1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148
| from bs4 import BeautifulSoup import re import urllib.request,urllib.error import xlwt import sqlite3
findLink = re.compile(r'<a href="(.*?)">') findImgSrc = re.compile(r'<img.*src="(.*?)"',re.S) findTitle = re.compile(r'<span class="title">(.*)</span>') findRating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>') findJudge = re.compile(r'<span>(\d*)人评价</span>') findInq = re.compile(r'<span class="inq">(.*)</span>') findBd = re.compile(r'<p class="">(.*?)</p>',re.S)
def main(): baseurl = "https://movie.douban.com/top250?start=" datalist = getData(baseurl) dbpath = "movie.db" saveData(datalist,dbpath)
def getData(baseurl): datalist = [] for i in range(0,10): url = baseurl + str(i*25) html = askURL(url)
soup = BeautifulSoup(html,"html.parser") for item in soup.find_all('div',class_="item"): data = [] item = str(item)
link = re.findall(findLink,item)[0] data.append(link)
imgSrc = re.findall(findImgSrc,item)[0] data.append(imgSrc)
titles = re.findall(findTitle, item) if len(titles)==2: ctitle = titles[0] otitle = titles[1].replace("/","") data.append(ctitle) data.append(otitle) else: data.append(titles[0]) data.append('')
rating = re.findall(findRating, item)[0] data.append(rating)
judgeNum = re.findall(findJudge, item)[0] data.append(judgeNum)
inq = re.findall(findInq,item) if len(inq) != 0: inq = inq[0].replace("。","") data.append(inq) else: data.append('')
bd = re.findall(findBd,item)[0] bd = re.sub('<br(\s+)?/>(\s+)?',"",bd) bd = re.sub('/',"",bd) data.append(bd.strip())
datalist.append(data) return datalist
def askURL(url): head = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.108 Safari/537.36"} request = urllib.request.Request(url,headers=head) html = "" try: response = urllib.request.urlopen(request) html = response.read().decode("utf-8") except urllib.error.URLError as e: if hasattr(e,"code"): print(e.code) if hasattr(e,"reason"): print(e.reason)
return html
def createTable(dbpath): sql = ''' CREATE TABLE movie250 ( id integer primary key autoincrement, info_link TEXT, pic_link TEXT, cname VARCHAR(255), oname VARCHAR(255), score FLOAT, rated NUMERIC, instroduction TEXT, info text ); ''' conn = sqlite3.connect(dbpath) cursor = conn.cursor() cursor.execute(sql) conn.commit() conn.close()
def saveData(datalist,dbpath): createTable(dbpath) conn = sqlite3.connect(dbpath) cur = conn.cursor()
for data in datalist: for index in range(len(data)): if index == 4 or index == 5: continue data[index] = '"'+data[index]+'"' sql = ''' INSERT INTO movie250( info_link, pic_link, cname, oname, score, rated, instroduction, info ) VALUES(%s) '''%",".join(data) cur.execute(sql) conn.commit() cur.close() conn.close()
if __name__ == '__main__': main() print("爬取完毕")
|