1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
| def parseBaidu(keyword, pagenum):
keywordsBaseURL = 'https://www.baidu.com/s?wd=' + str(quote(keyword)) + '&oq=' + str(quote(keyword)) + '&ie=utf-8' + '&pn='
pnum = 0
while pnum <= int(pagenum):
baseURL = keywordsBaseURL + str(pnum*10)
try:
request = requests.get(baseURL, headers=headers)
soup = BeautifulSoup(request.text, "html.parser")
for a in soup.select('div.c-container > h3 > a'):
url = requests.get(a['href'], headers=headers).url
yield url
except:
yield None
finally:
pnum += 1
|