您好,登錄后才能下訂單哦!
怎么在Python中使用beautifulSoup4爬取數據?很多新手對此不是很清楚,為了幫助大家解決這個難題,下面小編將為大家詳細講解,有這方面需求的人可以來學習下,希望你能有所收獲。
具體如下:
#! /usr/bin/python3 # -*- coding:utf-8 -*- from urllib.request import urlopen as open from bs4 import BeautifulSoup import re import pymysql def find_top_ten(url): response = open(url) bs = BeautifulSoup(response,'html.parser') tags = bs.select('span.tag-item a') top_ten_href = [tag.get('href') for tag in tags] top_ten_tag = [tag.text for tag in tags] # print(top_ten_href) # print(top_ten_tag) return top_ten_href def insert_into_mysql(records): con = pymysql.connect(host='localhost',user='root',password='root',database='quotes',charset='utf8',port=3306) cursor = con.cursor() sql = "insert into quotes(content,author,tags) values(%s,%s,%s)" for record in records: cursor.execute(sql, record) con.commit() cursor.close() con.close() # http://quotes.toscrape.com/tag/love/ #要獲取對應標簽中所有的名言 所以這里要考慮分頁的情況 #經過在網頁上查看知道分頁查詢的url #http://quotes.toscrape.com/tag/love/page/1/ #判斷到那一頁沒有數據 div.container div.row [1] def find_link_content(link): page = 1 while True: new_link = "http://quotes.toscrape.com" + link + "page/" # print(new_link) new_link = new_link + str(page) print(new_link) sub_bs = open(new_link) sub_bs = BeautifulSoup(sub_bs,'html.parser') quotes = sub_bs.select('div.row div.col-md-8 span.text') # 如果沒有數據就退出 if len(quotes) == 0: break #名言 quotes = [quote.text.strip('“”') for quote in quotes] #作者 authors = sub_bs.select('small.author') authors = [author.text for author in authors] # 標簽 tags_list = sub_bs.select('meta.keywords') tags_list = [tags.get('content') for tags in tags_list] # print(authors) # print(quotes) #print(tags_list) record_list = [] for i in range(len(quotes)): tags = tags_list[i] tags = tags.replace(',',',') print(tags) record = [quotes[i],authors[i],tags] record_list.append(record) insert_into_mysql(record_list) page += 1 # def main(): url = "http://quotes.toscrape.com/" parent_link = find_top_ten(url) for link in parent_link: print(link) find_link_content(link) if __name__ == '__main__': main()
看完上述內容是否對您有幫助呢?如果還想對相關知識有進一步的了解或閱讀更多相關文章,請關注億速云行業資訊頻道,感謝您對億速云的支持。
免責聲明:本站發布的內容(圖片、視頻和文字)以原創、轉載和分享為主,文章觀點不代表本網站立場,如果涉及侵權請聯系站長郵箱:is@yisu.com進行舉報,并提供相關證據,一經查實,將立刻刪除涉嫌侵權內容。