")))        input.send_keys(KEY_WORD)        submit.click()        total= wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,"#sw_mod_pagination_form > div > span")))        get_url()        time.sleep(2)        return total.text    except TimeoutException:        return search()def next_page(page_number):    try:        input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#jumpto")))        submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, "#jump-sub")))        input.clear()        input.send_keys(page_number)        submit.click()        time.sleep(5)        wait.until(EC.text_to_be_present_in_element((By.CSS_SELECTOR,"#sw_mod_pagination_content > div > span.page-cur"),str(page_number)))        get_url()        time.sleep(8)    except TimeoutException:        next_page(page_number)def get_url():    wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,"#sw_mod_searchlist")))        html=b.page_source    soup = BeautifulSoup(html,'html.parser')    a=soup.find_all("a",class_="list-item-title-text")    for i in a:        try:            get_information_url(i.attrs['href'])                    except:            continuedef save_to_mongo(results):    try:        if db[MONGO_TABLE].insert(results):            print('存储成功')    except:        print('存储异常')def get_information_url(url):    try:        b.get(url)        contactinfo=b.find_element_by_link_text("联系方式")        contactinfo.click()        time.sleep(1)        wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,"#site_content > div.grid-main > div > div > div > div.m-content")))        html=b.page_source        soup = BeautifulSoup(html,'html.parser')        div=soup.find("h4")        company_name=div.text        contactinfo_name=soup.find("a",class_="membername").text        MobilePhone=soup.find("dl",class_="m-mobilephone").text        MobilePhone=int(re.compile('(\d+)').search(MobilePhone).group())        addr=soup.find("dd",class_="address").text        print(company_name)        print(contactinfo_name)        print(MobilePhone)        print(addr)        contactinfos={"公司名":company_name,"联系人":contactinfo_name,"手机号码":MobilePhone,"地址":addr}        save_to_mongo(contactinfos)        time.sleep(8)    except TimeoutException:        get_information_url(url)def main():    total=search()    total=int(re.compile('(\d+)').search(total).group(1))    print(total)    for i in range(2,total +1):        next_page(i)if __name__ == '__main__':    main()

自己的学习笔记。