21.1.27

32652 ワード
スクロール python TIL テキストリンク
  • リクエスト、BeautifulSoup 4インストール後のデフォルト設定とページ数スクロール
    • import requests
from bs4 import BeautifulSoup

incruit_result = requests.get("https://search.incruit.com/list/search.asp?col=job&src=gsw*search&kw=%b9%e9%bf%a3%b5%e5&startno=0")

incruit_soup = BeautifulSoup(incruit_result.text, "html.parser")

paging = incruit_soup.find("p", {"class" : "sqr_paging sqr_pg_mid"})

pages = paging.find_all("a")

spans = []
for page in pages:
  spans.append(page.find("span"))
spans = spans[:-2]
# span으로 2~5페이지까지 나오고 마지막에 단추 두 개를 지웠음.
    すべてのページのジャンプボタンの前にspan値をスクロールするしかないようです.クロムに何か変化がありますか...
  • 最終ページ
    • を検索
    import requests
from bs4 import BeautifulSoup

incruit_result = requests.get("https://search.incruit.com/list/search.asp?col=job&src=gsw*search&kw=%b9%e9%bf%a3%b5%e5&startno=0")

incruit_soup = BeautifulSoup(incruit_result.text, "html.parser")

paging = incruit_soup.find("p", {"class" : "sqr_paging sqr_pg_mid"})

links = paging.find_all("a")

pages = []
for link in links:
  pages.append(link.find("span"))
pages = pages[:-2]
max_page = pages[-2]
# 5페이지니까.
    要求最大
  • ページ
    (incruit.py) 
    • import requests
from bs4 import BeautifulSoup

LIMIT = 20
URL = "https://search.incruit.com/list/search.asp?col=job&src=gsw*search&kw=%b9%e9%bf%a3%b5%e5&startno={LIMIT}"

def extract_incruit_pages():
  result = requests.get(URL)
  soup = BeautifulSoup(result.text, "html.parser")
  paging = soup.find("p", {"class" : "sqr_paging sqr_pg_mid"})
  links = paging.find_all("a")
  pages = []
  for link in links[:-2]:
    pages.append(int(link.string))
  max_page = pages[-2]
  return max_page

def extract_incruit_jobs(last_page):
  for page in range(last_page):
    result = requests.get(f"{URL}&startno={page*LIMIT}")
    print(result.status_code)
    (main.py)
    from incruit import extract_incruit_pages, extract_incruit_jobs

last_incruit_page = extract_incruit_pages()

extract_incruit_jobs(last_incruit_page)
    誤字に注意する.単純なものからもう少しで塞がれるところだった.幸いなことに、200枚はまあまあです.
  • 選抜職務
    • まず1ページの仕事を引いた.以前とは異なり、最後にget text()を使用すると、美化グループにコンテンツを抽出しやすくなります.
    import requests
from bs4 import BeautifulSoup

LIMIT = 20
URL = "https://search.incruit.com/list/search.asp?col=job&src=gsw*search&kw=%b9%e9%bf%a3%b5%e5&startno={LIMIT}"

def extract_incruit_pages():
  result = requests.get(URL)
  soup = BeautifulSoup(result.text, "html.parser")
  paging = soup.find("p", {"class" : "sqr_paging sqr_pg_mid"})
  links = paging.find_all("a")
  pages = []
  for link in links[:-2]:
    pages.append(int(link.string))
  max_page = pages[-2]
  return max_page

def extract_incruit_jobs(last_page):
  jobs = []
  #for page in range(last_page):
  result = requests.get(f"{URL}&startno={0*LIMIT}")
  soup = BeautifulSoup(result.text, "html.parser")
  results = soup.find_all("p", {"class" : "detail"})
  for result in results:
    title_case = result.find("span", {"class" : "rcrtTitle"})
    title = title_case.find("a").get_text()
    print(title)
  return jobs
    メイン料理は触らなかった.
  • 社名を抽出します.
    • こちらもNoneの価格がありますしかしこれはアンカーマークに囲まれていないテキストであり,いずれにしてもスクロールしても何の結果も生じない.残りはifゲートでstrを処理します.
    import requests
from bs4 import BeautifulSoup

LIMIT = 20
URL = "https://search.incruit.com/list/search.asp?col=job&src=gsw*search&kw=%b9%e9%bf%a3%b5%e5&startno={LIMIT}"

def extract_incruit_pages():
  result = requests.get(URL)
  soup = BeautifulSoup(result.text, "html.parser")
  paging = soup.find("p", {"class" : "sqr_paging sqr_pg_mid"})
  links = paging.find_all("a")
  pages = []
  for link in links[:-2]:
    pages.append(int(link.string))
  max_page = pages[-2]
  return max_page

def extract_incruit_jobs(last_page):
  jobs = []
  #for page in range(last_page):
  result = requests.get(f"{URL}&startno={0*LIMIT}")
  soup = BeautifulSoup(result.text, "html.parser")
  results = soup.find_all("p", {"class" : "detail"})
  for result in results:
    title = result.find("span", {"class" : "rcrtTitle"}).find("a").get_text()

  results2 = soup.find_all("h3")
  for result in results2:
    company = result.find("a")
    if company == result.find("h3"):
      company = str(result.find("h3"))
    else:
      company = str(result.find("a").string)
    print(company)
  return jobs
  • 枚だけ印刷したいのですが、他の資料と縛られています.このページは大変ですね.まず、役職と会社名のみを出力するスクロールで終了します.
    • (incruit.py)
    import requests
from bs4 import BeautifulSoup

LIMIT = 20
URL = "https://search.incruit.com/list/search.asp?col=job&src=gsw*search&kw=%b9%e9%bf%a3%b5%e5&startno={LIMIT}"

def extract_incruit_pages():
  result = requests.get(URL)
  soup = BeautifulSoup(result.text, "html.parser")
  paging = soup.find("p", {"class" : "sqr_paging sqr_pg_mid"})
  links = paging.find_all("a")
  pages = []
  for link in links[:-2]:
    pages.append(int(link.string))
  max_page = pages[-2]
  return max_page

def extract_incruit_jobs(last_page):
  jobs = []
  for page in range(last_page):
    result = requests.get(f"{URL}&startno={page*LIMIT}")
    soup = BeautifulSoup(result.text, "html.parser")
    results = soup.find_all("p", {"class" : "detail"})
    for result in results:
      title = result.find("span", {"class" : "rcrtTitle"}).find("a").get_text()

    results2 = soup.find_all("h3")
    for result in results2:
      company = result.find("a")
      if company == result.find("h3"):
        company = str(result.find("h3"))
      else:
        company = str(result.find("a").string)
      print({company + ':' + title})
  return jobs
    (main.py)
    from incruit import extract_incruit_pages, extract_incruit_jobs

last_incruit_page = extract_incruit_pages()

extract_incruit_jobs(last_incruit_page)
    残念なことに、総評:ウェブページは他のウェブページとは異なる構造(liで縛られたものなど)が等級化されていないので、学んだ内容より少し体現が少ない.(役職、社名).中間に会社名のない司会者でも解決できるのは良い経験です.(if文を使用).またstringのほかget text()を用いて文字列をキャプチャすることも学んだ.
    返信リンク
    CSSの追加方法を学ぶ
    私のVerlogでの成長過程