2018年07月25日 20:03:14 呢喃無音 閱讀數:50html
python爬取豆瓣電影Top250的信息。python
初學,因此代碼的不夠美觀和精煉。app
若是代碼有錯,請各位讀者在評論區評論,以避免誤導其餘同窗。動畫
(可能也沒多少人看)spa
import requests
#從bs4中導入BeautifulSoup模塊
from bs4 import BeautifulSoup
#獲取電影的名稱(中文,外文,其餘)
def get_movies_name():
#定製請求的頭部
headers = {
"user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:61.0) Gecko/20100101 Firefox/61.0",
"Host":"movie.douban.com"
}
movie_chinese_list=[]
movie_english_list=[]
movie_other_name_list=[]
for j in range(0,10):
i = (25 * j)
r = requests.get("https://movie.douban.com/top250?start="+str(i)+"&filter=",headers=headers)
soup=BeautifulSoup(r.text,"html.parser")
# 兩個參數:(標籤,標識符)
div_list=soup.find_all("div",class_="hd")
for each in div_list:
#each.a.span只會定位到a標籤下的第一個標籤的內容
#each.a.contents會定位到a標籤下的每個標籤的內容
#print(len(each.a.contents))
#movie_chinese=each.a.span.text.strip()
#第一個爲0.
movie_chinese=each.a.contents[1].text.strip()
#strip()除去字符串開頭和結尾指定的字符,默認爲空格或換行
movie_english=each.a.contents[3].text.strip()
movie_english=movie_english[2:]
#其餘名稱爲第6個內容,但可能存在沒有其餘名稱的電影。
if len(each.a.contents)>5:
movie_other=each.a.contents[5].text.strip()
movie_other=movie_other[2:]
movie_chinese_list.append(movie_chinese)
movie_english_list.append(movie_english)
movie_other_name_list.append(movie_other)
return movie_chinese_list,movie_english_list,movie_other_name_list
#獲取電影的導演和主演
def get_other_contents():
i=0
headers = {
"user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:61.0) Gecko/20100101 Firefox/61.0",
"Host":"movie.douban.com"
}
directors_list=[]#導演
starring_list=[]#主演
release_date_list=[]#上映年份
movie_country_list=[]#電影國別
film_classification_list=[]#電影分類
for j in range(0, 10):
i = (25 * j)
r = requests.get("https://movie.douban.com/top250?start=" + str(i) + "&filter=", headers=headers)
soup = BeautifulSoup(r.text, "html.parser")
div_list=soup.find_all("div",class_="bd")
for each in div_list:
if len(each.p.contents)>1:
"""國家,年份,類別"""
#對獲得的字符串進行處理
movie_information=each.p.contents[2].strip()
#對字符串經過」/「切片
movie_information=movie_information.split("/")
#去掉多餘的字符。
release_date_list.append(movie_information[0].strip("\xa0"))
movie_country_list.append(movie_information[1].strip(" "))
film_classification_list.append(movie_information[2].strip(" "))
"""導演,主演"""
# 顯示p標籤下第一部分的所有內容
#print(each.p.contents[0].strip())
#用" "對字符串進行分割
each_movie = each.p.contents[0].strip().split(" ")
director=each_movie[0]
#存在有導演,無主演的電影(動畫片)
if len(each_movie)>1:
starring=each_movie[1]
#去掉多餘字符(導演:)
directors_list.append(director.strip("導演:"))
# 去掉多餘字符(導演:. 和 /)
starring_list.append(starring.strip("主演:").strip(".").strip("/"))
return directors_list,starring_list,release_date_list,movie_country_list,film_classification_list
#獲取電影評分和經典影評
def get_movie_score():
headers = {
"user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:61.0) Gecko/20100101 Firefox/61.0",
"Host":"movie.douban.com"
}
movie_score_list = []#評分
movie_review_list = []#經典影評
for j in range(0, 10):
i = (25 * j)
r = requests.get("https://movie.douban.com/top250?start=" + str(i) + "&filter=", headers=headers)
soup = BeautifulSoup(r.text, "html.parser")
div_list_1=soup.find_all("div",class_="star")
div_list_2 = soup.find_all("p", class_="quote")
for each_1 in div_list_1:
#經過contents把代碼轉化成列表.
#經過text提取關鍵字
movie_score=each_1.contents[3].text
movie_score_list.append(movie_score)
for each_2 in div_list_2:
#經過contents把代碼轉化成列表.
#經過text提取關鍵字
#列表中只有一個元素
movie_review=each_2.text
movie_review_list.append(movie_review.strip())
return movie_review_list,movie_score_list
(movie_chinese_list,movie_english_list,movie_other_name_list)=get_movies_name()
print("豆瓣電影Top250中文電影名:(共%d個電影)"%len(movie_chinese_list))
print(movie_chinese_list)
print("豆瓣電影Top250外文電影名:(共%d個電影)"%len(movie_english_list))
print(movie_english_list)
print("豆瓣電影Top250其餘電影名:(共%d個電影)"%len(movie_other_name_list))
print(movie_other_name_list)
(directors_list,starring_list,release_date_list,movie_country_list,film_classification_list)=get_other_contents()
print("導演:")
print(directors_list)
print("主演:")
print(starring_list)
print("年份:")
print(release_date_list)
print("國家:")
print(movie_country_list)
print("類別:")
print(film_classification_list)
(movie_review_list,movie_score_list)=get_movie_score()
print("評分:")
print(movie_score_list)
print("經典影評:")
print(movie_review_list)
.net